CN113569149A

CN113569149A - Information processing method and device and electronic equipment

Info

Publication number: CN113569149A
Application number: CN202110875735.9A
Authority: CN
Inventors: 刘小杰; 温家琦
Original assignee: Rajax Network Technology Co Ltd
Current assignee: Rajax Network Technology Co Ltd
Priority date: 2021-07-30
Filing date: 2021-07-30
Publication date: 2021-10-29
Anticipated expiration: 2041-07-30
Also published as: CN113569149B

Abstract

The embodiment of the application provides an information processing method, an information processing device, electronic equipment and a computer storage medium, wherein the method comprises the following steps: determining a target position selected by a user on a current display map; acquiring target text information which is input by a user and used for determining a target address, and determining a target position according to the target text information; recalling a plurality of candidate points of interest based on the target location; obtaining ranking information of the candidate interest points according to attribute information of each candidate interest point in the candidate interest points, wherein the attribute information comprises at least one of use type information of the candidate interest points, the number of child interest points of the candidate interest points and the number of parent interest points of the candidate interest points. The method has more accuracy and rationality on the basis of the ranking information of the candidate interest points, which is obtained by at least one attribute information of the use type information of the candidate interest points, the number of the child interest points of the candidate interest points and the number of the parent interest points of the candidate interest points.

Description

Information processing method and device and electronic equipment

Technical Field

The present application relates to the field of computer technologies, and in particular, to an information processing method and apparatus, an electronic device, and a computer storage medium.

Background

With the rapid development of science and technology and the continuous improvement of modern life quality, the shopping mode of people becomes more and more convenient. Sometimes, the commodity or the article can be purchased on line without going out. Specifically, the user may fill in the shipping address in advance to ensure that the delivery personnel can deliver the goods or items purchased by the user to the user according to the shipping address.

When a user fills in a receiving address, the filled-in receiving address is generally divided into two parts, so that distribution is performed by a distributor conveniently, and the address is filled in by the user conveniently. The first part of the users can stamp points on the map or input keywords, and the terminal can directly show some points of interest to the users, and the users can select the points of interest to input the first part of the delivery address. The other part, namely: the second portion of the shipping address is entered by the user manually entering text. When the user fills in the receiving address, if the interest points are selected appropriately, the distribution personnel can carry out distribution conveniently. Therefore, how to accurately recommend some ordered interest points to the user for the user to select when inputting the receiving address becomes a problem to be solved urgently in the current process of filling the receiving address.

Disclosure of Invention

The embodiment of the application provides an information processing method, which aims to solve the problem of accurately recommending some ordered interest points to a user for the user to select when a receiving address is input. Meanwhile, the embodiment of the application provides an information processing device, an electronic device and a computer storage medium corresponding to the information processing method.

An embodiment of the present application provides an information processing method, including: determining a target position selected by a user on a current display map; acquiring target text information which is input by the user and used for determining a target address, and determining a target position according to the target text information; recalling a plurality of candidate points of interest based on the target location; obtaining ranking information of the candidate interest points according to attribute information of each candidate interest point in the candidate interest points, wherein the attribute information comprises at least one of usage type information of the candidate interest points, the number of child interest points of the candidate interest points and the number of parent interest points of the candidate interest points.

Optionally, the obtaining, according to the attribute information of each candidate interest point in the multiple candidate interest points, ranking information of the multiple candidate interest points includes: obtaining probability information whether each candidate interest point in the candidate interest points can become a target interest point selected by the user or not according to the attribute information of each candidate interest point in the candidate interest points; based on the probability information, obtaining ranking information of the candidate interest points.

Optionally, the obtaining, according to the attribute information of each candidate interest point in the plurality of candidate interest points, probability information of whether each candidate interest point in the plurality of candidate interest points corresponds to a target interest point selected by the user includes: inputting the attribute information of each candidate interest point in the candidate interest points into a target interest point probability information obtaining model, and obtaining probability information of whether each candidate interest point in the candidate interest points corresponds to the target interest point selected by the user.

Optionally, the method further includes: determining a target point of interest selected by the user from the plurality of candidate points of interest; and taking the target interest point and the user characteristic information corresponding to the user as training samples, training the target interest point probability information obtaining model, and obtaining the updated target interest point probability information obtaining model.

Optionally, the obtaining the ranking information of the candidate interest points based on the probability information includes: obtaining initial ranking information of the candidate interest points based on the probability information; and reordering the initially ordered candidate interest points based on a preset ordering strategy to obtain reordering information of the candidate interest points.

Optionally, the reordering of the initially ordered plurality of candidate interest points based on the preset ordering policy includes: and reordering the initially ordered plurality of candidate interest points based on the preset blacklist interest point.

Optionally, the inputting the attribute information of each candidate interest point in the multiple candidate interest points into a target interest point probability information obtaining model to obtain probability information of whether each candidate interest point in the multiple candidate interest points corresponds to a target interest point selected by the user includes: obtaining first ordering information of the number of the child interest points of each candidate interest point in the number of the child interest points of the candidate interest points, and second ordering information of the number of the parent interest points of each candidate interest point in the number of the parent interest points of the candidate interest points; inputting at least one of the first ranking information, the second ranking information, and the usage type information of each candidate interest point in the candidate interest points into a target interest point probability information obtaining model, and obtaining probability information of whether each candidate interest point in the candidate interest points corresponds to the target interest point selected by the user.

Optionally, the attribute information further includes a distance between a location of the candidate interest point and the target location, and a frequency of selecting the candidate interest point.

Optionally, the inputting the attribute information of each candidate interest point in the multiple candidate interest points into a target interest point probability information obtaining model to obtain probability information of whether each candidate interest point in the multiple candidate interest points corresponds to a target interest point selected by the user includes: obtaining third ranking information of the distance between the position of each candidate interest point and the target position in the distance between the positions of the candidate interest points and the target position and fourth ranking information of the frequency of the selected candidate interest points in the frequency of the selected candidate interest points; inputting at least one of the usage type information of the candidate interest points, the number of the child interest points of the candidate interest points, the number of the parent interest points of the candidate interest points, the third ordering information and the fourth ordering information into a target interest point probability information obtaining model, and obtaining probability information of whether each candidate interest point of the candidate interest points corresponds to the target interest point selected by the user.

