CN113672823A

CN113672823A - User native place prediction method and device

Info

Publication number: CN113672823A
Application number: CN202110910107.XA
Authority: CN
Inventors: 苏照杰
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2021-08-09
Filing date: 2021-08-09
Publication date: 2021-11-19

Abstract

The specification discloses a method and a device for predicting user native place, and particularly discloses that historical service data of a user in history are acquired, and historical events corresponding to the user in history are determined according to the service data. And then, generating an event information time sequence of the user in history according to history event information corresponding to each history event, wherein for each history event, the history event information corresponding to the history event comprises time information corresponding to the history event and geographical location information corresponding to the history event. Then, according to the event information time sequence, determining the change characteristics of the geographic position corresponding to each historical event in time and the attribute characteristics of the geographic position corresponding to each historical event, and predicting the native place of the user according to the change characteristics and the attribute characteristics. Therefore, the method and the device effectively improve the accuracy of the predicted native place of the user and improve the user experience.

Description

User native place prediction method and device

Technical Field

The specification relates to the technical field of internet, in particular to a user native place prediction method and device.

Background

With the rapid development of information technology, the cost for obtaining information by individuals is higher and higher, so that the service platform often predicts the preference of the users based on the personal basic information and behavior habits of the users, and then performs targeted information push according to the preference of the users, thereby improving the user experience.

In some service scenarios, the native location of the user often has a certain influence on the preference of the user. For example, in the catering business, Sichuan people may prefer to have a common cold dish and a string of Chinese rice roll, Shanxi people may prefer a bubble bun and a Chinese hamburger, and thus, the native place of a user is an extremely important reference item when predicting the dietary preference of the user.

At present, a service platform mainly determines the native place of a user from user authentication information. For the user which is not authenticated, the service platform needs to predict the native place of the user according to the user positioning data collected during the spring festival, and at the moment, the default is that most users return to the country during the spring festival.

However, with the development of society, more and more people accept the service platform in the working place in the past year, and the situation of the service platform in different places in the past year is more and more common, at this moment, the service platform still predicts the native place of the user according to the positioning data of the user in the spring festival, and the problem of low accuracy will occur.

Disclosure of Invention

The present specification provides a method and an apparatus for predicting a user's native place, so as to partially solve the above problems in the prior art.

The technical scheme adopted by the specification is as follows:

the specification provides a user native prediction method, which comprises the following steps:

acquiring historical service data of a user;

determining historical events corresponding to the user in history according to the service data;

generating an event information time sequence of the user in history according to the history event information corresponding to each history event, wherein the history event information corresponding to each history event comprises the time information corresponding to the history event and the geographical position information corresponding to the history event;

and determining the change characteristics of the geographic position corresponding to each historical event in time and the attribute characteristics of the geographic position corresponding to each historical event according to the event information time sequence, and predicting the native place of the user according to the change characteristics and the attribute characteristics.

Optionally, the geographic location information corresponding to the historical event includes a geographic area related to the historical event and description information of the geographic area corresponding to the historical event;

determining the change characteristics of the geographic position corresponding to each historical event in time and the attribute characteristics of the geographic position corresponding to each historical event according to the event information time sequence, wherein the determining specifically comprises the following steps:

determining the change characteristics of the geographic position corresponding to each historical event in time according to the event information time sequence and the geographic area related to each historical event, and

and for each historical event, determining the attribute characteristics of the geographic position corresponding to the historical event according to the description information of the geographic area corresponding to the historical event.

Optionally, the historical event includes at least one of a historical shopping event and a historical travel event.

Optionally, before generating the historical event information time sequence of the user in the history according to the historical event information corresponding to each historical event, the method further includes:

acquiring positioning data acquired aiming at the user at each set moment in history as historical positioning event information corresponding to the historical positioning event of the user;

and inserting the historical positioning events into historical events corresponding to the user in history according to the acquisition time of the historical positioning events, so as to generate an event information time sequence of the user in history according to the historical event information corresponding to the historical events and the sequence of the historical positioning event information corresponding to the historical positioning events in time.

Optionally, predicting the native place of the user according to the variation feature and the attribute feature specifically includes:

determining candidate native runs for the user according to the event information time sequence;

determining the confidence degree corresponding to each candidate native place according to the change characteristics and the attribute characteristics;

and predicting the native place of the user according to the confidence corresponding to each candidate native place.

