CN110929176A

CN110929176A - Information recommendation method and device and electronic equipment

Info

Publication number: CN110929176A
Application number: CN201811020341.XA
Authority: CN
Inventors: 石雪峰; 罗京
Original assignee: Beijing Sogou Technology Development Co Ltd
Current assignee: Beijing Sogou Technology Development Co Ltd
Priority date: 2018-09-03
Filing date: 2018-09-03
Publication date: 2020-03-27

Abstract

The embodiment of the invention discloses an information recommendation method, an information recommendation device and electronic equipment. The method comprises the steps of firstly obtaining key words input in a retrieval interface, extracting function words to be retrieved capable of representing categories or characteristics of interest point POI from the key words, then obtaining the interest point POI corresponding to the function words to be retrieved according to the corresponding relation between the function words and the interest point POI, setting the interest point POI extracted according to the function words to be retrieved as candidate interest point POI in order to accurately recommend information, then calculating the association degree between the function words to be retrieved and each candidate interest point POI, and finally selecting and recommending the candidate interest point POI according to the association degree, so that the technical problem that the attachment degree between the recommendation of the interest point POI and a user retrieval intention is not high in the prior art is solved, and the recommendation accuracy of the interest point POI is improved.

Description

Information recommendation method and device and electronic equipment

Technical Field

The present invention relates to the field of information technologies, and in particular, to an information recommendation method and apparatus, and an electronic device.

Background

With the continuous development of network technology, more and more people search for network information by using a network, for example, people search for geographical location information by using an electronic map, search for a web page where information corresponding to a keyword is located in a browser, and the like.

Currently, when retrieving corresponding web page information through keywords, relevant information is generally recommended according to information such as the popularity of web page search, the click rate, whether to participate in promotion, and the number of times of the input keywords appearing in web pages. When the point of interest (POI) is searched through the keyword (point of interest), the searched point of interest (POI) is recommended according to the distance between the POI and the current location, the popularity of the POI, whether to participate in promotion, and the like. Whether the POI is recommended according to the distance, the popularity or the popularization, the user cannot obtain the desired POI or cannot obtain the desired POI from the recommendation home page in many times, namely the technical problem that the fitness of the recommendation of the POI and the retrieval intention of the user is not high exists in the prior art.

Disclosure of Invention

The embodiment of the invention provides an information recommendation method and device and electronic equipment, and aims to solve the technical problem that in the prior art, the fitting degree of the recommendation of a point of interest (POI) and a user retrieval intention is not high.

In a first aspect, an embodiment of the present invention provides an information recommendation method, where the method includes:

acquiring a keyword input in a retrieval interface;

extracting functional words to be retrieved from the key words, wherein the functional words are used for representing categories or characteristics of POIs (points of interest), one POI corresponds to n functional words, and n is more than or equal to 2;

acquiring a point of interest (POI) corresponding to the function word to be retrieved as a candidate POI, and acquiring the association degree between the function word to be retrieved and each candidate POI;

and selecting and recommending the candidate POI according to the degree of association.

Optionally, the extracting a function word to be retrieved from the keyword includes:

extracting a target keyword from the keywords, wherein the target keyword can represent the retrieval intention of the keyword;

and taking the target keyword as the functional word to be retrieved.

Optionally, the method further includes:

establishing a corresponding relation between each point of interest (POI) and the function words according to the function words contained in the page content corresponding to each POI, or establishing a corresponding relation between each POI and the function words according to a retrieval log of each POI;

the obtaining of the point of interest POI corresponding to the function word to be retrieved as a candidate point of interest POI includes:

and acquiring the interest point POI corresponding to the function word to be retrieved as a candidate interest point POI according to the corresponding relation between each interest point POI and the function word.

Optionally, the establishing a correspondence between each point of interest POI and a function word according to the function word included in the page content corresponding to each point of interest POI includes:

extracting category words and/or characteristic words of each POI from registration information, classification information and comment information in page content corresponding to each POI;

and taking the category words and/or the feature words of each POI as the function words of each POI, and establishing the corresponding relation between each POI and the function words.

acquiring the name, category, characteristics and/or consumption information of the POI (point of interest) contained in the page content corresponding to each POI, wherein the consumption information is used for reflecting the consumption condition of a user at the POI;

clustering the name, category, characteristics and/or consumption information of each POI to obtain a functional word of each POI;

inputting the function words of each POI into a convolutional neural network, training the convolutional neural network, and representing the corresponding relation between each POI and the function words through the trained convolutional neural network, wherein the trained convolutional neural network can convert the input function words to be retrieved and output candidate POI.