Optionally, the obtaining, according to the attribute information of each candidate interest point in the multiple candidate interest points, ranking information of the multiple candidate interest points includes: obtaining evaluation score information whether each candidate interest point in the candidate interest points can become a target interest point selected by the user or not according to the attribute information of each candidate interest point in the candidate interest points; obtaining ranking information of the candidate interest points based on the evaluation score information.

Optionally, the obtaining, according to the attribute information of each candidate interest point in the plurality of candidate interest points, evaluation score information of whether each candidate interest point in the plurality of candidate interest points corresponds to a target interest point selected by the user includes: inputting the attribute information of each candidate interest point in the candidate interest points into a target interest point evaluation score information obtaining model, and obtaining evaluation score information of whether each candidate interest point in the candidate interest points corresponds to the target interest point selected by the user.

Optionally, the obtaining the ranking information of the candidate points of interest based on the evaluation score information includes: and taking the interest point with the highest evaluation score in the candidate interest points as the first-ranked interest point recommended to the user.

Optionally, the method further includes: obtaining the ranking information of other candidate interest points except the interest point ranked at the first position in the candidate interest points; obtaining ranking information of the candidate interest points based on the ranking information of the other candidate interest points.

Optionally, the obtaining the ranking information of the candidate interest points other than the first ranked interest point from the candidate interest points includes: obtaining text similarity between description information corresponding to other candidate interest points except the first ranked interest point in the candidate interest points and target text information input by the user and used for determining a target address; and ranking the other candidate interest points based on the text similarity to obtain ranking information of the other candidate interest points.

Optionally, the target interest point is an interest point for obtaining a receiving address corresponding to the delivered item.

Correspondingly, an embodiment of the present application provides an information processing apparatus, including: the target position determining unit is used for determining a target position selected by a user on the current display map; acquiring target text information which is input by the user and used for determining a target address, and determining a target position according to the target text information; a recall unit for recalling a plurality of candidate interest points based on the target location; the ranking information obtaining unit is configured to obtain ranking information of the candidate interest points according to attribute information of each candidate interest point in the candidate interest points, where the attribute information includes at least one of usage type information of the candidate interest points, a number of child interest points of the candidate interest points, and a number of parent interest points of the candidate interest points.

Correspondingly, an embodiment of the present application provides an electronic device, including: a processor; a memory for storing a computer program to be executed by the processor for executing the above-mentioned information processing method.

Correspondingly, the embodiment of the application provides a computer storage medium, wherein a computer program is stored in the computer storage medium, and the computer program is executed by a processor to execute the information processing method.

Compared with the prior art, the embodiment of the application has the following advantages:

an embodiment of the present application provides an information processing method, including: determining a target position selected by a user on a current display map; acquiring target text information which is input by the user and used for determining a target address, and determining a target position according to the target text information; recalling a plurality of candidate points of interest based on the target location; obtaining ranking information of the candidate interest points according to attribute information of each candidate interest point in the candidate interest points, wherein the attribute information comprises at least one of usage type information of the candidate interest points, the number of child interest points of the candidate interest points and the number of parent interest points of the candidate interest points. In the present embodiment, the ranking information of the plurality of candidate interest points is obtained based on at least one attribute information of the usage type information of the candidate interest points, the number of child interest points of the candidate interest points, and the number of parent interest points of the candidate interest points. In this way, the target position selected by the user on the current display map is determined at the same time; and target text information which is input by the user and used for determining the target address is obtained, the target position is determined according to the target text information, the obtained ranking information of the candidate interest points is enabled to be more accurate and reasonable, the target interest points selected by the user in the follow-up process based on the ranking information of the candidate interest points can be enabled to be more matched with the receiving address, and distribution can be conducted by distribution personnel based on the delivery address greatly.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art according to the drawings.

Fig. 1 is a first schematic diagram of an application scenario of an information processing method provided in the present application;

fig. 2 is a second schematic diagram of an application scenario of the information processing method provided in the present application;

fig. 3 is a third schematic view of an application scenario of the information processing method provided in the present application;

fig. 4 is a flowchart of an information processing method according to a first embodiment of the present application;

fig. 5 is a schematic diagram of an information processing apparatus according to a second embodiment of the present application;

fig. 6 is a schematic view of an electronic device according to a third embodiment of the present application.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit of this application and is therefore not limited to the specific implementations disclosed below.

Some embodiments of the information processing method provided by the application can be applied to recommending a candidate interest point list to a user when the user needs to fill in the receiving address information in a scene of purchasing a commodity or a meal, so that the user can select a certain interest point as a part of the receiving address.

In practice, after the user selects a certain interest point in the recommended candidate interest point list, the selected interest point is called a target interest point. The text information corresponding to the target interest points becomes a first part of the receiving address information, and then the user fills in more detailed address information as a second part of the receiving address information.

For example, when the shipping address information is a city a, a region B, a road C, a region D, and 15 3-floor 301 rooms, the region D may be a point of interest. Thus, when the user fills in the shipping address, cell D may be selected as the first part of the shipping address, and then more detailed address information is filled in: the 15 3-level 301 compartments serve as the second part of the shipping address. The two parts together constitute a shipping address.

Of course, cell D15 may also be a point of interest. Thus, when the user fills in the shipping address, cell D15 may be selected as the first part of the shipping address, and then more detailed address information is filled: the level 3 301 compartment serves as the second portion of the shipping address.