Optionally, determining, according to the event information time series, a change characteristic of the geographic position corresponding to each historical event in time and an attribute characteristic of the geographic position corresponding to each historical event, and predicting a native place of the user according to the change characteristic and the attribute characteristic, specifically including:

and inputting the event information time sequence into a pre-trained prediction model, so that the prediction model determines the change characteristics of the geographic position corresponding to each historical event in time and the attribute characteristics of the geographic position corresponding to each historical event according to the event information time sequence, and predicts the native place of the user according to the change characteristics and the attribute characteristics.

Optionally, training the prediction model specifically includes:

acquiring a training sample, wherein the training sample comprises historical business data of a sample user determined to be actually native;

determining historical events corresponding to the sample user in history according to historical service data of the sample user;

generating an event information time sequence of the sample user in the history according to the history event information of each history event corresponding to the sample user in the history;

inputting the historical event information time series of the sample user into the prediction model to obtain the prediction native of the sample user;

and training the prediction model by taking the minimization of the deviation between the prediction native place and the actual native place as an optimization target.

The present specification provides a prediction apparatus of user's native place, comprising:

the acquisition module is used for acquiring historical service data of a user;

the event determining module is used for determining historical events corresponding to the user in history according to the service data;

an event sequence generating module, configured to generate an event information time sequence of the user in history according to history event information corresponding to each history event, where, for each history event, the history event information corresponding to the history event includes time information corresponding to the history event and geographical location information corresponding to the history event;

and the native place prediction module is used for determining the change characteristics of the geographic position corresponding to each historical event in time and the attribute characteristics of the geographic position corresponding to each historical event according to the event information time sequence and predicting the native place of the user according to the change characteristics and the attribute characteristics.

The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described prediction method by a user.

The present specification provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above-mentioned prediction method by a user when executing the program.

The technical scheme adopted by the specification can achieve the following beneficial effects:

in the prediction method for the user's native place provided by the present specification, historical service data of the user is obtained, and according to the service data, historical events corresponding to the user in the history are determined. And then, generating an event information time sequence of the user in history according to history event information corresponding to each history event, wherein for each history event, the history event information corresponding to the history event comprises time information corresponding to the history event and geographical location information corresponding to the history event. Then, according to the event information time sequence, determining the change characteristics of the geographic position corresponding to each historical event in time and the attribute characteristics of the geographic position corresponding to each historical event, and predicting the native place of the user according to the change characteristics and the attribute characteristics.

According to the method, when the native place of the user is predicted, the historical event information time sequence of the user in the history is determined based on the historical event time information and the position information which are executed in the user history, and then the change characteristic of the geographic position corresponding to each historical event in the time and the attribute characteristic of the geographic position corresponding to each historical event are determined based on the event information time sequence. Therefore, as the historical events are executed by the user, the change of the position information of the historical events along with the time, particularly the change of the position information of the historical events along with the time before and after holidays, will obviously reflect the geographical position of the user in or to the user in the freely arranged time, at this time, the place where the user passes through is predicted by comprehensively considering various factors such as the fact that the place where the user passes through or to the geographical position belongs to the residential land, or the fact that the geographical position where the user passes through is a town without tourism characteristics, and the like, the accuracy of the predicted place where the user passes through is effectively improved, and the user experience is improved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:

FIG. 1 is a flow chart of a prediction method for native place of a user in the present specification;

FIG. 2 is a schematic flow chart of the training of a predictive model for predicting the whereabouts of a user in the present specification;

FIG. 3 is a schematic diagram of a user native prediction device provided herein;

fig. 4 is a schematic diagram of an electronic device corresponding to fig. 1 provided in the present specification.

Detailed Description

In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.

In daily life, part of services executed by people can keep the geographical positions related to the users when the users execute the services. After the geographic positions corresponding to the services are obtained according to the occurrence time of the services and a time sequence related to the geographic positions is formed, the time sequence can obviously reflect the change of the position of the user along with the time. At this time, if the attributes of the geographical locations (such as houses, business districts, tourist scenic spots, etc.) involved when the user performs each service are determined, it is possible to reasonably predict the change of the geographical locations involved when the user performs the service to some extent, and determine the native place of the user from the geographical locations. Therefore, the situation that the predicted user native accuracy is low due to the fact that the platform predicts the user native based on the positioning data during the spring festival of the user is effectively avoided, and the user predicted user native accuracy is improved.

