WO2018126740A1

WO2018126740A1 - Method and device for pushing information

Info

Publication number: WO2018126740A1
Application number: PCT/CN2017/103345
Authority: WO
Inventors: 徐光勇; 李光; 熊丽萍; 蒋智超; 杨铭
Original assignee: 百度在线网络技术（北京）有限公司
Priority date: 2017-01-04
Filing date: 2017-09-26
Publication date: 2018-07-12
Also published as: CN108268573A; CN108268573B

Abstract

The present application discloses a method and device for pushing information. A specific embodiment of the method comprises: acquiring geographical location information of a terminal of a user; acquiring geographical location information corresponding to a pre-stored item to be pushed; determining, on the basis of the geographical location information of the terminal, the geographical location information corresponding to the item to be pushed and a preset distance threshold, a set of items to be pushed and acquiring pre-generated feature information of each item to be pushed in the set of items to be pushed and a score of each item to be pushed; with respect to each item to be pushed in the set of items to be pushed, determining a matching level between pre-generated feature information of the user and the feature information of the item to be pushed; and selecting, on the basis of the score of each of the items to be pushed and the matching level between the feature information of the user and the feature information of each of the items to be pushed, an item to be pushed from the set of items to be pushed, and pushing to the terminal the selected item to be pushed and an associated item to be pushed in association with the selected item to be pushed. The embodiment improves the quality of the selected information.

Description

Method and apparatus for pushing information

Cross-reference to related applications

The present application claims the priority of the Japanese Patent Application Serial No. JP-A--------

Technical field

The present application relates to the field of computer technologies, and in particular, to the field of information processing technologies, and in particular, to a method and apparatus for pushing information.

Background technique

With the rapid development of applications based on User Generated Content (UGC), users can post comments, comments and opinions in such applications, integrating Internet users' comments, consumer exposure and social sentiment. User-originated content evaluation system can collect higher-rated merchants and lower-rated merchants, and recommend valuable commentary information and practical merchant information to consumers by discovering consumers' interests and interested merchants. In this way, consumers can be more comprehensively aware of merchants or commodities for consumers to make purchasing decisions. Therefore, it is particularly important to push targeted and high-quality business information and product information to consumers.

Summary of the invention

The purpose of the present application is to propose an improved method and apparatus for pushing information to solve the technical problems mentioned in the background section above.

In a first aspect, the present application provides a method for pushing information, including: acquiring geographic location information of a user's terminal; acquiring pre-stored geographic location information corresponding to the to-be-pushed item; The location information corresponding to the push item and the preset distance threshold determine the set of items to be pushed, and obtain the feature information of each item to be pushed in the pre-generated item set and the score of each item to be pushed; Item Determining, by each of the to-be-pushed items in the set, the degree of matching between the feature information of the pre-generated user and the feature information of the item to be pushed; based on the score of each item to be pushed, the feature information of the user, and the feature information of each item to be pushed Matching degree, selecting at least one item to be pushed in the to-be-push item set, and pushing the selected item to be pushed and the associated item to be pushed associated with the selected item to be pushed to the terminal.

In some embodiments, at least one item to be pushed is selected in the to-be-pushed item set based on the score of each item to be pushed, the feature information of the user, and the matching degree of the feature information of each item to be pushed, including: for each item to be pushed Determining whether the score of the item to be pushed is greater than a preset score threshold; if yes, dividing the item to be pushed into the first subset of items to be pushed; from the first subset of items to be pushed The at least one item to be pushed is selected according to the matching degree of the feature information of the user and the feature information of each item to be pushed in the first subset of the item to be pushed.

In some embodiments, at least one item to be pushed is selected in the to-be-pushed item set based on the score of each item to be pushed, the feature information of the user, and the matching degree of the feature information of each item to be pushed, including: for each item to be pushed And determining, according to each item to be pushed, whether the matching degree of the feature information of the user and the feature information of the item to be pushed is greater than a preset matching degree threshold; if yes, dividing the item to be pushed into the second subset of the item to be pushed And selecting at least one item to be pushed from the descending order of the scores of the items to be pushed in the second subset of the items to be pushed in the second subset of items to be pushed.

In some embodiments, pushing the selected item to be pushed and the associated item to be pushed associated with the selected item to be pushed to the terminal includes: acquiring an associated item to be pushed item associated with the selected item to be pushed; acquiring each Correlating the scores of the items to be pushed and the feature information of each of the associated items to be pushed; for each associated item to be pushed, determining the matching degree between the feature information of the associated item to be pushed and the feature information of the user; The score, the matching degree of the feature information of each associated item to be pushed and the feature information of the user, select at least one associated item to be pushed in the associated item to be pushed, and push the selected item to be pushed to the terminal.

In some embodiments, the method further includes: for each of the to-be-pushed items, the at least one score item associated with the item to be pushed and the pre-correspondence corresponding to each of the at least one score item Set weights and score each item to be pushed.

In some embodiments, the method further comprises: mining the feature information of the user in the behavior data of the user, wherein the behavior data comprises at least one of the following: location data, search information, and consumption information.

In some embodiments, the method further comprises: pushing, to the terminal, the comment information associated with the selected item to be pushed and the comment information of the associated item to be pushed associated with the selected item to be pushed.

In a second aspect, the present application provides an apparatus for pushing information, where the apparatus includes: a first acquiring unit configured to acquire geographic location information of a terminal of the user; and a second acquiring unit configured to acquire the pre-stored waiting The first determining unit is configured to determine, according to the geographical location information of the terminal, the geographic location information corresponding to the item to be pushed and the preset distance threshold, determine the to-be-pushed item set, and obtain the pre-generated waiting to be generated. The feature information of each item to be pushed and the score of each item to be pushed are pushed; the second determining unit is configured to determine feature information of the user generated in advance for each item to be pushed in the item set to be pushed. a matching degree with the feature information of the item to be pushed; the first pushing unit is configured to be based on the score of each item to be pushed, the matching degree of the feature information of the user and the feature information of each item to be pushed, in the item to be pushed Selecting at least one item to be pushed, and pushing the selected item to be pushed and the associated item to be pushed associated with the selected item to be pushed to the terminal

In some embodiments, the first pushing unit includes: a first determining module, configured to determine, for each of the items to be pushed, whether the score of the item to be pushed is greater than a preset score threshold; a dividing module, configured to divide the item to be pushed into a first subset of the item to be pushed; the first selecting module is configured to select, according to the characteristic information of the user, the first subset of the item to be pushed At least one item to be pushed is selected in order of matching of the feature information of each item to be pushed in the first subset of the push item.

In some embodiments, the first pushing unit further includes: a second determining module, configured to determine, for each of the to-be-pushed items, the matching of the feature information of the user with the feature information of the item to be pushed Whether the degree is greater than a preset matching degree threshold; the second dividing module is configured to: if yes, divide the item to be pushed into a second subset of the item to be pushed; and the second selecting module is configured to be used for the item to be pushed According to the second item to be pushed in the second sub-collection The scores of each item to be pushed in the subset are in descending order, and at least one item to be pushed is selected.