When a shipping address is newly added or changed, a user may generally obtain a candidate interest point list to select an interest point in two ways, one way may be to obtain the candidate interest point list by stamping a point on a displayed map, and the other way may be to obtain the candidate interest point list by inputting a keyword in a search box. In the present application, the determination of the target position selected by the user on the currently displayed map may be considered at the same time, that is: a manner of stamping points on the displayed map; and acquiring target text information which is input by a user and used for determining a target address, and determining a target position according to the target text information, namely: the manner in which the keywords are entered within the search box.

The above way of the stamp point or the way of inputting the key word is to obtain a position, that is: the target location to recall a plurality of candidate points of interest that need to be ranked based on the target location. After the candidate interest points needing to be ranked are recalled, ranking the candidate interest points based on the attribute information of the candidate interest points, further obtaining ranking information of the candidate interest points, and finally obtaining a candidate interest point list.

In practice, the point that the user has stamped in the map or the keyword that is entered is for the purpose of selecting a target location that is visible to the user. The target position objectively has geographic latitude and longitude, a plurality of candidate interest points can be recalled based on the geographic latitude and longitude information corresponding to the target position, and then the candidate interest points are ranked, so that the candidate interest point list can be obtained.

As shown in fig. 1, which is a first schematic view of an application scenario of the information processing method provided by the present application, a page is switched to the page shown in fig. 2 by clicking a "select detailed address" in the page shown in fig. 1. Fig. 2 is a second schematic view of an application scenario of the information processing method provided in the present application.

The map on the page shown in fig. 2 may be used to stamp points to obtain a candidate interest point list, and if a suitable point cannot be found on the map finally, that is, a suitable point cannot be found as a target location, a keyword may be entered in the "please enter address" search box to obtain another candidate interest point list again. Of course, the list of candidate points of interest obtained for the first time may not be the same as the list of candidate points of interest obtained for the second time.

Of course, no matter how the mode of stamping points or inputting keywords is adopted, after the page shown in fig. 2 is stamped or the keywords are input, the page is switched to the page shown in fig. 3, and fig. 3 is a third schematic view of an application scenario of the information processing method provided by the present application. The page shown in fig. 3 shows a candidate interest point list for the user to select a certain interest point as the target interest point. It is understood that in the present embodiment, the way of inputting the keywords or the stamp points is to obtain the candidate interest point list to edit the shipping address information.

The information processing method is used for obtaining a more accurate and reasonable candidate interest point list and displaying the candidate interest point list in the page shown in FIG. 3, so that when a user selects a target interest point with a top rank in the candidate interest point list, the position of the target interest point is more matched with a receiving address.

Specifically, when obtaining the candidate interest point list, the ranking information of the candidate interest points needs to be obtained, and the manner of obtaining the ranking information of the candidate interest points mainly includes the following two manners.

The first way to obtain ranking information of multiple candidate points of interest: and when the user selects the target position in a point-stamping mode, taking the position of the point selected by the user aiming at the current display map as the target position. Then, based on the target position, a plurality of candidate interest points to be recommended are recalled. For example, when the user timestamp point is a point corresponding to building E as the target location, the candidate points of interest to be recalled may be building E, eastern building E, western building E, 3 rd floor of building E, or southern building E.

After obtaining a plurality of candidate interest points to be recommended, the plurality of candidate interest points need to be ranked. The plurality of candidate points of interest may be ranked to obtain ranking information for the plurality of candidate points of interest in the following manner.

Specifically, the ranking information of the plurality of candidate interest points may be obtained according to the attribute information of each of the plurality of candidate interest points. More specifically, obtaining the ranking information of the multiple candidate interest points according to the attribute information of each candidate interest point in the multiple candidate interest points may refer to: firstly, obtaining probability information whether each candidate interest point in the candidate interest points can become a target interest point selected by a user or not according to the attribute information of each candidate interest point in the candidate interest points; then, based on the probability information, ranking the candidate interest points, namely: ranking information for a plurality of candidate points of interest is obtained.

In the present application, the probability information may also be replaced by confidence information, evaluation score information, or other result information indicating the possibility that the candidate interest point can become the target interest point selected by the user. The probability information is used to indicate the probability that the candidate interest point becomes the target interest point.

The obtaining of the ranking information of the candidate interest points based on the probability information may be: and according to the possibility that each candidate interest point becomes the target interest point, sorting the candidate interest points which are possible to become the target interest points according to the possibility from large to small, and further obtaining a candidate interest point sorting list.

Specifically, when obtaining probability information of whether each candidate interest point in the multiple candidate interest points can become a target interest point selected by a user according to the attribute information of each candidate interest point in the multiple candidate interest points, the following method is adopted: and inputting the attribute information of each candidate interest point in the candidate interest points into the target interest point probability information obtaining model to obtain probability information of whether each candidate interest point in the candidate interest points can become the target interest point selected by the user or not.

The input attribute information includes: at least one of usage type information of the candidate interest point, the number of interest points of the candidate interest point, and the number of parent interest points of the candidate interest point. The usage type information of the candidate points of interest may be usage type information such as office buildings, residential homes, and shopping malls. The number of child interest points of the candidate interest point may refer to a number of child candidate interest points of the candidate interest point, and the number of parent interest points of the candidate interest point may refer to a number of parent candidate interest points of the candidate interest point. For example, E building is a parent interest point in the east region of E building, and E building east region are both interest points of the plurality of candidate interest points.

Specifically, for convenience of data processing, after obtaining the attribute information of each candidate interest point, at least one of first ranking information of the number of child interest points of each candidate interest point in the number of child interest points of the plurality of candidate interest points, second ranking information of the number of parent interest points of each candidate interest point in the number of parent interest points of the plurality of candidate interest points, and use type information of each candidate interest point is obtained.

Further, the attribute information of each candidate interest point in the multiple candidate interest points is used as input information of the target interest point probability information obtaining model, and is input into the target interest point probability information obtaining model to obtain probability information of whether each candidate interest point in the multiple candidate interest points corresponds to a target interest point selected by a user, where the probability information may be: and inputting at least one of the first sequencing information, the second sequencing information and the use type information of each candidate interest point into the target interest point probability information obtaining model by taking the at least one of the first sequencing information, the second sequencing information and the use type information of each candidate interest point as input information of the target interest point probability information obtaining model so as to obtain probability information of whether each candidate interest point in the plurality of candidate interest points corresponds to the target interest point selected by the user or not.