The following will explain in detail the prediction scheme provided in this specification by the user in conjunction with the examples.

Fig. 1 is a schematic flow chart of a user native prediction method in this specification, which specifically includes the following steps:

step S100, acquiring historical service data of the user.

The execution subject of the prediction method native to the user provided in the present specification may be a platform or a server, or may be a terminal device such as a desktop computer. For convenience of description, the following description will be made by taking only the platform as an execution subject.

In a specific implementation, the service data acquired by the platform may be service data of all executed services in the history of the user, or may be service data that has been executed in a time period (for example, the last three years) set in the history of the user. The service corresponding to the service data may be a service related to the location data, which has been executed by the user, and the service may be an online shopping service (including taking out on a take-out platform, purchasing fresh goods on a fresh goods platform, purchasing living goods on a comprehensive online shopping platform, etc.), an online ticket purchasing service (including purchasing train tickets or air tickets for travel, etc.), and the like. Each time the service is executed, the position information related to the execution of the service is recorded. For example, each time the user takes a take-out, there are at least two pieces of location information, namely, the user order placing address and the user meal receiving address. For another example, when the user purchases a travel train ticket each time, there are location information such as an getting-on station corresponding to the train ticket, a getting-off station corresponding to the train ticket, and a destination city where the user travels.

When the platform user is in historical service data, if the service is an online shopping service, the service data acquired by the platform is the service data in the service order generated by the user during each online shopping. If the service is an online ticket-buying service, the service data acquired by the platform is the service data in the ticket-buying order generated by the user each time the ticket is bought.

Step S102, determining each historical event corresponding to the user in history according to the service data.

In specific implementation, for each service, the platform determines that each service has been executed by the user in history from service data corresponding to the service, and each service execution is used as a historical event, and then combines the historical events determined under each service to obtain each historical event corresponding to the user in history. Wherein, aiming at different services, the platform determines different historical events. Namely, the historical events determined in the online shopping service are historical shopping events, and the historical events determined in the ticket purchasing service are historical travel events.

For example, in the online shopping service, each online shopping of the user can be regarded as a historical event (that is, each time the user orders for a take-out on a take-out platform, each time the user purchases a fresh food on a fresh food platform, the user purchases a fresh food on a comprehensive online shopping platform, the user purchases living goods on the comprehensive online shopping platform, and the user also purchases a historical shopping event). In the ticket buying service, each time a user buys and uses a ticket, a train ticket or an airplane ticket, the user can be used as a historical travel event. And then, all the determined historical shopping events and historical travel events of the platform are combined together to be used as historical events corresponding to the user in history.

Step S104, generating an event information time sequence of the user in history according to the history event information corresponding to each history event, wherein for each history event, the history event information corresponding to the history event comprises the time information corresponding to the history event and the geographical position information corresponding to the history event.

In specific implementation, the platform acquires historical event information corresponding to each historical event from service data of a service to which the historical event belongs, then sorts the historical events according to the time sequence of the historical events to obtain a sorting result, and then generates an event information time sequence of the user in the history according to the sorting result and the historical event information corresponding to the historical events. For each historical event, the time information corresponding to the historical event may be the time when the historical event is executed, and the geographical location information corresponding to the historical event includes the geographical area involved by the historical event and the description information of the geographical area corresponding to the historical event.

For example, each historical event corresponding to the user in history comprises a historical event a, a historical event B and a historical event C, wherein the event a occurs earlier than the historical event B and later than the historical event C. The platform generates the historical event information time series of the user, that is, historical event information corresponding to the historical event a, the historical event B and the historical event C is respectively acquired, and then the historical event information time series of the user in the history is generated according to the historical event information corresponding to each historical event: { historical event information corresponding to historical event C, historical event information corresponding to historical event a, and historical event information corresponding to historical event B }.

In addition, for the historical events determined in different services, the historical event information corresponding to the historical events is not exactly the same, and needs to be determined according to actual requirements, which will be described in the following.