In some embodiments, the first pushing unit further includes: a first acquiring module configured to acquire an associated to-be-pushed item set associated with the selected item to be pushed; and a second obtaining module configured to acquire each association a score of the item to be pushed and feature information of each of the associated item to be pushed; a third determining module configured to determine, for each associated item to be pushed, a matching degree of the feature information of the item to be pushed and the feature information of the user; The pushing module is configured to select at least one associated to-be-pushed item in the associated to-be-push item set based on the score of each associated item to be pushed, the feature information of each associated item to be pushed, and the feature information of the user, and Push the selected association to be pushed.

In some embodiments, the apparatus further includes: a scoring unit configured to score each item to be pushed for each item to be pushed for each item to be pushed, based on the at least one score item associated with the item to be pushed and at least A preset weight corresponding to each of the sub-items is scored, and each item to be pushed is scored.

In some embodiments, the apparatus further includes: a mining unit configured to mine the feature information of the user in the behavior data of the user, wherein the behavior data includes at least one of the following: positioning data, search information, and consumption information.

In some embodiments, the apparatus further includes: a second pushing unit configured to push, to the terminal, the comment information associated with the selected item to be pushed and the comment information of the associated item to be pushed associated with the selected item to be pushed.

In a third aspect, the application further provides a server comprising: one or more processors; a memory for storing one or more programs; and when the one or more programs are executed by the one or more processors The above processor is implemented to implement the method for pushing information provided by the present application.

In a fourth aspect, the present application further provides a computer readable storage medium having stored thereon a computer program, the program being executed by a processor, such that the computer readable storage medium implements the method for pushing information provided by the present application .

The method and device for pushing information provided by the present application determine the to-be-pushed item set based on the acquired geographic location information of the user, the pre-stored geographic location information of the item to be pushed, and a preset distance threshold. Each item to be pushed in the push item collection a score, a feature information of each item to be pushed, and feature information of the pre-generated user, selecting at least one item to be pushed in the set of items to be pushed, and pushing the selected item to be pushed and the selected item to the user The association item to be pushed is associated with the push item, thereby improving the quality of the selected information and realizing more targeted information push.

DRAWINGS

Other features, objects, and advantages of the present application will become more apparent from the detailed description of the accompanying drawings.

1 is an exemplary system architecture diagram to which the present application can be applied;

2 is a flow diagram of one embodiment of a method for pushing information in accordance with the present application;

3 is an exemplary flowchart of an application scenario of a method for pushing information according to the present application;

4 is a flow chart of still another embodiment of a method for pushing information in accordance with the present application;

Figure 5 is a block diagram showing an embodiment of an apparatus for pushing information according to the present application;

6 is a block diagram showing the structure of a computer system suitable for implementing the server of the embodiment of the present application.

detailed description

The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention, rather than the invention. It is also to be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings.

FIG. 1 illustrates an exemplary system architecture 100 of an embodiment of a method for pushing information or a device for pushing information to which the present application may be applied.

As shown in FIG. 1, system architecture 100 can include

terminal devices

101, 102, 103, network 104, and server 105. The network 104 is used to provide a medium for communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various types of connections, such as wired, wireless communication links, fiber optic cables, and the like.

The user 110 can interact with the server 105 over the network 104 using the

terminal devices

101, 102, 103 to receive or transmit messages and the like. Various communication client applications, such as a shopping application, a map application, a navigation application, a search application, a web browser application, an instant communication tool, a mailbox client, and a social platform, may be installed on the

terminal devices

101, 102, and 103. Software, payment software, etc.

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting data reception and transmission, including but not limited to smartphones, tablets, smart watches, laptop portable computers, desktop computers, and the like.

The server 105 may be a server that provides various services, such as a background server that acquires geographical location information of the terminal, uses feature information of the user of the terminal, and pre-stored scores and feature information of the item to be pushed. The background server may perform processing such as analyzing the geographical location information of the obtained terminal, using the feature information of the user of the terminal, and the pre-stored scores and feature information of the item to be pushed, and processing the result (for example, the selected to be pushed to be pushed) The item and the associated item to be pushed associated with the selected item to be pushed are fed back to the terminal device.

It should be noted that the method for pushing information provided by the embodiment of the present application is generally performed by the server 105. Accordingly, the device for pushing information is generally disposed in the server 105.

It should be understood that the number of terminal devices, networks, and servers in Figure 1 is merely illustrative. Depending on the implementation needs, there can be any number of terminal devices, networks, and servers.

With continued reference to FIG. 2, a flow 200 of one embodiment of a method for pushing information in accordance with the present application is illustrated. The method for pushing information includes the following steps:

Step 201: Obtain geographic location information of the user's terminal.

In this embodiment, the electronic device (for example, the server shown in FIG. 1) on which the method for pushing information runs can obtain the geographical location information of the terminal from the terminal that the user uses for positioning by using a wireless connection. The above electronic devices can be set globally A satellite navigation system such as a Global Positioning System (GPS) or a BeiDou Navigation Satellite System (BDS) locates the terminal and acquires geographic location information of the terminal. The geographical location information may be longitude information and latitude information of the location of the terminal, for example, when the terminal is located in Tiananmen Square, Beijing, the geographic location information of the terminal may be 116 degrees 23 minutes 17 seconds east longitude and 39 degrees 54 minutes north latitude 27 Seconds; it may also be the name of the street where the terminal is located or the house number information of the location, for example, the intersection of Zhichun Road and Zhongguancun East Road, Haidian District, Beijing; or the landmark building near the location of the terminal Object or landmark location, for example, Exit B of Peking University Dongmen Subway Station.

Step 202: Acquire pre-stored geographic location information corresponding to the item to be pushed.

In this embodiment, the electronic device may acquire the geographical location information in the attribute information of the item to be pushed stored in advance. The electronic device may pre-store a plurality of items to be pushed, wherein the items to be pushed may be merchant information, product information, event information, coupon information, and the like. The item to be pushed may correspond to a plurality of attribute information, for example, geographic location information corresponding to the item to be pushed (also referred to as a Position Of Interest (POI)), and an industry category to which the item to be pushed belongs (for example, a catering category) , tourism, clothing and apparel, etc.), characteristic information of the item to be pushed (for example, good service attitude, high cost performance, fresh ingredients, etc.), evaluation information, exposure information and public opinion information of the item to be pushed. The electronic device may obtain the exposure information and the public opinion information of the to-be-pushed item from a news application or an application based on user-originated content (for example, word of mouth, Sina Weibo, etc.). The above exposure information usually refers to the negative information revealed. The above-mentioned public opinion information can also be called public opinion information, which refers to the occurrence, development and change of the intermediary social events in a certain social space. The public opinion generated by the social managers, enterprises, individuals, and other organizations as well as their political, social, and moral orientations may be positive, negative, or neutral.