Of course, the target interest point probability information obtaining model is a model for obtaining probability information of whether the candidate interest point corresponds to the target interest point selected by the user or not based on the attribute information of the candidate interest point. And when the probability information is replaced by the confidence information, the corresponding model is the target interest point confidence information obtaining model.

The attribute information further comprises the distance between the position of the candidate interest point and the target position and the frequency of selecting the candidate interest point. Therefore, the attribute information of each candidate interest point in the multiple candidate interest points is used as the input information of the target interest point probability information obtaining model, and is input into the target interest point probability information obtaining model, so as to obtain probability information of whether each candidate interest point in the multiple candidate interest points corresponds to the target interest point selected by the user, and the probability information may also be: and inputting at least one of the use type information of the candidate interest points, the number of the child interest points of the candidate interest points and the number of the parent interest points of the candidate interest points, third ordering information of the distance between the position of each candidate interest point and the target position in the distance between the positions of the candidate interest points and the target position, and fourth ordering information of the frequency of the selected candidate interest points in the frequency of the selected candidate interest points into the target interest point probability information obtaining model to obtain probability information of whether each candidate interest point in the candidate interest points corresponds to the target interest point selected by the user or not.

After the probability information of each candidate interest point in the candidate interest points is obtained, the probability information can be sorted from large to small according to the numerical value, and the sorting information of the probability information is obtained; then, the candidate interest points are ranked according to the ranking information of the probability information, the ranking information of the candidate interest points is obtained, and then a candidate interest point ranking list is obtained.

The above is the first way of obtaining the ranking information of the candidate points of interest, and the following is a description of the second way of obtaining the ranking information of the candidate points of interest.

When the user selects a location by the stamp dot without finding a suitable dot, the user may determine a target location based on the keyword input by the user by inputting a keyword on the page as shown in fig. 2.

Then, based on the target position determined by the keyword, a plurality of candidate interest points are recalled.

After obtaining a plurality of candidate points of interest, different from the first way: in the method, evaluation score information of whether each candidate interest point in the candidate interest points can become a target interest point selected by a user or not is obtained according to the attribute information of each candidate interest point in the candidate interest points. Likewise, the attribute information includes at least one of usage type information of the candidate interest point, a number of child interest points of the candidate interest point, and a number of parent interest points of the candidate interest point.

Specifically, as an embodiment of obtaining evaluation score information of whether each candidate interest point in the plurality of candidate interest points can become a target interest point selected by the user: inputting the attribute information of each candidate interest point in the candidate interest points into a target interest point evaluation score information obtaining model, and obtaining evaluation score information of whether each candidate interest point in the candidate interest points corresponds to the target interest point selected by the user. In this manner, the manner of inputting the attribute information of each candidate interest point of the multiple candidate interest points into the target interest point evaluation score information obtaining model is similar to the manner of inputting the attribute information of each candidate interest point of the multiple candidate interest points into the target interest point probability information obtaining model, and for the specific manner of inputting the model, reference is made to the first manner of obtaining the ranking information of the multiple candidate interest points, and details are not repeated here.

Different from the first method for obtaining the ranking information of the candidate interest points, in the second method for obtaining the ranking information of the candidate interest points, the interest point with the highest evaluation score in the candidate interest points is used as the first ranked interest point recommended to the user.

Based on this, the first ranked point of interest in the candidate point of interest list has been obtained. In order to enable the user to select other candidate interest points through the candidate interest point list, the ranking information of other candidate interest points except the interest point ranked at the first position among the candidate interest points is also required to be obtained.

Specifically, obtaining the ranking information of other candidate interest points of the plurality of candidate interest points except the first ranked interest point may refer to: firstly, obtaining the text similarity between the description information corresponding to other candidate interest points except the first-ranked interest point in the plurality of candidate interest points and the keyword information for determining the target address input by the user. And then, ranking other candidate interest points based on the text similarity to obtain ranking information of the other candidate interest points.

After obtaining the ranking information of other candidate interest points, ranking the other candidate interest points after the first ranked interest point according to the ranking of the other candidate interest points, and obtaining the ranking information of a plurality of candidate interest points, thereby obtaining a candidate interest point ranking list.

For example, when the keyword input by the user is "mansion 3 level 301 room", the target interest point evaluation score information obtaining model is input with attribute information of each candidate interest point "mansion E, mansion east, mansion west, mansion east 3 level, and mansion south" so that the evaluation score among the obtained candidate interest points is "mansion east 3 level". Thus, "east zone 3 of building E" may be the first ranked point of interest of the plurality of candidate point of interest lists.

And then, performing text similarity matching on the description information 'E mansion, east mansion, west mansion and south mansion' of the other candidate interest points and the keyword 'E mansion 3-layer 301 room', and sequencing the 'E mansion, east mansion, west mansion and south mansion' based on the text similarity matching process. Suppose the other candidate interest points have the following ordering results: e mansion, E mansion west, E mansion east, and E mansion south. Then the order of the candidate interest point list obtained finally is: e building east 3 layers, E building west, E building east, and E building south.

Fig. 1 to fig. 3 described above are diagrams of an application scenario of the information processing method of the present application, and an embodiment of the present application does not specifically limit the application scenario of the information processing method, and the application scenario of the information processing method is only one embodiment of the application scenario of the information processing method provided by the present application, and the application scenario is provided to facilitate understanding of the information processing method provided by the present application, and is not used to limit the information processing method provided by the present application. In the embodiment of the present application, no further description is given to other application scenarios of the information processing method.

First embodiment

A first embodiment of the present application provides an information processing method, which is described below with reference to fig. 4.