Optionally, the establishing a corresponding relationship between each point of interest POI and a function word according to the retrieval log of each point of interest POI includes:

acquiring a target keyword contained in a retrieval log of each POI;

and taking the target key words as function words of POI (point of interest) corresponding to the retrieval log.

Optionally, the obtaining of the association degree between the function word to be retrieved and each candidate POI includes:

converting each candidate point of interest (POI) into a first word vector and converting the functional words to be retrieved into a second word vector according to all the functional words corresponding to each candidate point of interest (POI);

and calculating the similarity between the first word vector and the second word vector, and taking the similarity as the association degree between the functional word to be retrieved and each candidate POI.

Optionally, the selecting and recommending the candidate POI according to the degree of association includes:

acquiring the candidate POI with the association degree larger than a set threshold value as a target POI, and recommending the target POI; or

And acquiring the top m candidate interest points POI with the maximum relevance as target interest points POI, and recommending the target interest points POI, wherein m is more than or equal to 1.

In a second aspect, an embodiment of the present invention further provides an information recommendation apparatus, where the apparatus includes:

the keyword acquisition module is used for acquiring keywords input in the retrieval interface;

the function word extracting module is used for extracting function words to be retrieved from the key words, wherein the function words are used for representing categories or characteristics of POI (point of interest), one POI corresponds to n function words, and n is more than or equal to 2;

the interest point POI obtaining module is used for obtaining a interest point POI corresponding to the function word to be retrieved as a candidate interest point POI and obtaining the association degree between the function word to be retrieved and each candidate interest point POI;

and the POI recommending module is used for selecting and recommending the candidate POI according to the relevance.

Optionally, the function word extracting module is configured to:

and taking the target keyword as the functional word to be retrieved.

Optionally, the apparatus further comprises:

the corresponding relationship establishing module is used for establishing a corresponding relationship between each point of interest POI and the function words according to the function words contained in the page content corresponding to each point of interest POI, or establishing a corresponding relationship between each point of interest POI and the function words according to the retrieval log of each point of interest POI;

the point of interest POI obtaining module is configured to:

Optionally, the module for establishing a corresponding relationship is configured to:

Optionally, the module for establishing a corresponding relationship is further configured to:

acquiring a target keyword contained in a retrieval log of each POI;

Optionally, the point of interest POI obtaining module is further configured to:

converting each candidate POI into a first vector word and converting the function word to be retrieved into a second vector word according to all the function words corresponding to each candidate POI;

and calculating the similarity between the first vector word and the second vector word, and taking the similarity as the association degree between the function word to be retrieved and each candidate POI.

Optionally, the POI recommending module is configured to:

acquiring the candidate POI with the association degree larger than a set threshold value as a target POI, and recommending the target POI;

In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, the program being executed by a processor to perform the following steps:

acquiring a keyword input in a retrieval interface;

In a fourth aspect, embodiments of the present invention provide an electronic device, comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors include instructions for:

acquiring a keyword input in a retrieval interface;

and selecting and recommending the candidate POI according to the degree of association. One or more technical solutions in the embodiments of the present application have at least the following technical effects:

the invention provides an information recommendation method, an information recommendation device and electronic equipment, wherein the method comprises the following steps: acquiring a keyword input in a retrieval interface; extracting functional words to be retrieved from the key words, wherein the functional words are used for representing categories or characteristics of POI (point of interest), one POI corresponds to n functional words, and n is more than or equal to 2; acquiring a point of interest (POI) corresponding to the function word to be retrieved as a candidate POI, and acquiring the association degree between the function word to be retrieved and each candidate POI; and selecting and recommending the candidate POI according to the degree of association. Because one POI corresponds to a plurality of function words and one function word can also correspond to a plurality of POIs, the POIs extracted according to the function words to be retrieved are complicated, in order to accurately recommend the POIs, the POIs extracted according to the function words to be retrieved are set as candidate POIs, then the association degree between the function words to be retrieved and each candidate POI is obtained, the recommended candidate POIs are selected according to the association degree, so that the POIs with the large association degree with the function words to be retrieved can be preferentially recommended, the function words to be retrieved are extracted from the retrieval key words, the retrieval intention of a user is met, namely the POIs with the large association degree with the function words to be retrieved relatively accord with the retrieval intention of the user, therefore, the POIs are recommended based on the association degree between the function words to be retrieved and the POIs, the method and the device solve the technical problem that the fitting degree of the point of interest (POI) recommendation and the user retrieval intention is not high in the prior art, and improve the POI recommendation accuracy.