Step 203: Determine, according to the geographic location information of the terminal, the geographic location information corresponding to the item to be pushed and the preset distance threshold, determine the to-be-push item set, and obtain feature information of each to-be-push item in the pre-generated item to be pushed item. The score of each item to be pushed.

In this embodiment, the electronic device acquires the geographical location information of the terminal in step 201, and obtains the geographical location letter corresponding to the to-be-pushed item in step 202. After the information, the distance between the geographic location of the terminal and the geographic location corresponding to the to-be-pushed item may be determined, and the distance is compared with a preset distance threshold, and the distance corresponding to the preset distance threshold is obtained. The item to be pushed is generated, and the item to be pushed is generated; after that, the feature information of each item to be pushed in the set of to-be-pushed items and the score of each item to be pushed are acquired, wherein the feature information may be described above. The information of the feature to be pushed, the feature information may also be referred to as tag information, that is, the information identifying the feature of the item to be pushed. For example, when the item to be pushed is the catering business information, the feature information may be clean and hygienic. When the above-mentioned item to be pushed is service product information (for example, nail service information, beauty service information, etc.), the characteristic information may be a good service attitude, a gift, and the like. The score of the above-mentioned item to be pushed may be an evaluation score of the netizen for the push item, for example, five stars or 9.8 points, etc.; or may be an evaluation score calculated according to the comment information, exposure information, and public opinion information of the net user's push item. .

In this embodiment, the electronic device may extract or mine the feature information from the comment information of the item to be pushed. The electronic device may first extract each piece of comment information of the item to be pushed; then, segment the piece of comment information, and generate a set of comment words; finally, set the comment word set and the feature in the preset feature information library The information is matched, and the matched feature information is used as the feature information of the to-be-pushed item. When the item to be pushed is the merchant information, the electronic device may extract the feature information of the merchant information from the business scope in the registration information corresponding to the merchant corresponding to the merchant information, for example, from the merchant. The main types of cuisine operated by the merchant are extracted from the business scope, such as Hunan cuisine, Cantonese cuisine, and Minnan cuisine. The electronic device may further obtain exposure information and public opinion information of the to-be-pushed item from a news application or an application based on user-originated content, and extract feature information of the to-be-pushed item from the exposure information and the public opinion information.

In some optional implementation manners of the embodiment, the electronic device may score each item to be pushed. First, a score item for scoring the item to be pushed may be obtained, and the above item may be comment information, exposure information, and public opinion information; afterwards, some sentiment classification models may be utilized (eg, Conditional Random Fields (CRFs) ), Support Vector Machine (SVM), etc.) The information is classified into emotions, and the comment information can be divided into positive comment information, negative comment information and neutral comment information (no emotional comment information), and the sentiment information can be classified into emotions by using the sentiment classification model, and the public opinion information can be divided into positive Lyric information, negative public opinion information and neutral public opinion information (no emotional public opinion information). Then, a preset weight value corresponding to each of the above-mentioned rating items may be acquired, for example, the weighting value of the exposure information, the review information, and the public opinion information may be set according to the importance level of the rating. Finally, calculating a product of the number of each scored item and the preset weight value of the scored item, and adding the respective products to obtain a score of the item to be pushed, wherein the electronic device can automatically recognize the score when performing the scoring operation To score the emotional color of the sub-item, if the sub-item is negative information, you can add a negative sign (-) before the obtained product or multiply the obtained product by the value of "-1" as the product result; if the score is neutral information , you can set the weight value of the score to 0. As an example, when the exposure information has a weight value of -3, the positive comment information has a weight value of 2, the negative comment information has a weight value of -2, the positive lyric information has a weight value of 1, and the negative lyric information has a weight value of -1. At the time, the exposure information is 1, the positive comment information is 15, the negative comment information is 2, the positive lyric information is 3, and the negative lyric information is 1. The score of the item to be pushed is 25 .

Step 204: Determine, for each item to be pushed in the set of items to be pushed, a degree of matching between the feature information of the pre-generated user and the feature information of the item to be pushed.

In this embodiment, the electronic device may first acquire feature information of the user, and the feature information of the user may also be referred to as image information of the user, which is abstracted according to information such as social attributes, living habits, and consumption behavior of the user. A tagged message. For example, the user's characteristic information may be extracted according to the national information in the basic information of the user. For example, if the nationality of the user is a Hui nationality, the characteristic information of the user may be extracted as “halal”; according to the user's living habits, for example, focusing on health care, The user can extract the feature information of the user, such as cleaning, and can also extract the user's feature information according to the user's eating habits, consumption information, and the like. Then, for each item to be pushed in the set of items to be pushed determined in step 203, the matching degree of the feature information of the user and the feature information of the item to be pushed may be determined, and the electronic device may set the feature information of the user with The feature information of the item to be pushed is matched one by one, and the degree of matching between the feature information of the user and the feature information of the item to be pushed is determined according to the matched number. For example, if the feature information of the item to be pushed includes the characteristics of the above user The feature information of the information to be pushed may be completely matched with the feature information of the user, that is, the matching degree is 1; if the feature information of the to-be-pushed item includes the characteristics of the user The part of the feature information in the information may determine that the feature information of the item to be pushed has a partial matching relationship with the feature information of the user, and the matching degree may be determined according to the quantity of the matching relationship; and if the feature information of the item to be pushed does not Including any feature information in the feature information of the user, it may be determined that the feature information of the item to be pushed has a mismatch relationship with the feature information of the user, that is, the matching degree is 0.

In some optional implementation manners of the embodiment, before determining the matching degree between the feature information of the user and the to-be-pushed item or the associated item to be pushed, the behavior data of the user may be first mined to generate the user. Feature information, wherein the behavior data may include positioning data of the user, such as determining the preference of the user for the restaurant type according to the positioning data of the user during the peak period of the meal; the behavior data may also include the user's search information, such as the user Searching for "Beijing Authentic Sichuan Restaurant" in the search engine, the user's characteristic information "Steamed", "Spicy", etc. can be extracted according to this search information; the above behavior data can also include the user's consumption information, such as the user spending in the western restaurant If the number of times is large, the user's characteristic information "Western food" can be extracted.

Step 205: Select at least one item to be pushed in the to-be-push item set based on the score of each item to be pushed, the feature information of the user, and the matching degree of the feature information of each item to be pushed, and push the selected item to be pushed to the terminal. And the associated item to be pushed associated with the selected item to be pushed.