Please refer to fig. 4, which is a flowchart illustrating an information processing method according to a first embodiment of the present application.

The information processing method of the embodiment of the application comprises the following steps:

step S401: determining a target position selected by a user on a current display map; and acquiring target text information which is input by a user and used for determining a target address, and determining a target position according to the target text information.

When the user fills in the receiving address information, a target position is selected to obtain a recommended candidate interest point list.

There are various ways to determine the target location provided by the user, and two ways may be: determining a target position selected by a user on a current display map; or acquiring target text information which is input by a user and used for determining a target address, and determining a target position according to the target text information.

For example, referring to fig. 2, when a user stamps a point on a presented map, the point stamped by the user may be taken as an example of a target location selected on the currently presented map. When a user inputs a keyword in the "please input an address" search box shown in fig. 2, the input keyword may be used as an example of target text information input by the user for determining a target address.

In the application, the ranking information of the candidate interest points finally obtained in the mode of stamping points is used as a first mode for obtaining the ranking information of the candidate interest points, and the ranking information of the candidate interest points obtained in the mode of inputting keywords is used as a second mode for obtaining the ranking information of the candidate interest points. The first way to obtain ranking information for a plurality of candidate points of interest may be different from the second way to obtain ranking information for a plurality of candidate points of interest. The first way to obtain ranking information for multiple candidate points of interest focuses on "recommending" key points to the user; the first way to obtain ranking information for multiple candidate points of interest focuses on embodying the "search" key point.

Step S402: based on the target location, a plurality of candidate points of interest are recalled.

As an embodiment for recalling a plurality of candidate points of interest based on the target location: recalling interest points within a specified distance range of the target position based on the target position; and taking the interest points within the specified distance range of the target position as a plurality of candidate interest points.

When the user determines the target location by inputting the keyword, as an implementable manner for recalling a plurality of candidate points of interest based on the target location, it may further be: and recalling the interest points with the description information similar to the keywords. For example, the input keyword is "Zhongji building", and the certain interest point recalled may be "Zhongji building". The 'Zhonghui mansion' is the description information of the recalled interest points.

Step S403: obtaining ranking information of the candidate interest points according to the attribute information of each candidate interest point in the candidate interest points; the attribute information includes at least one of usage type information of the candidate interest point, a number of child interest points of the candidate interest point, and a number of parent interest points of the candidate interest point.

There are various ways to obtain ranking information of multiple candidate interest points according to the attribute information of each candidate interest point in the multiple candidate interest points, and two ways to obtain ranking information of multiple candidate interest points according to the attribute information of each candidate interest point in the multiple candidate interest points are specifically introduced.

The first way to obtain the ranking information of multiple candidate interest points according to the attribute information of each candidate interest point in the multiple candidate interest points is described in detail as follows,

in a first manner of obtaining ranking information of a plurality of candidate points of interest based on attribute information of each of the plurality of candidate points of interest, a target location is selected by way of a user stamp point.

Specifically, in a first manner of obtaining ranking information of a plurality of candidate interest points according to attribute information of each candidate interest point of the plurality of candidate interest points, first, probability information of whether each candidate interest point of the plurality of candidate interest points corresponds to a target interest point selected by a user is obtained according to the attribute information of each candidate interest point of the plurality of candidate interest points; then, based on the probability information, ranking information of the candidate interest points is obtained.

In this embodiment, the target point of interest is a point of interest for obtaining a shipping address corresponding to the delivered item.

More specifically, as a way of obtaining probability information of whether each candidate interest point of the plurality of candidate interest points can become a target interest point selected by a user according to the attribute information of each candidate interest point of the plurality of candidate interest points, the following may be mentioned: inputting the attribute information of each candidate interest point in the candidate interest points into a target interest point probability information obtaining model, and obtaining probability information of whether each candidate interest point in the candidate interest points corresponds to the target interest point selected by a user.

The target interest point probability information obtaining model is continuously updated and optimized in the using process, so that probability information obtained by the updated target interest point probability information obtaining model is more accurate. The manner in which the optimization model is updated may be as described below: firstly, determining a target interest point selected by a user from a plurality of candidate interest points; and then, taking the target interest point and the user characteristic information corresponding to the user as training samples, training the target interest point probability information acquisition model, and acquiring the updated target interest point probability information acquisition model.

For example, some interest points in the candidate interest points may be selected by the target user, and some interest points may not be selected by the target user, and the target interest point probability information obtaining model is trained by using the determined target interest points selected by the target user and the user feature information of the target user as training samples, so as to obtain the updated target interest point probability information obtaining model. Therefore, the target interest point probability information obtaining model can be always in the training process, and the obtained probability information is more and more reliable.

The user characteristic information can refer to characteristic information of occupation and the like of the user, a large number of users are clustered through the user characteristic information, which interest points are easy to select by a certain group of users can be obtained, and probability information obtained through a target interest point probability information obtaining model is more reliable and accurate.

In order to improve the accuracy of the obtained probability information and facilitate processing of a large amount of information or a large amount of data, the attribute information of each candidate interest point in the plurality of candidate interest points is input into the target interest point probability information obtaining model to obtain probability information of whether each candidate interest point in the plurality of candidate interest points can be a target interest point selected by a user, and the following method can be used.

First, first ordering information of the number of the child interest points of each candidate interest point in the number of the child interest points of the plurality of candidate interest points and second ordering information of the number of the parent interest points of each candidate interest point in the number of the parent interest points of the plurality of candidate interest points are obtained.

And then inputting at least one of the first sequencing information, the second sequencing information and the use type information of each candidate interest point in the plurality of candidate interest points into a target interest point probability information obtaining model to obtain probability information of whether each candidate interest point in the plurality of candidate interest points corresponds to the target interest point selected by the user.

In addition, the attribute information further includes a distance between a position of the candidate interest point and the target position, and a frequency of selecting the candidate interest point.