Drawings

Fig. 1 shows a flowchart of an information recommendation method according to an embodiment of the present invention.

Fig. 2 is a schematic diagram illustrating an information recommendation apparatus according to an embodiment of the present invention.

FIG. 3 is a block diagram illustrating an electronic device in accordance with an example embodiment.

Fig. 4 is a schematic structural diagram of a server in an embodiment of the present invention.

Detailed Description

The main implementation principle, the specific implementation mode and the corresponding beneficial effects of the technical scheme of the embodiment of the present application are explained in detail with reference to the accompanying drawings.

Examples

Referring to fig. 1, fig. 1 is a flowchart illustrating an information recommendation method according to an embodiment of the present invention. The embodiment of the invention provides an information recommendation method which can be applied to a client and a server. The information recommendation method comprises the following steps:

s100: acquiring a keyword input in a retrieval interface;

s200: extracting functional words to be retrieved from the key words, wherein the functional words are used for representing categories or characteristics of POIs (points of interest), one POI corresponds to n functional words, and n is more than or equal to 2;

s300: acquiring a point of interest (POI) corresponding to the function word to be retrieved as a candidate POI, and acquiring the association degree between the function word to be retrieved and each candidate POI;

s400: and selecting and recommending the candidate POI according to the degree of association.

In S100, the search interface may be a search interface corresponding to a search frame of an application program such as a browser or a map, or may be a search interface provided by a system of the electronic device or the application program when some information is selected. In addition, the keywords input in the search interface may be input by the user, or may be automatically generated or selected by a system or an application of the electronic device.

Keywords (keywords) refer to words used by a single medium when making a use index. Here, there may be a plurality of keywords input.

Generally, the accuracy of extracting the search keyword and the accuracy of a search output result have great influence, and the accuracy of extracting an accurate keyword can be improved fundamentally. For the embodiment of the invention, the accurate function word to be retrieved is extracted from the key word input in the retrieval interface, and the point of interest POI corresponding to the function word to be retrieved can be correspondingly obtained, so that the obtained point of interest POI can better accord with the retrieval intention of the user.

In order to obtain an accurate function word to be retrieved, the embodiment of the present invention obtains the function word to be retrieved by using the scheme described in step S200 below.

S200: and extracting functional words to be retrieved from the key words, wherein the functional words are used for representing categories or characteristics of POI (point of interest), one POI corresponds to n functional words, and n is more than or equal to 2.

The Point of interest POI is also called Point of Information. The electronic map is generally represented by bubble icons, and the POI is a scenic spot, a government agency, a company, a market, a restaurant and the like on the electronic map. The POI is core data based on location services, and has wide application scenes on an electronic map, such as a destination selected before navigation, surrounding restaurants and the like.

The function words are used for representing categories or characteristics of the POI. The category or feature of one point of interest POI may be described by a plurality of functions, different categories of point of interest POIs may have the same feature, and points of interest POIs having different features may also have the same or similar categories, and thus, it may be understood that one point of interest POI may correspond to a plurality of function words, and one function word may also correspond to a plurality of point of interest POIs.

For example, the functional word "roast duck" may correspond to a storefront corresponding to the brand "pan-poly", that is, the point of interest POI of "pan-poly" may correspond to the functional word "roast duck", and may also correspond to the functional word "beijing roast duck". The point of interest POI "hagyra hotel" may correspond to a function word of "accommodation", "hotel", etc.

Extracting the functional words to be retrieved from the keywords, and obtaining the functional words through the following steps: firstly, extracting a target keyword from the keywords, wherein the target keyword can represent the retrieval intention of the keywords; and then, taking the target keyword as the functional word to be retrieved. The number of target keywords is not limited, and may be one or more.