In this embodiment, the electronic device may be based on the score of each item to be pushed acquired in step 203 and the matching degree of the feature information of the user determined in step 204 and the feature information of each item to be pushed, in the to-be-push item set. Selecting at least one item to be pushed, for example, all the items to be pushed with a matching degree of 1 may be pushed, or all items to be pushed except the matching degree of 0 may be pushed; and a part of the item to be pushed with a matching degree of 1 may also be pushed; Then, the selected to-be-pushed item and the associated to-be-pushed item associated with the selected item to be pushed are pushed to the terminal, wherein the electronic device can perform big data analysis on the obtained plurality of items to be pushed. The probability that the user views, purchases, clicks, etc. on the second item to be pushed at the same time as or after the operation of viewing, purchasing, clicking, etc., the first item to be pushed, The second item to be pushed corresponding to the probability that is greater than the preset probability threshold is set as the associated item to be pushed of the first item to be pushed. The associated to-be-pushed item may be an associated to-be-push item associated with the selected scene information to be pushed. For example, when the item to be pushed is the catering business information, the associated item to be pushed of the item to be pushed may be The entertainment venue information (such as movie theater information, board game club information, etc.) in the vicinity of the catering business; or the item to be pushed associated with the geographical location information corresponding to the selected item to be pushed, for example, when the item to be pushed is In the case of the product information, the associated item to be pushed of the item to be pushed may be the merchant information of the merchant to which the item corresponding to the item information is sold, or the item information of other items in the merchant.

In this embodiment, the electronic device may select at least one item to be pushed from the set of items to be pushed according to the score of each item to be pushed according to the scores of the items to be pushed, or may be based on the feature information of the user. The matching degree of the feature information of each item to be pushed is selected from the set of items to be pushed in the order that the matching degree is large to small, and at least one item to be pushed is selected.

In some optional implementations of the embodiment, the electronic device may first acquire an associated to-be-push item set associated with the selected item to be pushed, which is generated in advance according to an algorithm such as big data analysis; a score of each associated item to be pushed in the set of push items and feature information of each associated item to be pushed; and then, for each item to be pushed, determining feature information of the item to be pushed and feature information of the user The matching degree may be determined by determining the number of the feature information in which the feature information of the associated to-be-pushed item matches the feature information of the user, and finally, the matching degree may be determined based on the score of each associated item to be pushed, and each associated item to be pushed. And matching the feature information with the feature information of the user, selecting at least one associated item to be pushed in the set of associated to-be-push items, and pushing the selected item to be pushed to the terminal, wherein the electronic device may be associated The number of points to be pushed is in the order of the above-mentioned association items to be pushed Selecting at least one associated item to be pushed; or selecting at least one associated item to be pushed in the associated to-be-push item set in descending order of matching degree; and determining whether the score of the associated item to be pushed is greater than a preset score The threshold value is used to push the associated to-be-pushed item whose score is greater than the preset score threshold to the user; or whether the matching degree between the feature information of the associated item to be pushed and the feature information of the user is greater than a preset The matching threshold is used to push the associated to-be-pushed item whose matching degree is greater than the preset matching degree threshold to the user.

In some optional implementation manners of the embodiment, the electronic device may further push, to the terminal, the comment information associated with the selected item to be pushed and the comment information of the associated item to be pushed associated with the selected item to be pushed. For the above users to make decisions based on the comment information.

The method provided by the foregoing embodiment of the present application, by associating the feature information and the behavior information of the user with the feature information and the score of the item to be pushed, pushes the item to be pushed to the user, and also pushes the association to be associated with the item to be pushed. Push items, which improves the quality of the selected information and enables more targeted information push.

With continued reference to FIG. 3, FIG. 3 is an exemplary flowchart of an application scenario of a method for pushing information in accordance with the present application. In FIG. 3, the background information push server may first perform big data analysis on the behavior data in the user's behavior database 311 to generate feature information of the user; and then, extract the geography of the item to be pushed from the attribute information database 312 of the item to be pushed. The location information, the industry category and the feature information are further determined according to the comment information, the exposure information, and the public opinion information in the rating item library 313 of the item to be pushed, and then generated based on the geographic location information of each item to be pushed. The item set to be pushed is further selected according to the score of each item to be pushed, the feature information of each item to be pushed, and the feature information of the user, at least one item to be pushed is selected in the to-be-push item set; finally, the selected item to be pushed is pushed to the user. Item and/or associated information to be pushed and/or comment information of the item to be pushed associated with the item to be pushed. The background information push server may further add the comment information published by the user to the rating item library 313 of the item to be pushed.

With further reference to FIG. 4, a flow 400 of yet another embodiment of a method for pushing information is shown. The process 400 of the method for pushing information includes the following steps:

Step 401: Obtain geographic location information of the user's terminal.

In this embodiment, the electronic device (for example, the server shown in FIG. 1) on which the method for pushing information runs can obtain the geographical location information of the terminal from the terminal that the user uses for positioning by using a wireless connection. The above electronic device can locate the terminal through a satellite navigation system such as a global positioning system and a China Beidou satellite navigation system, and acquire geographic location information of the terminal. The above geographical location information may be the above terminal The longitude information and the latitude information of the location; the street name or the house number information of the location where the terminal is located; or the landmark building or the landmark location near the location of the terminal.

Step 402: Acquire pre-stored geographic location information corresponding to the item to be pushed.

In this embodiment, the electronic device may acquire geographical location information in an attribute of a pre-stored item to be pushed. The electronic device may pre-store a plurality of items to be pushed, wherein the items to be pushed may be merchant information, product information, event information, coupon information, and the like. The item to be pushed may correspond to multiple attributes, for example, geographic location information corresponding to the item to be pushed, industry category to which the item to be pushed belongs, feature information of the item to be pushed, evaluation information, exposure information, and public opinion information of the item to be pushed, and the like. . The electronic device may acquire the exposure information and the public opinion information of the to-be-pushed item from a news application or an application mainly based on user-originated content. The above exposure information usually refers to the negative information revealed. The above-mentioned public opinion information can also be called public opinion information, which refers to the occurrence, development and change of the intermediary social events in a certain social space. The public opinion generated by the social managers, enterprises, individuals, and other organizations as well as their political, social, and moral orientations may be positive, negative, or neutral.

Step 403: Determine, according to the geographic location information of the terminal, the geographic location information corresponding to the item to be pushed and the preset distance threshold, determine the to-be-push item set, and obtain feature information of each to-be-push item in the pre-generated item to be pushed item. The score of each item to be pushed.

In this embodiment, the electronic device acquires the geographical location information of the terminal in step 401, and after obtaining the geographical location information corresponding to the to-be-pushed item in step 402, the geographic location of the terminal and the to-be-determined The distance between the geographic locations corresponding to the item is compared, and the distance is compared with the preset distance threshold, and the to-be-pushed item corresponding to the distance that is less than the preset distance threshold is obtained, and the item to be pushed is generated; The feature information of each to-be-pushed item in the foregoing set of to-be-pushed items and the score of each to-be-pushed item may be acquired, where the feature information may be information describing the feature of the item to be pushed, and the feature information may also be It is called label information, that is, information identifying the characteristics of the item to be pushed. For example, when the item to be pushed is the catering business information, the characteristic information may be clean, large amount of vegetables, authentic northeast food, etc. When the push item is the service item information, the feature information may be a good service attitude, a gift, and the like. The score of the above-mentioned item to be pushed may be an evaluation score of the netizen for the push item, for example, five stars or 9.8 points, etc.; or may be an evaluation score calculated according to the comment information, exposure information, and public opinion information of the net user's push item. .