Therefore, as the attribute information of each candidate interest point in the plurality of candidate interest points is input into the target interest point probability information obtaining model, obtaining probability information of whether each candidate interest point in the plurality of candidate interest points corresponds to the target interest point selected by the user may further refer to: first, third ranking information of the distance between the position of each candidate interest point and the target position in the distance between the positions of the candidate interest points and the target position and fourth ranking information of the frequency of the selected candidate interest points in the frequency of the selected candidate interest points are obtained. And then inputting at least one of the use type information of the candidate interest points, the number of the child interest points of the candidate interest points, the number of the parent interest points of the candidate interest points, third sequencing information and fourth sequencing information into a target interest point probability information obtaining model to obtain probability information of whether each candidate interest point in the plurality of candidate interest points corresponds to the target interest point selected by the user.

In this embodiment, the target interest point probability information obtaining model adopts at least one of the following algorithms: a bagging algorithm, a random forest algorithm, a boosting algorithm, and an Xgboost algorithm.

After probability information whether each candidate interest point in the candidate interest points can become a target interest point selected by a user is obtained, based on the probability information, ranking information of the candidate interest points is obtained.

In this embodiment, as a way of obtaining ranking information of multiple candidate interest points based on probability information, it may refer to: firstly, obtaining initial sequencing information of a plurality of candidate interest points based on probability information; and then, reordering the initially ordered candidate interest points based on a preset ordering strategy to obtain reordering information of the candidate interest points.

Specifically, the reordering of the initially ordered candidate interest points based on the preset ordering policy may refer to: and reordering the initially ordered plurality of candidate interest points based on the preset blacklist interest point. The re-ranking of the initially ranked candidate interest points is equivalent to precise ranking, and the ranking of the candidate interest points can be more accurate. For example, when a candidate point of interest is found to rank higher, but is found to be a blacklisted point of interest, the candidate point of interest may be moved backwards in the sequence or deleted among the initially ordered plurality of candidate points of interest. On the contrary, if a candidate interest point can be found in the white list interest points, the sequence is moved forward.

In this embodiment, as obtaining the ranking information of the candidate interest points based on the probability information, the following may be mentioned: and sequencing the probability information from large to small according to the numerical value, and further obtaining sequencing information of a plurality of candidate interest points.

The above is a related description of a first manner of obtaining ranking information of a plurality of candidate interest points according to attribute information of each of the plurality of candidate interest points, and a second manner of obtaining ranking information of a plurality of candidate interest points according to attribute information of each of the plurality of candidate interest points is described below.

In a second manner of obtaining ranking information of a plurality of candidate interest points according to attribute information of each of the plurality of candidate interest points, a target position is determined in a manner that a user inputs a keyword.

In this manner, a keyword input by the user serves as an example of target text information input by the user for determining a target address. Namely: the target text information may refer to a keyword that is input in order to obtain a candidate point of interest list when filling out a shipping address. For example, it may refer to a keyword entered in a "please enter address" search box in the page as shown in fig. 2.

When the user inputs the keyword, as recalling a plurality of candidate interest points based on the target location, the following may be also mentioned: firstly, recalling interest points with description information similar to target text information; then, among the interest points with the description information similar to the target text information, the interest points in the specified distance range of the target position are screened, and the interest points in the specified distance range of the target position are used as a plurality of candidate interest points.

As a second way of obtaining ranking information of a plurality of candidate interest points according to attribute information of each candidate interest point in the plurality of candidate interest points, the second way may specifically be: firstly, obtaining evaluation score information whether each candidate interest point in the candidate interest points can become a target interest point selected by a user or not according to the attribute information of each candidate interest point in the candidate interest points; then, based on the evaluation score information, ranking information of the candidate interest points is obtained.

In this embodiment, the evaluation score information of whether each candidate interest point of the plurality of candidate interest points can become the target interest point selected by the user is obtained according to the attribute information of each candidate interest point of the plurality of candidate interest points, and may be: inputting the attribute information of each candidate interest point in the candidate interest points into a target interest point evaluation score information obtaining model, and obtaining evaluation score information of whether each candidate interest point in the candidate interest points corresponds to the target interest point selected by the user.

In this embodiment, the target interest point evaluation score information obtaining model may adopt an Xgboost algorithm.

Similar to the optimization updating of the target interest point probability information obtaining model, the target interest point evaluation score information obtaining model can also be optimized and updated. For optimization and update of the model, please refer to the first explanation about optimization and update of the model in a manner of obtaining ranking information of a plurality of candidate interest points according to attribute information of each candidate interest point in the plurality of candidate interest points, which is not described herein again.

Similarly, the data amount or the information amount that may be related to the attribute information of each candidate interest point in the plurality of candidate interest points is large, and in order to improve the accuracy of the obtained evaluation score information and facilitate processing of a large amount of information or a large amount of data, the attribute information of each candidate interest point in the plurality of candidate interest points is input into the target interest point evaluation score information obtaining model to obtain evaluation score information of whether each candidate interest point in the plurality of candidate interest points corresponds to the target interest point selected by the user, which may be as follows.

And then inputting at least one of the first sequencing information, the second sequencing information and the use type information of each candidate interest point in the plurality of candidate interest points into a target interest point evaluation score information obtaining model to obtain evaluation score information of whether each candidate interest point in the plurality of candidate interest points corresponds to the target interest point selected by the user.

In addition, similarly, the attribute information further includes a distance between the position of the candidate interest point and the target position, and a frequency of selecting the candidate interest point.

Therefore, as inputting the attribute information of each candidate interest point in the plurality of candidate interest points into the target interest point evaluation score information obtaining model, obtaining evaluation score information of whether each candidate interest point in the plurality of candidate interest points corresponds to the target interest point selected by the user or not may further refer to: first, third ranking information of the distance between the position of each candidate interest point and the target position in the distance between the positions of the candidate interest points and the target position and fourth ranking information of the frequency of the selected candidate interest points in the frequency of the selected candidate interest points are obtained. And then inputting at least one of the use type information of the candidate interest points, the number of the child interest points of the candidate interest points, the number of the parent interest points of the candidate interest points, third sequencing information and fourth sequencing information into a target interest point evaluation score information obtaining model to obtain evaluation score information of whether each candidate interest point in the plurality of candidate interest points corresponds to the target interest point selected by the user.