There may be a plurality of keywords obtained from the search interface, and one or more keywords may be extracted therefrom as target keywords. As an embodiment, the step of extracting the target keyword from the keywords may specifically be: inputting a keyword into a pre-trained CNN (Convolutional Neural Network), outputting a target keyword corresponding to the keyword by the CNN, wherein the target keyword can represent a retrieval intention of the keyword, the CNN is pre-trained by adopting a sample set consisting of the keyword and the corresponding target keyword, and the trained CNN can convert the input keyword into the target keyword. The CNN is a feedforward neural network, the artificial neuron can respond to peripheral units and can perform large-scale information processing, input weights in the feedforward correction network are corrected according to input samples, and the finally obtained CNN can reflect one or more outputs corresponding to the input information.

As another embodiment, the step of extracting the target keyword from the keywords specifically includes: inputting keywords into a pre-trained decision tree model, outputting target keywords corresponding to the keywords by the decision tree model, wherein the target keywords can represent the retrieval intention of the keywords, the decision tree model is trained by adopting a sample set consisting of the keywords and the corresponding target keywords in advance, and the trained decision tree model can convert the input keywords into the target keywords.

In both embodiments, the target keyword is extracted from the keyword based on a machine learning method, and as another embodiment, a noun or a verb in the keyword may be extracted from the input keyword, and the noun or the verb may be used as the target keyword.

The corresponding relation exists between the function words and the POI, and the target key words can represent the retrieval intention of the input key words, so that the target key words obtained from the key words are used as the function words to be retrieved, the POI is recommended according to the function words to be retrieved, the recommended POI can be more close to the retrieval intention of the user, errors are reduced fundamentally, and the recommended POI is more in line with the retrieval intention of the user.

In this embodiment of the present invention, before S300, the information recommendation method further includes establishing a correspondence between each POI and a function word. The establishment of the corresponding relationship between each point of interest POI and the function word may be implemented in various ways, and specifically, may be implemented in the following ways:

as an implementation manner of establishing the correspondence between each point of interest POI and the function word, the correspondence between each point of interest POI and the function word may be established according to the function word included in the page content corresponding to each point of interest POI.

The content of the page corresponding to the point of interest POI refers to content contained in a page where a webpage or a map interface corresponding to the point of interest POI is located, where the content may include text, pictures, videos, audio, and the like, and specifically, may include registration information, classification information, comment information, and the like of the point of interest POI.

In order to establish a corresponding relationship between each point of interest POI and a function word according to the function word included in the page content corresponding to each point of interest POI, the following method may be specifically adopted:

as a first implementation manner, the correspondence between each point of interest POI and a function word may be established by:

extracting category words and/or characteristic words of each POI from registration information, classification information and comment information in page content corresponding to each POI; and taking the category words and/or the feature words of each POI as the function words of each POI, and establishing the corresponding relation between each POI and the function words. Specifically, the classification information, the registration information, the characteristics in the comment information, and the like may be used as the category words and/or the characteristic words of the point of interest POI, or the method described in step 210 may be used to extract the category words and/or the characteristic words of the point of interest POI from the registration information and the comment information.

As a second implementation manner, the correspondence between each POI and a function word may be established as follows:

firstly, the name, the category, the characteristics and/or the consumption information of the POI contained in the page content corresponding to each POI are obtained, wherein the consumption information is used for reflecting the consumption condition of a user at the POI. The consumption condition comprises the per-person consumption price, the singular number of dish points, the number of network friends comments, the number of praise and the like.

In the embodiment of the present invention, the name, category, feature and/or consumption information of the point of interest POI may be obtained by searching on the network, or the name, category, feature and/or consumption information of the point of interest POI may be obtained from a pre-established database containing the name, category, feature and/or consumption information of the point of interest POI, where the pre-established database may be formed by the name, category, feature and/or consumption information of the point of interest POI obtained from a data interface of a partner, or may be formed by the name, category, feature and/or consumption information of the point of interest POI obtained on the network in advance.

Secondly, clustering the name, category, characteristics and/or consumption information of each POI to obtain the functional words of each POI.