For example, in an online shopping service, the time information corresponding to the historical event may be the time of generating the service order, and the geographic location information corresponding to the historical event may be the location where the user is located when the service order is generated (may be a city where the user is located, a city district where the user is located (county city), a street where the user is located (county town), and the like, that is, a geographic area related to the historical event), a shipping address of the service order (which may be description information of the geographic area corresponding to the historical event), and the like.

In the online ticket buying service, the time information corresponding to the historical event may be the departure time of the user using a corresponding public transportation means where the user takes a ticket or a train ticket or an airplane ticket, and the geographic location information corresponding to the historical event may include a city where the user's destination is located (which may be a geographic area related to the historical event) and a category of the transportation means taken to the destination (which may be description information of the geographic area corresponding to the historical event).

The size of the geographic area may be set according to actual requirements, which is not specifically limited in this specification.

In addition, in an actual application scenario, the number of historical events of the user is relatively limited, at this time, the platform can also obtain positioning data of the user according to preset time to enrich and predict data used by the user in native place, the auxiliary platform predicts the native place of the user according to the historical events, and accuracy of the predicted native place of the user is improved.

Specifically, before the platform generates the historical event information time sequence of the user, the platform may further obtain, as historical positioning event information corresponding to the historical positioning event of the user, positioning data acquired for the user at each set time in the history (for example, user positioning data acquired at 3 am every day), insert each historical positioning event into each historical event corresponding to the user in the history according to the acquisition time of each historical positioning event, and finally generate the historical event information time sequence of the user in the history according to the historical event information corresponding to each historical event and the chronological order of the historical positioning event information corresponding to each historical positioning event.

The collection time of the positioning data corresponding to each historical positioning event can be used as the time information corresponding to the historical positioning event, and meanwhile, the data related to the geographical position where the user is located in the positioning data can be used as the position information corresponding to the historical positioning event. In a specific implementation, the location information corresponding to the historical positioning event may include a longitude and latitude of a geographic location where the user is located, a city of the geographic location where the user is located, and a Point of Interest (POI) name associated with the geographic location where the user is located (e.g., a XXX mall, a XXX building, a XXX business center, a XXX cell, etc.).

Here, the geographic area corresponding to the historical positioning event may also be set according to the business requirement. In a specific implementation, the setting of the geographic area corresponding to the historical positioning event may be consistent with the setting of the geographic area corresponding to the historical event.

Step S106, determining the change characteristics of the geographic position corresponding to each historical event in time and the attribute characteristics of the geographic position corresponding to each historical event according to the event information time sequence, and predicting the native place of the user according to the change characteristics and the attribute characteristics.

In a specific implementation, when determining the change feature and the attribute feature, the platform determines, for each historical event, the attribute feature of the geographic location itself corresponding to the historical event according to the description information of the geographic area corresponding to the historical event, and determines the change feature of the geographic location corresponding to each historical event in terms of time according to the event information time series and the geographic area related to each historical event. Then, determining each candidate native place aiming at the user according to the event information time sequence, then determining the confidence corresponding to each candidate native place according to the determined change characteristics and attribute characteristics, and finally predicting the native place of the user according to the confidence corresponding to each candidate native place.

If the event information time sequence contains historical event information corresponding to historical events and historical positioning event information corresponding to historical positioning events, the platform determines the attribute characteristics of the geographic position corresponding to each event (including the historical events and the historical positioning events), and determines the change characteristics of the geographic position corresponding to each event in time according to the event information time sequence and the geographic area related to each event (including the historical events and the historical positioning events).

The following illustrates how the platform predicts the native place of the user based on historical events.

For example, historical events of the user include historical shopping events, and the platform determines the commodity category to which commodities purchased by the user belong according to each historical shopping event; judging whether the commodity category belongs to a preset specific category or not; if the historical shopping event belongs to the business order, the platform determines the geographic position corresponding to the user when the business order corresponding to the historical shopping event is generated and the business address of the business order corresponding to the historical shopping event; if the geographic position corresponding to the user is inconsistent with the service address, the platform improves the confidence that the service address is the native place of the user and reduces the confidence that the geographic position corresponding to the user is the native place of the user.

The specific commodity can be large household electrical appliance equipment, decoration materials and other commodities, and users working outside can not easily buy the large household electrical appliance equipment and the decoration materials from rented places before the working places have no own houses.