Step 404: Determine, for each item to be pushed in the set of items to be pushed, a degree of matching between the feature information of the pre-generated user and the feature information of the item to be pushed.

In this embodiment, the electronic device may first acquire feature information of the user, and the feature information of the user may also be referred to as image information of the user, which is abstracted according to information such as social attributes, living habits, and consumption behavior of the user. A tagged message. For example, the user's characteristic information may be extracted according to the national information in the basic information of the user; the user's living habits may be extracted according to the user's living habits, for example, focusing on health care, cleanliness, etc.; and the user's eating habits, consumption information, etc. may also be extracted. User's feature information. Then, for each item to be pushed in the set of items to be pushed determined in step 403, the matching degree of the feature information of the user and the feature information of the item to be pushed may be determined, and the electronic device may set the feature information of the user with The feature information of the item to be pushed is matched one by one, and the degree of matching between the feature information of the user and the feature information of the item to be pushed is determined according to the matched number. For example, if the feature information of the to-be-pushed item includes all the feature information in the feature information of the user, the feature information of the item to be pushed may be determined as described above. The feature information of the user has an exact matching relationship, that is, the matching degree is 1; if the feature information of the to-be-pushed item includes part of the feature information in the feature information of the user, the feature information of the item to be pushed and the user may be determined. The feature information has a partial matching relationship, and the matching degree may be determined according to the number of matching relationships; and if the feature information of the to-be-pushed item does not include any feature information in the feature information of the user, the to-be-pushed item may be determined. There is a mismatch between the feature information and the feature information of the above user, that is, the matching degree is 0.

Step 405: Determine, for each item to be pushed in each item to be pushed, whether the score of the item to be pushed is greater than a preset score threshold.

In this embodiment, for each of the items to be pushed, the electronic device may determine whether the score of the item to be pushed is greater than a preset score threshold, and the score threshold may be manually set manually, or It is the default of the above electronic devices. For example, if the score of 5 is very satisfactory and the score of 4 is satisfactory, the score threshold can be set to 4 points. When it is determined that the score of the item to be pushed is greater than a preset score threshold, step 406 may be performed.

Step 406: If the score of the item to be pushed is greater than a preset score threshold, divide the item to be pushed into the first subset of items to be pushed.

In this embodiment, if the score of the item to be pushed is greater than the preset score threshold, the electronic device may divide the item to be pushed into the first subset of the item to be pushed, that is, the first subset of the item to be pushed. The items to be pushed in the item may be items to be pushed whose score is greater than a preset score threshold. After the item to be pushed is divided into the first subset of items to be pushed, step 407 is performed.

Step 407: Select at least one item to be pushed from the first to last group of items to be pushed according to the matching degree of the feature information of the user and the feature information of each item to be pushed in the first subset of the item to be pushed. .

In this embodiment, the first sub-set of the item to be pushed may be selected according to the matching degree of the feature information of the user and the feature information of each item to be pushed in the first subset of the item to be pushed, in descending order. At least one item to be pushed. If the item to be pushed is selected, the item to be pushed is one item to be pushed with the largest matching degree; if three items to be pushed are selected, the matching degree is sorted into the top three items to be pushed. After selecting the item to be pushed, execute Step 411.

Step 408: Determine, for each item to be pushed in each item to be pushed, whether the matching degree between the feature information of the user and the feature information of the item to be pushed is greater than a preset matching degree threshold.

In this embodiment, for each item to be pushed, the electronic device may determine whether the matching degree between the feature information of the user and the feature information of the item to be pushed is greater than a preset matching degree threshold, and the matching is performed. The degree threshold may be manually set manually, or may be defaulted by the above electronic device, for example, setting the matching threshold to 0.8. When it is determined that the matching degree between the feature information of the user and the feature information of the to-be-pushed item is greater than a preset matching degree threshold, step 409 may be performed.

Step 409: If the matching degree of the feature information of the user and the feature information of the item to be pushed is greater than a preset matching degree threshold, the item to be pushed is divided into the second subset of the item to be pushed.

In this embodiment, if the matching degree between the feature information of the user and the feature information of the item to be pushed is greater than a preset matching degree threshold, the electronic device may divide the item to be pushed into the second subset of the item to be pushed. The items to be pushed in the second subset of the items to be pushed may be the items to be pushed whose matching degree is greater than the preset matching degree threshold. After the item to be pushed is divided into the second subset of items to be pushed, step 410 is performed.

Step 410: Select at least one item to be pushed from the second sub-set of items to be pushed according to the order of the scores of each item to be pushed in the second subset of items to be pushed.

In this embodiment, at least one item to be pushed may be selected from the second subset of the items to be pushed in the order of the scores of the items to be pushed in the second subset of items to be pushed. If the item to be pushed is selected, the item to be pushed is the item to be pushed with the largest score; if the item to be pushed is selected, the item to be pushed is sorted into the top three items to be pushed. After the item to be pushed is selected, step 411 is performed.

Step 411: Push the selected item to be pushed and the associated item to be pushed associated with the selected item to be pushed to the terminal.

In this embodiment, after selecting the item to be pushed from step 407 or step 410, the electronic device may push the selected item to be pushed and the associated item to be pushed associated with the selected item to be pushed to the terminal, wherein The above electronic devices can be obtained through the acquisition The data to be pushed for big data analysis shows that the probability that the user views, purchases, clicks, etc. on the second item to be pushed at the same time as or after the first item to be pushed, is greater than The second item to be pushed corresponding to the probability of the preset probability threshold is set as the associated item to be pushed of the first item to be pushed. The associated to-be-pushed item may be an associated to-be-push item associated with the selected scene information to be pushed. For example, when the item to be pushed is the catering business information, the associated item to be pushed of the item to be pushed may be The entertainment information in the vicinity of the catering business; or the item to be pushed associated with the geographical location information corresponding to the selected item to be pushed, for example, when the item to be pushed is the item information, the association of the item to be pushed is to be The push item may be the merchant information of the merchant sold by the item corresponding to the item information, or the item information of other items in the merchant.

As can be seen from FIG. 4, the flow 400 of the method for pushing information in the present embodiment highlights the step of selecting a push item as compared with the embodiment corresponding to FIG. Therefore, the solution described in this embodiment can introduce more methods for selecting a to-be-pushed item, thereby improving the quality of the selected information, and implementing more targeted information push.

With further reference to FIG. 5, as an implementation of the method shown in the above figures, the present application provides an embodiment of an apparatus for pushing information, the apparatus embodiment corresponding to the method embodiment shown in FIG. The device can be specifically applied to various electronic devices.