After obtaining evaluation score information of whether each candidate interest point in the plurality of candidate interest points can become a target interest point selected by the user, obtaining ranking information of the plurality of candidate interest points based on the evaluation score information may refer to: and taking the interest point with the highest evaluation score in the candidate interest points as the first-ranked interest point recommended to the user.

In order to show the candidate interest points except the first-ranked interest point in the candidate interest points to the user, the method may further obtain ranking information of other candidate interest points except the first-ranked interest point in the candidate interest points, and obtain ranking information of the candidate interest points based on the ranking information of the other candidate interest points.

Specifically, as obtaining the ranking information of other candidate interest points except the first ranked interest point from the multiple candidate interest points, the following may be specifically mentioned: firstly, obtaining the text similarity between the description information corresponding to other candidate interest points except the first ranked interest point in the candidate interest points and the target text information input by the user and used for determining the target address; and then, ranking other candidate interest points based on the text similarity to obtain ranking information of the other candidate interest points.

The first obtained ranking information of the candidate points of interest is ranking information obtained based on the way of the point stamping adopted by the user, and in the first ranking way, the emphasis is on recommending surrounding points of interest to the user according to the ranking. And if the proper interest points cannot be obtained from the ranking information obtained in the adopted stamping point mode, obtaining ranking information of a plurality of candidate interest points by adopting a second mode, wherein the ranking information of the candidate interest points obtained by the second mode is the ranking information obtained based on the mode that the user inputs keywords, and in the second ranking mode, the emphasis is to provide the first ranked interest points to the user according to the ranking and substantially provide the searched interest points to the client. The first mode of obtaining the ranking information of the candidate interest points is combined with the second mode of obtaining the ranking information of the candidate interest points to form a mode that the peripheral search focuses on 'recommendation' and the keyword search focuses on 'search'.

In the present embodiment, the ranking information of the plurality of candidate interest points is obtained based on at least one attribute information of the usage type information of the candidate interest points, the number of child interest points of the candidate interest points, and the number of parent interest points of the candidate interest points. In this way, the target position selected by the user on the current display map is determined at the same time; and target text information which is input by the user and used for determining the target address is obtained, the target position is determined according to the target text information, the obtained ranking information of the candidate interest points is enabled to be more accurate and reasonable, the target interest points selected by the user in the follow-up process based on the ranking information of the candidate interest points can be enabled to be more matched with the receiving address, and distribution can be conducted by distribution personnel based on the delivery address greatly.

Second embodiment

In correspondence with the information processing method provided in the first embodiment of the present application, a second embodiment of the present application correspondingly provides an information processing apparatus. Since the device embodiment is substantially similar to the first embodiment, it is relatively simple to describe, and reference may be made to some descriptions of the first embodiment for relevant points. The device embodiments described below are merely illustrative.

Fig. 5 is a schematic diagram of an information processing apparatus according to a second embodiment of the present application.

The information processing apparatus includes: a target position determining unit 501, configured to determine a target position selected by a user on a current display map; acquiring target text information which is input by the user and used for determining a target address, and determining a target position according to the target text information; a recalling unit 502, configured to recall a plurality of candidate points of interest based on the target location; a ranking information obtaining unit 503, configured to obtain ranking information of the candidate interest points according to attribute information of each candidate interest point in the candidate interest points, where the attribute information includes at least one of usage type information of the candidate interest points, a number of child interest points of the candidate interest points, and a number of parent interest points of the candidate interest points.

Optionally, the sorting information obtaining unit is specifically configured to: obtaining probability information whether each candidate interest point in the candidate interest points can become a target interest point selected by the user or not according to the attribute information of each candidate interest point in the candidate interest points; based on the probability information, obtaining ranking information of the candidate interest points.

Optionally, the sorting information obtaining unit is specifically configured to: inputting the attribute information of each candidate interest point in the candidate interest points into a target interest point probability information obtaining model, and obtaining probability information of whether each candidate interest point in the candidate interest points corresponds to the target interest point selected by the user.

Optionally, the method further includes: a model updating unit; the model updating unit is specifically configured to: determining a target point of interest selected by the user from the plurality of candidate points of interest; and taking the target interest point and the user characteristic information corresponding to the user as training samples, training the target interest point probability information obtaining model, and obtaining the updated target interest point probability information obtaining model.

Optionally, the sorting information obtaining unit is specifically configured to: obtaining initial ranking information of the candidate interest points based on the probability information; and reordering the initially ordered candidate interest points based on a preset ordering strategy to obtain reordering information of the candidate interest points.

Optionally, the sorting information obtaining unit is specifically configured to: and reordering the initially ordered plurality of candidate interest points based on the preset blacklist interest point.

Optionally, the sorting information obtaining unit is specifically configured to: obtaining first ordering information of the number of the child interest points of each candidate interest point in the number of the child interest points of the candidate interest points, and second ordering information of the number of the parent interest points of each candidate interest point in the number of the parent interest points of the candidate interest points; inputting at least one of the first ranking information, the second ranking information, and the usage type information of each candidate interest point in the candidate interest points into a target interest point probability information obtaining model, and obtaining probability information of whether each candidate interest point in the candidate interest points corresponds to the target interest point selected by the user.

Optionally, the sorting information obtaining unit is specifically configured to: obtaining third ranking information of the distance between the position of each candidate interest point and the target position in the distance between the positions of the candidate interest points and the target position and fourth ranking information of the frequency of the selected candidate interest points in the frequency of the selected candidate interest points; inputting at least one of the usage type information of the candidate interest points, the number of the child interest points of the candidate interest points, the number of the parent interest points of the candidate interest points, the third ordering information and the fourth ordering information into a target interest point probability information obtaining model, and obtaining probability information of whether each candidate interest point of the candidate interest points corresponds to the target interest point selected by the user.