For another example, historical events of the user include historical trip events, and the platform determines, for each historical trip event, a destination corresponding to the historical trip event and trip time corresponding to the historical trip event; if the travel time is determined to be within the set time period, the confidence that the destination corresponding to the historical travel event is the native place of the user is improved, and meanwhile, the confidence that other alternative addresses are the native places of the user is reduced. The set time period includes a legal holiday, and the set time period may be a legal holiday or a time period formed by the legal holiday and set time before and after the legal holiday.

For another example, a user has a takeout order every day in city a between 26 to 30 days in 4 months, the delivery addresses are all XXX building XXX seats 504, and purchase and use an airplane ticket flying from city a to city B in 30 days in 4 months and an airplane ticket flying from city B to city a in 5 months and 5 days in 5 months, and there is a takeout order placed in city B in 3 days in 5 months, and the delivery addresses are 3 places 301 in XXX district XXX of XXX city XXX of XXX province in XXX, and are recovered to be a takeout order every day after 6 days in 5 months, and the delivery addresses are unchanged, and city B is a small and medium-sized city (non-tourist city).

Thus, when predicting the native place of the user, the platform determines that the candidate native place of the user is a city A and a city B, and sets an initial confidence corresponding to the city A and an initial confidence corresponding to the city B. Since 5 months 1-5 days are legal holidays, the user is mostly located in the city A in a plurality of periods of non-holidays, the specified take-out address is a commercial building, the user goes to the city B in the legal holiday period, the confidence that the city B is the user's place is improved by the platform, and the confidence that the city A is the user's place is reduced. Meanwhile, the city B is a non-tourism city, the specified takeaway meal receiving address is the property of resident residences, the confidence that the city B is the native place of the user is further improved, and the confidence that the city A is the native place of the user is reduced. Thus, city B is the user's native place with a higher confidence than city A is, at which point the platform prefers that city B be the user's native place.

Of course, the platform may also use pre-trained predictive models to predict the native place of the user.

Specifically, the platform inputs the event information time sequence into a pre-trained prediction model, so that the prediction model determines the change characteristics of the geographic position corresponding to each historical event in time and the attribute characteristics of the geographic position corresponding to each historical event according to the event information time sequence. Then, after determining each candidate native place for the user according to the event information time sequence, the platform determines the confidence degree corresponding to each candidate native place according to the determined change characteristics and the attribute characteristics, and finally predicts the native place of the user according to the confidence degree corresponding to each candidate native place.

The prediction model can be obtained by adopting a Recurrent Neural Network (RNN) RNN Neural Network training, the adopted loss function can be a multi-class cross entropy, and an optimizer adam is used for completing the training of the prediction model. Further, in order to improve the accuracy of the model, two layers of RNN neural networks may be superimposed to form a prediction model in this specification, so that the output of the first layer of RNN neural network is used as the input of the second layer of RNN neural network, the depth of the model is increased, and the capability of the prediction model to capture detailed features is improved.

In addition, as for the above mentioned prediction model for predicting the native place of the user, as shown in fig. 2, the present specification further provides a corresponding training method, which includes the following specific steps:

step 200, obtaining a training sample, wherein the training sample comprises historical business data of a sample user determined to be actually native.

In a specific implementation, the sample user whose actual native place is determined may be a user who has completed real-name authentication in a service supported by the platform, and the actual native place of the users may be native place information actively filled in by the user in the real-name authentication process, or native place information determined according to identification numbers filled in by the users.

Step 202, determining historical events corresponding to the sample user in history. And according to the historical service data of the sample user.

And 204, generating historical event information time series of the sample user according to historical event information of historical events corresponding to the sample user in history.

Step 206, inputting the historical event information time series of the sample user into the prediction model to obtain the prediction native of the sample user.

And step 208, training the prediction model by taking the deviation between the prediction native place and the actual native place as an optimization target.

In the training process, the native process of predicting the sample users is consistent with the actual prediction process described above, and is not illustrated here.

The following describes in detail the execution process of the prediction method native to the user in this specification with reference to examples, and only history takeout events are taken as history shopping events, history positioning events and history travel events as examples.