The names, categories, characteristics and/or consumption information of the POIs can be learned and clustered by using a decision tree model, a convolutional neural network, an SVM (Support Vector Machine) model and other Machine learning models to obtain the functional words of each POI. Specifically, a sample set formed by the name, category, feature and/or consumption information of the POI is collected in advance, the sample set is input into the machine learning model, the machine learning model is trained, and the trained machine learning model can convert the input name, category, feature and/or consumption information of the POI and output functional words corresponding to the POI.

And then, after the function word of each POI is obtained, establishing the corresponding relation between the function word and the POI. Specifically, the functional words of each POI are input into a convolutional neural network, the convolutional neural network is trained, and the trained convolutional neural network can represent the corresponding relationship between each POI and the functional words, that is, the trained convolutional neural network can convert the input functional words to be retrieved to output candidate POIs. For example, keywords such as "ice cream, fried chicken, hamburger, cola" are input into the convolutional neural network, and the convolutional neural network can output the POI corresponding to "Kendeki".

As another implementation of establishing a correspondence between each point of interest POI and a function word, the correspondence between each point of interest POI and a function word may be established according to a search log of each point of interest POI, and specifically, may be implemented in the following manner:

first, a target keyword included in a retrieval log of each point of interest POI is acquired. The number of the obtained target keywords may be one or more, and the embodiment does not limit the number of the target keywords. One target keyword corresponds to one function word, and one function word can correspond to a plurality of POIs.

Here, the search log of each point of interest POI includes keywords input in a past search history, and a target keyword corresponding to the keyword and a user selection result corresponding to the target keyword, for example, when the user clicks a certain search result, the user selection result corresponds to one point of interest POI. For example, a record in such a format is recorded in the retrieval log: the target keyword < - > the user selects the result < - > POI.

Then, after the retrieval log of the POI is obtained, the target keyword can be found along the path of the point of interest POI < - > user selection result < - > target keyword.

And then, the obtained target key words are used as function words of the POI corresponding to the retrieval log, and the corresponding relation between the POI and the function words is established.

Of course, the correspondence between the POI and the function word may also be established by training the classification model. The method comprises the steps of training a classification model by taking a large number of POI (point of interest) and corresponding target keywords as training samples, enabling the classification model to well classify the target keywords and the POI, inputting the target keywords into the trained classification model when the target keywords are obtained, and outputting the POI corresponding to the target keywords.

S300: and acquiring the interest point POI corresponding to the function word to be retrieved as a candidate interest point POI, and acquiring the association degree between the function word to be retrieved and each candidate interest point POI.

Specifically, the candidate point of interest POI may be obtained by obtaining, as the candidate point of interest POI, a point of interest POI corresponding to the function word to be retrieved according to a correspondence between each point of interest POI and the function word.

The obtaining of the association degree between the function word to be retrieved and each candidate point of interest POI may be implemented as follows:

converting each candidate point of interest (POI) into a first word vector and converting the functional words to be retrieved into a second word vector according to all the functional words corresponding to each candidate point of interest (POI); and calculating the similarity between the first word vector and the second word vector, and taking the similarity as the association degree between the functional word to be retrieved and each candidate POI. An included angle between the first word vector and the second word vector can be calculated, then a cosine value of the included angle is calculated, the similarity between the first word vector and the second word vector is measured by the cosine value, the larger the cosine value is, the higher the similarity between the first word vector and the second word vector is, the smaller the cosine value is, and the lower the similarity between the first word vector and the second word vector is.

Step S400: and selecting and recommending the candidate POI according to the degree of association.

When the number of the acquired candidate points of interest POIs obtains a certain value, the candidate points of interest POIs to be recommended are unrealistic and unnecessary, and therefore, the candidate points of interest POIs need to be selectively recommended.

Selecting and recommending the candidate POI according to the degree of association, which can be specifically realized by the following method:

as an implementation manner, the candidate point of interest POI with the relevance degree greater than the set threshold is obtained as a target point of interest POI, and the target point of interest POI is recommended.

As another implementation manner, the top m candidate interest points POI with the maximum relevance are obtained as target interest points POI, and the target interest points POI are recommended, wherein m is larger than or equal to 1.