As shown in FIG. 5, the apparatus 500 for pushing information according to this embodiment includes: a first obtaining unit 501, a second obtaining unit 502, a first determining unit 503, a second determining unit 504, and a first pushing unit 505. . The first obtaining unit 501 is configured to acquire the geographical location information of the terminal of the user; the second obtaining unit 502 is configured to acquire the geographical location information corresponding to the pre-stored item to be pushed; the first determining unit 503 is configured to be configured to be based on the a geographic location information of the terminal, a geographic location information corresponding to the to-be-pushed item, and a preset distance threshold, determining a to-be-pushed item set, and acquiring feature information of each to-be-pushed item in the to-be-pushed item set generated in advance a score of each item to be pushed; the second determining unit 504 is configured to determine, for each item to be pushed in the set of items to be pushed, the feature information of the user that is generated in advance and the feature information of the item to be pushed a matching degree; the first pushing unit 505 is configured to select at least one to be pushed in the to-be-pushed item set based on a score of each item to be pushed, a matching degree of the feature information of the user, and feature information of each item to be pushed. And pushing the selected item to be pushed and the selected one to the terminal The associated item to be pushed associated with the item to be pushed.

In this embodiment, the first acquiring unit 501 of the apparatus 500 for pushing information may obtain the geographical location information of the terminal from the terminal that the user uses for positioning by using a wireless connection manner. The first acquiring unit 501 can locate the terminal by using a satellite navigation system such as a global positioning system or a China Beidou satellite navigation system, and acquire geographic location information of the terminal. The geographical location information may be the longitude information and the latitude information of the location of the terminal; or the street name of the terminal or the house number information of the location; or the landmark building near the location of the terminal. Or iconic location.

In this embodiment, the second obtaining unit 502 of the apparatus 500 for pushing information may acquire the geographical location information in the attribute of the pre-stored item to be pushed. The second obtaining unit 502 may store a plurality of items to be pushed in advance, wherein the items to be pushed may be merchant information, product information, event information, coupon information, and the like. The item to be pushed may correspond to multiple attributes, for example, geographic location information corresponding to the item to be pushed, industry category to which the item to be pushed belongs, feature information of the item to be pushed, evaluation information, exposure information, and public opinion information of the item to be pushed, and the like. . The second obtaining unit 502 may obtain the exposure information and the public opinion information of the item to be pushed from the news application or the application mainly based on the user original content. The above exposure information usually refers to the negative information revealed. The above-mentioned public opinion information can also be called public opinion information, which refers to the occurrence, development and change of the intermediary social events in a certain social space. The public opinion generated by the social managers, enterprises, individuals, and other organizations as well as their political, social, and moral orientations may be positive, negative, or neutral.

In this embodiment, after the first acquiring unit 501 acquires the geographical location information of the terminal, and after the second acquiring unit 502 acquires the geographical location information corresponding to the to-be-pushed item, the first determining unit 503 may determine The distance between the geographic location of the terminal and the geographic location corresponding to the to-be-pushed item, and the distance is compared with the preset distance threshold, and the to-be-pushed item corresponding to the distance that is less than the preset distance threshold is obtained. And generating the to-be-pushed item; and then acquiring the feature information of each of the to-be-pushed items in the set of the to-be-pushed items and the score of each item to be pushed, wherein the feature information may be a feature describing the item to be pushed. Information, the above characteristic information It may also be referred to as tag information, that is, information identifying the characteristics of the item to be pushed. The score of the above-mentioned item to be pushed may be the evaluation score of the net item for the push item; or may be the evaluation score calculated according to the comment information, the exposure information, and the public opinion information of the push item of the netizen.

In this embodiment, the second determining unit 504 of the apparatus 500 for pushing information may first acquire the feature information of the user, and the feature information of the user may also be referred to as the portrait information of the user, which refers to the social attribute and life according to the user. A tagged message abstracted from information such as habits and consumer behavior. For example, the feature information of the user may be extracted according to the ethnic information in the basic information of the user; the feature information of the user may be extracted according to the living habit of the user; and the feature information of the user may be extracted according to the eating habits, consumption information, and the like of the user. Then, for each item to be pushed determined in the first determining unit 503, the matching degree of the feature information of the user and the feature information of the item to be pushed may be determined, and the electronic device may use the user. The feature information is matched with the feature information of the item to be pushed one by one, and the matching degree between the feature information of the user and the feature information of the item to be pushed is determined according to the matched number.

In this embodiment, the first pushing unit 505 may be based on the scores of the respective items to be pushed acquired in the first determining unit 503 and the feature information of the user determined in the second determining unit 504 and the characteristics of each item to be pushed. Selecting at least one item to be pushed in the to-be-pushed item set; after that, the selected item to be pushed and the associated item to be pushed associated with the selected item to be pushed may be pushed to the terminal, where the first The pushing unit 505 can perform big data analysis on the obtained plurality of items to be pushed, and obtain that the second item to be pushed is viewed by the user while viewing, purchasing, clicking, and the like of the first item to be pushed. The probability of the operation, such as the purchase, the click, and the like, sets the second item to be pushed corresponding to the probability of the preset probability threshold to be the associated item to be pushed of the first item to be pushed. The association to be pushed item may be the associated item to be pushed associated with the selected scene information to be pushed, or may be the item to be pushed associated with the selected location information corresponding to the item to be pushed.

In some optional implementation manners of the embodiment, the first pushing unit 505 may include a first determining module (not shown), a first dividing module (not shown), and a first selecting module ( Not shown in the figure). The first determining module may determine whether the score of the item to be pushed is greater than a preset for each item to be pushed in each item to be pushed. a score threshold, the score threshold may be manually set manually, or may be defaulted by the electronic device; after the first determining module determines that the score of the item to be pushed is greater than a preset score threshold, the first division The module may divide the item to be pushed into the first subset of the item to be pushed, that is, the item to be pushed in the first subset of the item to be pushed may be a item to be pushed whose score is greater than a preset score threshold; The first selection module may select at least one of the first subset of the to-be-pushed items according to the matching degree of the feature information of the user and the feature information of each item to be pushed in the first subset of the item to be pushed. Items to be pushed.

In some optional implementation manners of the embodiment, the first pushing unit 505 may further include a second determining module (not shown), a second dividing module (not shown), and a second selecting module. (not shown in the figure). The second determining module may determine whether the matching degree between the feature information of the user and the feature information of the to-be-pushed item is greater than a preset matching degree threshold, and the matching degree threshold is used for each of the items to be pushed. It may be manually set manually, or may be defaulted by the foregoing electronic device; after the second determining module determines that the matching degree between the feature information of the user and the feature information of the to-be-pushed item is greater than a preset matching degree threshold, The second dividing module may divide the to-be-pushed item into the second subset of the item to be pushed, that is, the item to be pushed in the second subset of the to-be-pushed item may be a matching degree that is greater than a preset matching degree threshold. Pushing the item; finally, the second selecting module may select at least one item to be pushed from the second subset of the item to be pushed according to the order of the points of each item to be pushed in the second subset of the item to be pushed, in descending order .