Firstly, the platform obtains order data (namely business data) of takeout orders (namely historical takeout events) completed by a user from historical takeout data of the user, obtains ticket ordering data (namely business data) of used tickets (namely historical travel events) from historical ticket buying data of the user, and randomly selects one piece of mobile phone positioning data from daily mobile phone positioning data of the user to serve as the positioning data (namely business data) of the historical positioning events of the day.

Then, for each historical take-out event, the platform determines the historical take-out event information (including the order-placing time (as the time information of the historical take-out event), the order-placing city (as the geographical area related to the historical take-out event), and the meal-receiving address (as the description information of the geographical area corresponding to the historical take-out event) corresponding to the historical take-out event from the order-placing data corresponding to the historical take-out event, meanwhile, for each historical travel event, the platform determines the historical travel event information (including the travel time (as the time information of the historical travel event), the destination city (as the geographical area related to the historical travel event), and the traffic type (such as trains and planes) (as the description information of the geographical area corresponding to the historical travel event) corresponding to the historical travel event from the order-placing data corresponding to the historical travel event, for each historical positioning event, the platform determines historical positioning event information (including positioning time (serving as time information of the historical positioning event), a positioning city (serving as a geographic area related to the historical positioning event), and a positioning poi address (serving as description information of the geographic area corresponding to the historical positioning event) corresponding to the historical positioning event from the mobile phone positioning data corresponding to the historical positioning event.

Next, the platform unifies the data format of the time information of each historical event, the geographical area related to each historical event, and the description information of the geographical area corresponding to each historical event. For example, the time information of each historical event is uniformly accurate to the day and is identified in a year-month-day form. Cities in the geographic area involved by each historical event are the same to city level and are represented in the form of city code (city code) on a global basis.

And then, the platform arranges the events according to the time sequence of the events to obtain a sequencing result, and generates an event information time sequence corresponding to the user according to the historical takeout event information, the historical positioning event information and the historical trip event information which are unified in data format.

In this process, for each historical event, the platform may perform one-hot coding on the time information of the historical event according to the date as a time feature, perform one-hot coding on the geographical area related to the historical event according to the city code as a location feature, convert a word in the description information of the geographical area corresponding to the historical event into a word vector and perform one-hot coding as a description feature, and then combine the time feature, the location feature, and the description feature corresponding to the historical event to obtain a combined feature corresponding to the historical event (i.e., an attribute feature of the geographical location itself corresponding to the historical event).

And finally, the platform splices the combined features corresponding to the events according to the occurrence time sequence (obtaining the change feature of the geographic position corresponding to each historical event in time and the attribute feature of the geographic position corresponding to each historical event), and inputs the combined features into a pre-trained prediction model to obtain the native place corresponding to the user.

In addition, in this specification, when the native place of the user is predicted, the confidence corresponding to the predicted native place may also be determined. Therefore, when the predicted user native place is used for executing the service, the users can be screened according to the confidence corresponding to the predicted user native place and the service requirement, and the service information is pushed to the users meeting the screening condition.

For example, when predicting user preferences to push user's favorite commodities to a user, the user is predicted based on information of various aspects of the user and not only based on native prediction, and thus, the confidence level of the predicted user native may be set to be low, for example, a user native with a confidence level higher than 0.8 may be regarded as credible data, which may be used to predict user preferences. For another example, when a business activity on the hometown topic of place a is developed, the target group targeted by the business is very specific (i.e. native to the user of place a), at this time, the business needs to be pushed to the user whose predicted native confidence of the user is higher than that of place a, for example, the business is pushed to the user whose predicted native confidence of the user is higher than 0.95.

Through the steps, when predicting the native place of the user, the platform determines the historical event information time sequence of the user based on the historical event time information and the position information which are executed by the user in the history, and then determines the change characteristic of the geographic position corresponding to each historical event in time and the attribute characteristic of the geographic position corresponding to each historical event. Therefore, because the historical events are executed by the user, the change of the position information of the historical events along with the time, particularly the change of the position information of the historical events along with the time before and after holidays, will obviously reflect the geographical position of the user in or to the user in the freely arranged time, at this time, the place where the user passes through is predicted by comprehensively considering the various factors that the place where the user passes through or to the geographical position belongs to the property of residential land, or the geographical position where the user passes through is a town without tourism characteristics, and the like, and the accuracy of the predicted place where the user passes through is effectively improved.