Therefore, candidate POI with relatively high association can be preferentially recommended and recommended in a targeted manner, and the recommended POI is more in line with the retrieval intention of the user, so that the requirements of the user are met, and the obtained POI does not need to be recommended, and resources are saved.

By adopting the scheme, firstly, the key words input in the retrieval interface are obtained, the function words to be retrieved capable of representing the categories or the characteristics of the POI are extracted from the key words, and then the POI corresponding to the function words to be retrieved is obtained according to the corresponding relation between the function words and the POI. Since one point of interest POI corresponds to a plurality of function words, and one function word may also correspond to a plurality of point of interest POIs, the point of interest POIs extracted according to the function words to be retrieved are complicated, and in order to be able to accurately recommend information, the point of interest POIs extracted according to the function words to be retrieved are set as candidate point of interest POIs. And then obtaining the association degree between the function word to be retrieved and each candidate point of interest (POI), converting each candidate point of interest (POI) into a first word vector and converting the function word to be retrieved into a second word vector in order to intuitively and accurately obtain the association degree between the function word to be retrieved and each candidate point of interest (POI), calculating the similarity between the first word vector and the second word vector, and taking the similarity as the association degree between the function word to be retrieved and each candidate point of interest (POI). And finally, selecting and recommending candidate POI according to the degree of association, so that POI with high degree of association with the function word to be retrieved can be preferentially recommended, and the function word to be retrieved is extracted from the retrieval key word and accords with the retrieval intention of the user, namely, POI with high degree of association with the function word to be retrieved accords with the retrieval intention of the user better than POI with low degree of association, therefore, the POI is recommended based on the degree of association between the function word to be retrieved and the POI, the technical problem of low degree of attachment between the recommendation of the POI and the retrieval intention of the user in the prior art is solved, and the accuracy of POI recommendation of the POI is improved. The embodiment of the present application further provides an information recommendation apparatus 200, which is applied to a client or a server for information recommendation. Referring to fig. 2, the apparatus includes: the system comprises a keyword obtaining module 210, a function word extracting module 220, a point of interest (POI) obtaining module 230, a POI recommending module 240 and a corresponding relationship establishing module 250. The keyword obtaining module 210, the function word extracting module 220, the point of interest obtaining module 230, the point of interest recommending module 240, and the corresponding relationship establishing module 250 may be connected through a bus. The keyword obtaining module 210 is configured to obtain a keyword input in the search interface.

The function word extracting module 220 is configured to extract function words to be retrieved from the key words, where the function words are used to represent categories or features of the point of interest POIs, one point of interest POI corresponds to n function words, and n is greater than or equal to 2.

The point of interest POI obtaining module 230 is configured to obtain a point of interest POI corresponding to the function word to be retrieved as a candidate point of interest POI, and obtain a degree of association between the function word to be retrieved and each candidate point of interest POI.

And a POI recommending module 240, configured to select a POI candidate to be recommended according to the relevance.

As an optional implementation manner, the extracting function word module 220 is configured to: and extracting a target keyword from the keywords, wherein the target keyword can represent the retrieval intention of the keywords, and the target keyword is used as the functional word to be retrieved.

As an optional implementation, the apparatus further comprises: a corresponding relationship establishing module 250, configured to establish a corresponding relationship between each point of interest POI and a function word according to the function word included in the page content corresponding to each point of interest POI, or establish a corresponding relationship between each point of interest POI and a function word according to a search log of each point of interest POI, where the point of interest obtaining module 230 is configured to: and acquiring the interest point POI corresponding to the function word to be retrieved as a candidate interest point POI according to the corresponding relation between each interest point POI and the function word.

As an optional implementation manner, the establishing correspondence module 250 is configured to: extracting category words and/or characteristic words of each POI from registration information, classification information and comment information in page content corresponding to each POI; and taking the category words and/or the feature words of each POI as the function words of each POI, and establishing the corresponding relation between each POI and the function words.

As an optional implementation manner, the establishing correspondence module 250 is further configured to:

the method comprises the steps of obtaining the name, category, feature and/or consumption information of a point of interest (POI) contained in page content corresponding to each POI, wherein the consumption information is used for reflecting the consumption condition of a user at the POI, clustering the name, category, feature and/or consumption information of each POI to obtain a functional word of each POI, inputting the functional word of each POI into a convolutional neural network, training the convolutional neural network, and representing the corresponding relation between each POI and the functional word through the trained convolutional neural network, wherein the trained convolutional neural network can convert the input functional word to be retrieved to output a candidate POI.