In some optional implementation manners of the embodiment, the first pushing unit 505 may further include a first acquiring module (not shown), a second acquiring module (not shown), and a third determining module. (not shown in the figure) and push module (not shown). The first acquiring module may first acquire an associated to-be-pushed item set that is associated with the selected item to be pushed, which is generated in advance according to an algorithm such as a big data analysis; and then the second acquiring module may obtain the related item to be pushed in the set. Each of the associated scores of the items to be pushed and the feature information of each of the associated items to be pushed; and, for each associated item to be pushed, the third determining module may determine the feature information of the associated item to be pushed and the characteristics of the user The degree of matching of the information may be determined by determining the number of the feature information of the association of the feature to be pushed and the feature information of the user; and finally, the pushing module Determining at least one associated item to be pushed in the associated to-be-push item set based on the score of each associated item to be pushed, the feature information of each associated item to be pushed, and the feature information of the user, and pushing the item to the terminal a selected item to be pushed, wherein the electronic device may select at least one associated item to be pushed in the associated item to be pushed item in descending order of the score of the item to be pushed; or The small order selects at least one associated item to be pushed in the set of associated to-be-push items; and may further determine whether the score of the associated item to be pushed is greater than a preset score threshold, and the associated item to be pushed is greater than the preset score threshold. Pushing to the user; determining whether the matching degree of the feature information of the associated to-be-pushed item and the feature information of the user is greater than a preset matching degree threshold, and pushing the associated to-be-pushed item whose matching degree is greater than a preset matching degree threshold user.

In some optional implementations of this embodiment, the apparatus 500 for pushing information may further include a scoring unit (not shown). First, the scoring unit may obtain a scoring item for scoring the item to be pushed, and the scoring item may be comment information, exposure information, and public opinion information; and then, some sentiment classification models may be utilized (eg, conditional random field, support vector) Emotion classification of comment information, the comment information can be divided into positive comment information, negative comment information and neutral comment information, and the sentiment information can be classified into emotions by using these sentiment classification models, and the public opinion information can be divided into positive Lyric information, negative public opinion information and neutral public opinion information. Then, a preset weight value corresponding to each of the above-mentioned rating items may be acquired, for example, the weighting value of the exposure information, the review information, and the public opinion information may be set according to the importance level of the rating. Finally, calculating a product of the number of each scored item and the preset weight value of the scored item, and adding the respective products to obtain a score of the item to be pushed, wherein the electronic device can automatically recognize the score when performing the scoring operation To score the emotional color of the sub-item, if the sub-item is negative information, you can add a negative sign (-) before the obtained product or multiply the obtained product by the value of "-1" as the product result; if the score is neutral information , you can set the weight value of the score to 0.

In some optional implementations of this embodiment, the apparatus 500 for pushing information may further include a mining unit (not shown). Before determining the matching degree between the feature information of the user and the item to be pushed or the item to be pushed, the mining unit may first perform mining on the behavior data of the user to generate the feature information of the user, where The foregoing behavior data may include positioning data of the user; the behavior data may also include search information of the user; the behavior data may further include consumption information of the user.

In some optional implementations of this embodiment, the apparatus 500 for pushing information may further include a second push unit (not shown). The second pushing unit may further push the selected comment information associated with the item to be pushed and the comment information of the associated item to be pushed associated with the selected item to be pushed to the terminal for the user to make a decision according to the comment information.

Those skilled in the art will appreciate that the apparatus 500 for pushing information described above also includes some other well-known structures, such as a processor, a memory, etc., which are not shown in FIG. 5 in order to unnecessarily obscure the embodiments of the present disclosure. Out.

Referring now to Figure 6, a block diagram of a computer system 600 suitable for use in implementing a server in accordance with an embodiment of the present invention is shown. The server shown in FIG. 6 is merely an example, and should not impose any limitation on the function and scope of use of the embodiments of the present application.

As shown in FIG. 6, computer system 600 includes a central processing unit (CPU) 601 that can be loaded into a program in random access memory (RAM) 603 according to a program stored in read only memory (ROM) 602 or from storage portion 608. And perform various appropriate actions and processes. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also coupled to bus 604.

The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a storage portion 608 including a hard disk or the like. And a communication portion 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the Internet. Driver 610 is also coupled to I/O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like, is mounted on the drive 610 as needed so that a computer program read therefrom is installed into the storage portion 608 as needed.

In particular, the processes described above with reference to the flowcharts may be implemented as a computer software program in accordance with an embodiment of the present disclosure. For example, an embodiment of the present disclosure includes a computer program product comprising a computer program carried on a computer readable medium, the computer program The program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via communication portion 609, and/or installed from removable media 611. When the computer program is executed by the central processing unit (CPU) 601, the above-described functions defined in the method of the present application are performed. It should be noted that the computer readable medium described herein may be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain or store a program, which can be used by or in connection with an instruction execution system, apparatus or device. In the present application, a computer readable signal medium may include a data signal that is propagated in the baseband or as part of a carrier, carrying computer readable program code. Such propagated data signals can take a variety of forms including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer readable signal medium can also be any computer readable medium other than a computer readable storage medium, which can transmit, propagate, or transport a program for use by or in connection with the instruction execution system, apparatus, or device. . Program code embodied on a computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality and operation of possible implementations of systems, methods and computer program products in accordance with various embodiments of the invention. In this regard, each block of the flowchart or block diagram can represent a module, a program segment, or a portion of code that includes one or more of the logic functions for implementing the specified. Executable instructions. It should also be noted that in some alternative implementations, the functions noted in the blocks may also occur in a different order than that illustrated in the drawings. For example, two successively represented blocks may actually be executed substantially in parallel, sometimes It can also be performed in the reverse order, depending on the function involved. It is also noted that each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts, can be implemented in a dedicated hardware-based system that performs the specified function or operation. Or it can be implemented by a combination of dedicated hardware and computer instructions.

The units involved in the embodiments of the present invention may be implemented by software or by hardware. The described unit may also be disposed in the processor, for example, as a processor including a first acquisition unit, a second acquisition unit, a first determination unit, a second determination unit, and a first push unit. The names of these units do not in any way constitute a limitation on the unit itself. For example, the first acquisition unit may also be described as “a unit that acquires geographic location information of the user's terminal”.

In another aspect, the present application also provides a computer readable medium, which may be included in the apparatus described in the above embodiments, or may be separately present and not incorporated into the apparatus. The computer readable medium carries one or more programs. When the one or more programs are executed by the device, the device is configured to: obtain geographic location information of the user's terminal; and obtain pre-stored geographic location information corresponding to the item to be pushed. And determining, according to the geographic location information of the terminal, the geographic location information corresponding to the item to be pushed and the preset distance threshold, determining the to-be-pushed item set, and acquiring the feature information of each to-be-pushed item in the pre-generated set of items to be pushed and each a score of the item to be pushed; determining, for each item to be pushed in the set of items to be pushed, a degree of matching between the feature information of the pre-generated user and the feature information of the item to be pushed; based on the score of each item to be pushed, the characteristics of the user Matching the information with the feature information of each item to be pushed, selecting at least one item to be pushed in the to-be-push item set, and pushing the selected item to be pushed and the associated item to be pushed associated with the selected item to be pushed to the terminal .