The above method for predicting the user whereabouts provided for one or more embodiments of the present specification is based on the same idea, and the present specification further provides a corresponding device for predicting the user whereabouts, as shown in fig. 3.

Fig. 3 is a schematic diagram of a user native prediction device provided in this specification, which specifically includes:

an obtaining module 300, configured to obtain historical service data of a user;

an event determining module 301, configured to determine, according to the service data, historical events corresponding to the user in history;

a time sequence generating module 302, configured to generate a historical event information time sequence of the user in history according to historical event information corresponding to each historical event, where, for each historical event, the historical event information corresponding to the historical event includes time information corresponding to the historical event and geographical location information corresponding to the historical event;

a native place prediction module 303, configured to determine, according to the event information time sequence, a change feature of the geographic location corresponding to each historical event in time and an attribute feature of the geographic location corresponding to each historical event, and predict a native place of the user according to the change feature and the attribute feature.

the native prediction module 303 is specifically configured to determine, according to the event information time series and the geographic area related to each historical event, a change characteristic of the geographic position corresponding to each historical event in time, and determine, for each historical event, an attribute characteristic of the geographic position corresponding to the historical event according to the description information of the geographic area corresponding to the historical event.

Optionally, the event determining module 301 is further configured to, according to historical event information corresponding to each historical event, before generating a historical event information time sequence of the user in the history, acquire positioning data acquired for the user at each historical set time, as historical positioning event information corresponding to the historical positioning event of the user; and inserting the historical positioning events into historical events corresponding to the user in history according to the acquisition time of the historical positioning events, so as to generate an event information time sequence of the user in history according to the historical event information corresponding to the historical events and the sequence of the historical positioning event information corresponding to the historical positioning events in time.

Optionally, the native place prediction module 303 is specifically configured to determine, according to the event information time series, candidate native places for the user; determining the confidence degree corresponding to each candidate native place according to the change characteristics and the attribute characteristics; and predicting the native place of the user according to the confidence corresponding to each candidate native place.

Optionally, the native relevance prediction module 303 is specifically configured to input the event information time series into a pre-trained prediction model, so that the prediction model determines, according to the event information time series, a change feature of the geographic position corresponding to each historical event in time and an attribute feature of the geographic position corresponding to each historical event, and predicts the native relevance of the user according to the change feature and the attribute feature.

Optionally, the apparatus further comprises:

a training module 304, configured to obtain a training sample, where the training sample includes historical business data of a sample user where an actual native place is determined; determining historical events corresponding to the sample user in history according to historical service data of the sample user; generating an event information time sequence of the sample user in the history according to the history event information of each history event corresponding to the sample user in the history; inputting the historical event information time series of the sample user into the prediction model to obtain the prediction native of the sample user; and training the prediction model by taking the minimization of the deviation between the prediction native place and the actual native place as an optimization target.

The present specification also provides a computer-readable storage medium storing a computer program operable to execute the method of predicting user native locations provided in fig. 1 above.

This specification also provides a schematic block diagram of the electronic device shown in fig. 4. As shown in fig. 4, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs the computer program to realize the user native prediction method described in the above fig. 1. Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

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.

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 a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description 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.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.

Claims

1. A method for predicting a user's native place, comprising:

acquiring historical service data of a user;

2. The method according to claim 1, wherein the geographical location information corresponding to the historical event comprises a geographical area involved by the historical event and description information of the geographical area corresponding to the historical event;

3. The method of claim 1 or 2, wherein the historical events include at least one of historical shopping events, historical travel events.

4. The method according to claim 1, wherein before generating the historical event information time series of the user in the history according to the historical event information corresponding to each historical event, the method further comprises:

5. The method of claim 1, wherein predicting the user's native place based on the variation characteristics and the attribute characteristics comprises:

6. The method according to claim 1, wherein a change characteristic of the geographic position corresponding to each historical event in time and an attribute characteristic of the geographic position corresponding to each historical event are determined according to the event information time series, and a native place of the user is predicted according to the change characteristic and the attribute characteristic, specifically comprising:

7. The method of claim 6, wherein training the predictive model comprises:

8. A prediction apparatus for user native place, comprising:

the acquisition module is used for acquiring historical service data of a user;

9. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1 to 7.

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 7 when executing the program.