As an optional implementation manner, the establishing correspondence module 250 is further configured to: acquiring a target keyword contained in a retrieval log of each POI; and taking the target key words as function words of POI (point of interest) corresponding to the retrieval log.

As an optional implementation manner, the point of interest POI obtaining module 230 is further configured to: converting each candidate POI into a first vector word and converting the function word to be retrieved into a second vector word according to all the function words corresponding to each candidate POI; and calculating the similarity between the first vector word and the second vector word, and taking the similarity as the association degree between the function word to be retrieved and each candidate POI.

As an optional implementation manner, the POI recommending module 240 is configured to: and acquiring candidate interest points POI with the association degree larger than a set threshold value as target interest points POI, recommending the target interest points POI, acquiring the first m candidate interest points POI with the maximum association degree as the target interest points POI, and recommending the target interest points POI, wherein m is larger than or equal to 1. With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Fig. 3 is a block diagram illustrating an electronic device 800 for recommending point of interest (POI) in accordance with an exemplary embodiment. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.

Referring to fig. 3, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communication component 816.

The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing elements 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operation at the device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 800 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the electronic device 800. For example, the sensor assembly 814 may detect an open/closed state of the device 800, the relative positioning of components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, orientation or acceleration/deceleration of the electronic device 800, and a change in the temperature of the electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast associated information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communications component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 804 comprising instructions, executable by the processor 820 of the electronic device 800 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

A non-transitory computer readable storage medium in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform a method of information recommendation, the method comprising:

acquiring a keyword input in a retrieval interface; extracting functional words to be retrieved from the key words, wherein the functional words are used for representing categories or characteristics of POIs (points of interest), one POI corresponds to n functional words, and n is more than or equal to 2; acquiring a point of interest (POI) corresponding to the function word to be retrieved as a candidate POI, and acquiring the association degree between the function word to be retrieved and each candidate POI; and selecting and recommending the candidate POI according to the degree of association.

Fig. 4 is a schematic structural diagram of a server in an embodiment of the present invention. The server 1900 may vary widely by configuration or performance and may include one or more Central Processing Units (CPUs) 1922 (e.g., one or more processors) and memory 1932, one or more storage media 1930 (e.g., one or more mass storage devices) storing applications 1942 or data 1944. Memory 1932 and storage medium 1930 can be, among other things, transient or persistent storage. The program stored in the storage medium 1930 may include one or more modules (not shown), each of which may include a series of instructions operating on a server. Still further, a central processor 1922 may be provided in communication with the storage medium 1930 to execute a series of instruction operations in the storage medium 1930 on the server 1900.

The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input-output interfaces 1958, one or more keyboards 1956, and/or one or more operating systems 1941, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is only limited by the appended claims

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims

1. An information recommendation method, characterized in that the method comprises:

acquiring a keyword input in a retrieval interface;

2. The information recommendation method according to claim 1, wherein the extracting the function word to be retrieved from the keyword comprises:

and taking the target keyword as the functional word to be retrieved.

3. The information recommendation method of claim 1, further comprising:

4. The information recommendation method according to claim 3, wherein the establishing of the correspondence between each POI and the functional words according to the functional words contained in the page content corresponding to each POI comprises:

5. The information recommendation method according to claim 3, wherein the establishing of the correspondence between each POI and the functional words according to the functional words contained in the page content corresponding to each POI comprises:

6. The information recommendation method according to claim 3, wherein the establishing of the correspondence between each POI and the function word according to the search log of each POI comprises:

acquiring a target keyword contained in a retrieval log of each POI;

7. The information recommendation method according to claim 1, wherein the selecting and recommending the candidate POI according to the relevance comprises:

8. An information recommendation apparatus, characterized in that the apparatus comprises:

9. A computer-readable storage medium having a computer program stored thereon, the program being executable by a processor to perform the steps of:

acquiring a keyword input in a retrieval interface;

10. An electronic device comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors the one or more programs including instructions for:

acquiring a keyword input in a retrieval interface;