The above description is only a preferred embodiment of the invention and a description of the principles of the applied technology. It should be understood by those skilled in the art that the scope of the invention referred to in the present invention is not limited to the specific combination of the above technical features, and should also be covered by the above technical features or without departing from the above inventive concept. Other technical solutions formed by arbitrarily combining the equivalent features. For example, the above features are combined with the technical features disclosed in the present invention, but are not limited to the technical features having similar functions.

Claims

A method for pushing information, the method comprising:

Obtaining geographic location information of the user's terminal;

Obtaining the geographical location information corresponding to the pre-stored item to be pushed;

Determining, according to the geographic location information of the terminal, the geographic location information corresponding to the to-be-pushed item and the preset distance threshold, determining a to-be-pushed item set, and acquiring each of the to-be-pushed item items in the to-be-pushed item set that is generated in advance Feature information and a score for each item to be pushed;

Determining a degree of matching between the feature information of the user and the feature information of the item to be pushed in advance for each item to be pushed in the set of items to be pushed;

Selecting at least one item to be pushed in the set of items to be pushed based on a score of each item to be pushed, a matching degree of the feature information of the user, and feature information of each item to be pushed, and pushing the selected item to the terminal a to-be-pushed item and an associated item to be pushed associated with the selected item to be pushed.
The method according to claim 1, wherein the matching of the scores of the items to be pushed, the feature information of the user, and the feature information of each item to be pushed is selected in the set of items to be pushed. At least one item to be pushed, including:

Determining, for each of the items to be pushed, each of the items to be pushed, whether the score of the item to be pushed is greater than a preset score threshold;

If yes, the item to be pushed is divided into the first subset of items to be pushed;

Selecting at least one of the first sub-set of the item to be pushed according to the matching degree of the feature information of the user and the feature information of each item to be pushed in the first subset of the item to be pushed, in descending order Items to be pushed.
The method according to claim 1, wherein the matching of the scores of the items to be pushed, the feature information of the user, and the feature information of each item to be pushed is selected in the set of items to be pushed. At least one item to be pushed, including:

Determining, for each of the to-be-pushed items, whether the matching degree of the feature information of the user and the feature information of the item to be pushed is greater than a preset matching degree threshold;

If yes, the item to be pushed is divided into the second subset of items to be pushed;

And selecting at least one item to be pushed from the second sub-set of the item to be pushed according to the order of the scores of the items to be pushed in the second subset of the item to be pushed.
The method according to any one of claims 1-3, wherein the pushing the selected item to be pushed and the associated item to be pushed associated with the selected item to be pushed to the terminal comprises:

Obtaining an associated to-be-pushed item set associated with the selected item to be pushed;

Obtaining a score of each associated item to be pushed and characteristic information of each associated item to be pushed;

For each associated item to be pushed, determining a matching degree between the feature information of the associated item to be pushed and the feature information of the user;

Selecting at least one associated to-be-pushed item in the associated to-be-push item set based on the score of each associated item to be pushed, the feature information of each associated item to be pushed, and the feature information of the user, and to the terminal Push the selected association to be pushed.
The method according to any one of claims 1 to 3, wherein the method further comprises:

For each of the items to be pushed, each of the items to be pushed is scored based on the at least one score item associated with the item to be pushed and the preset weight corresponding to each of the at least one of the points .
The method according to any one of claims 1 to 3, wherein the method further comprises:

Mining the feature information of the user in the behavior data of the user, wherein the behavior data includes at least one of the following: positioning data, search information, and consumption information.
The method of claim 1 further comprising:

And uploading, to the terminal, the comment information associated with the selected item to be pushed and the comment information of the associated item to be pushed associated with the selected item to be pushed.
A device for pushing information, characterized in that the device comprises:

a first acquiring unit, configured to acquire geographic location information of the terminal of the user;

a second acquiring unit, configured to acquire geographical location information corresponding to the pre-stored item to be pushed;

a first determining unit, configured to determine a to-be-pushed item set based on the geographic location information of the terminal, the geographic location information corresponding to the to-be-pushed item, and a preset distance threshold, and obtain the pre-generated item to be pushed Feature information of each item to be pushed in the collection and a score of each item to be pushed;

a second determining unit, configured to determine, for each of the items to be pushed in the set of items to be pushed, a matching degree of the feature information of the user that is generated in advance and the feature information of the item to be pushed;

a first pushing unit, configured to select at least one item to be pushed in the set of items to be pushed, based on a score of each item to be pushed, a matching degree of the feature information of the user, and feature information of each item to be pushed, and Pushing the selected item to be pushed and the associated item to be pushed associated with the selected item to be pushed to the terminal.
The device according to claim 8, wherein the first pushing unit comprises:

a first determining module, configured to determine, for each of the items to be pushed, whether the score of the item to be pushed is greater than a preset score threshold;

a first dividing module configured to: if yes, divide the item to be pushed into a first subset of items to be pushed;

a first selection module, configured to select, according to the feature information of the user from the first subset of the item to be pushed, the matching degree of the feature information of each item to be pushed in the first subset of the item to be pushed In the small order, select at least one item to be pushed.
The device according to claim 8, wherein the first pushing unit further comprises:

a second determining module, configured to determine, for each of the to-be-pushed items, whether the matching degree between the feature information of the user and the feature information of the to-be-pushed item is greater than a preset matching degree threshold;

a second dividing module configured to: if yes, divide the item to be pushed into a second subset of items to be pushed;

a second selection module, configured to select at least one item to be pushed from the second sub-set of the item to be pushed according to the order of the scores of each item to be pushed in the second subset of the item to be pushed .
The device according to any one of claims 8 to 10, wherein the first pushing unit further comprises:

a first acquiring module, configured to acquire an associated to-be-pushed item set associated with the selected item to be pushed;

a second obtaining module, configured to acquire a score of each associated item to be pushed and feature information of each associated item to be pushed;

a third determining module, configured to determine, for each associated item to be pushed, a matching degree between the feature information of the associated item to be pushed and the feature information of the user;

a pushing module, configured to select at least one associated to-be-pushed item in the associated to-be-push item set based on a score of each associated item to be pushed, a matching degree of feature information of each associated item to be pushed, and feature information of the user And pushing the selected association to be pushed item to the terminal.
The device according to any one of claims 8 to 10, wherein the device further comprises:

a scoring unit configured to score each item to be pushed for each of the items to be pushed, each of the at least one score item associated with the item to be pushed and each of the at least one score item Corresponding preset weights are used to score each item to be pushed.
The device according to any one of claims 8 to 10, wherein the device further comprises:

a mining unit configured to mine feature information of the user in behavior data of the user, where the behavior data includes at least one of the following: positioning data, search information Information and consumption information.
The device according to claim 8, wherein the device further comprises:

The second pushing unit is configured to push, to the terminal, the comment information associated with the selected item to be pushed and the comment information of the associated item to be pushed associated with the selected item to be pushed.
A server that includes:

One or more processors;

a memory for storing one or more programs;

The one or more processors are caused to perform the method of any one of claims 1-7 when the one or more programs are executed by the one or more processors.
A computer readable storage medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the method of any of claims 1-7.