Optionally, the sorting information obtaining unit is specifically configured to: obtaining evaluation score information whether each candidate interest point in the candidate interest points can become a target interest point selected by the user or not according to the attribute information of each candidate interest point in the candidate interest points; obtaining ranking information of the candidate interest points based on the evaluation score information.

Optionally, the sorting information obtaining unit is specifically configured to: inputting the attribute information of each candidate interest point in the candidate interest points into a target interest point evaluation score information obtaining model, and obtaining evaluation score information of whether each candidate interest point in the candidate interest points corresponds to the target interest point selected by the user.

Optionally, the sorting information obtaining unit is specifically configured to: and taking the interest point with the highest evaluation score in the candidate interest points as the first-ranked interest point recommended to the user.

Optionally, the sorting information obtaining unit is further configured to: obtaining the ranking information of other candidate interest points except the interest point ranked at the first position in the candidate interest points; obtaining ranking information of the candidate interest points based on the ranking information of the other candidate interest points.

Optionally, the sorting information obtaining unit is specifically configured to: obtaining text similarity between description information corresponding to other candidate interest points except the first ranked interest point in the candidate interest points and target text information input by the user and used for determining a target address; and ranking the other candidate interest points based on the text similarity to obtain ranking information of the other candidate interest points.

Third embodiment

Corresponding to the method of the first embodiment of the present application, a third embodiment of the present application further provides an electronic device.

As shown in fig. 6, fig. 6 is a schematic view of an electronic device provided in a third embodiment of the present application.

The electronic device includes: a processor 601; a memory 602 for storing a computer program to be executed by the processor for performing the method of the first embodiment.

Fourth embodiment

In correspondence with the method of the first embodiment of the present application, a fourth embodiment of the present application also provides a computer storage medium storing a computer program that is executed by a processor to perform the method of the first embodiment.

Although the present application has been described with reference to the preferred embodiments, it is not intended to limit the present application, and those skilled in the art can make variations and modifications without departing from the spirit and scope of the present application, therefore, the scope of the present application should be determined by the claims that follow.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

1. Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer-readable medium does not include non-transitory computer-readable storage media (non-transitory computer readable storage media), such as modulated data signals and carrier waves.

2. As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Claims

1. An information processing method characterized by comprising:

determining a target position selected by a user on a current display map; acquiring target text information which is input by the user and used for determining a target address, and determining a target position according to the target text information;

recalling a plurality of candidate points of interest based on the target location;

obtaining ranking information of the candidate interest points according to attribute information of each candidate interest point in the candidate interest points, wherein the attribute information comprises at least one of usage type information of the candidate interest points, the number of child interest points of the candidate interest points and the number of parent interest points of the candidate interest points.

2. The method of claim 1, wherein obtaining ranking information of the candidate interest points according to the attribute information of each candidate interest point of the candidate interest points comprises:

obtaining probability information whether each candidate interest point in the candidate interest points can become a target interest point selected by the user or not according to the attribute information of each candidate interest point in the candidate interest points;

based on the probability information, obtaining ranking information of the candidate interest points.

3. The method according to claim 2, wherein obtaining probability information of whether each candidate interest point of the candidate interest points can become a target interest point selected by the user according to the attribute information of each candidate interest point of the candidate interest points comprises:

inputting the attribute information of each candidate interest point in the candidate interest points into a target interest point probability information obtaining model, and obtaining probability information of whether each candidate interest point in the candidate interest points corresponds to the target interest point selected by the user.

4. The method of claim 3, further comprising:

determining a target point of interest selected by the user from the plurality of candidate points of interest;

and taking the target interest point and the user characteristic information corresponding to the user as training samples, training the target interest point probability information obtaining model, and obtaining the updated target interest point probability information obtaining model.

5. The method of claim 2, wherein obtaining ranking information of the candidate points of interest based on the probability information comprises:

obtaining initial ranking information of the candidate interest points based on the probability information;

and reordering the initially ordered candidate interest points based on a preset ordering strategy to obtain reordering information of the candidate interest points.

6. The method of claim 5, wherein the re-ranking the initially ranked plurality of candidate points of interest based on a preset ranking policy comprises:

and reordering the initially ordered plurality of candidate interest points based on the preset blacklist interest point.

7. The method of claim 3, wherein the inputting the attribute information of each candidate interest point of the plurality of candidate interest points into a target interest point probability information obtaining model to obtain probability information of whether each candidate interest point of the plurality of candidate interest points corresponds to a target interest point selected by the user comprises:

obtaining first ordering information of the number of the child interest points of each candidate interest point in the number of the child interest points of the candidate interest points, and second ordering information of the number of the parent interest points of each candidate interest point in the number of the parent interest points of the candidate interest points;

inputting at least one of the first ranking information, the second ranking information, and the usage type information of each candidate interest point in the candidate interest points into a target interest point probability information obtaining model, and obtaining probability information of whether each candidate interest point in the candidate interest points corresponds to the target interest point selected by the user.

8. An information processing apparatus characterized by comprising:

the target position determining unit is used for determining a target position selected by a user on the current display map; acquiring target text information which is input by the user and used for determining a target address, and determining a target position according to the target text information;

a recall unit for recalling a plurality of candidate interest points based on the target location;

the ranking information obtaining unit is configured to obtain ranking information of the candidate interest points according to attribute information of each candidate interest point in the candidate interest points, where the attribute information includes at least one of usage type information of the candidate interest points, a number of child interest points of the candidate interest points, and a number of parent interest points of the candidate interest points.

9. An electronic device, comprising:

a processor;

a memory for storing a computer program for execution by the processor to perform the method of any one of claims 1 to 7.

10. A computer storage medium, characterized in that it stores a computer program that is executed by a processor to perform the method of any one of claims 1-7.