# US 2021/0239486 A1 · Method and apparatus for predicting destination, electronic device and storage medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0239486 A1
- Document ID: US20210239486A1
- Status: Published application
- Kind: A1
- Application number: 17/213,872
- Filed: 2021-03-26
- Published: 2021-08-05
- Earliest claimed: 2020-08-26
- Assignees: Beijing Baidu Netcom Science Technology Co., Ltd.
- Applicants: Beijing Baidu Netcom Science and Technology Co., Ltd.
- Inventors: Zhenduo LIANG; Feng BING; Zichao YUAN; Yan ZHANG; Kaikai JIA
- Web page: https://patentgrep.com/patent/US20210239486A1

## CPC

- G06F 16/9537: Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
- G01C 21/3476: {using point of interest [POI] information, e.g. a route passing visible POIs}
- G01C 21/3484: {Personalized, e.g. from learned user behaviour or user-defined profiles}
- G01C 21/3617: {using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement}
- G06F 18/2113: by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F 18/24143: {Distances to neighbourhood prototypes, e.g. restricted Coulomb energy networks [RCEN]}
- G06F 18/24323: {Tree-organised classifiers}
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/00: Machine learning
- G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202)
- G06Q 30/0261: {based on user location}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

The present disclosure discloses a method and apparatus for predicting a destination, an electronic device and a storage medium, and relates to the field of artificial intelligence technology. A specific implementation comprises: acquiring personalized data of a user and space-time scenario data of the user at a current moment; predicting, through a pre-trained prediction model, a target destination of the user at the current moment based on the personalized data, the space-time scenario data and an attribute feature of each pre-determined candidate destination; and recommending the target destination to the user. The embodiment of the present disclosure may effectively improve the accuracy of the destination prediction and is suitable for more general travel scenarios, and thus, the user experience may be improved.

## Claims

### Claim 1

A method for predicting a destination, comprising:
acquiring personalized data of a user and space-time scenario data of the user at a current moment;
predicting, through a pre-trained prediction model, a target destination of the user at the current moment based on the personalized data, the space-time scenario data and an attribute feature of each pre-determined candidate destination; and
recommending the target destination to the user.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the personalized data comprises at least user feature data and behavior feature data, the user feature data comprises at least one of: a gender, an age, an occupation category, an industry to which the user belongs, a company to which the user belongs, an income level, an asset condition, or a consumption level, the behavior feature data comprises at least one of: a retrieval location, a navigation location, or a arrival location, and the attribute feature comprises at least one of: location coordinates of the each candidate destination, a type of a point of interest, or a location tag.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the predicting comprises:
inputting the personalized data, the space-time scenario data and the attribute feature into a pre-trained machine learning model, the machine learning model comprising a linear model, a tree model, and a neural network model; and
outputting the target destination through the machine learning model.

### Claim 4 (depends on 3)

The method according to claim 3, wherein the outputting comprises:
calculating, through the machine learning model, a probability value of being selected or a probability value of being unselected, corresponding to the each candidate destination; and
sorting all candidate destinations according to the probability value of being selected or the probability of being unselected, and determining the target destination according to the sorting result.

### Claim 5 (depends on 1)

The method according to claim 1, wherein before the acquiring the method further comprises:
using a piece of pre-acquired positive sample data or negative sample data as current sample data; and
inputting the current sample data into the prediction model if the prediction model does not satisfy a preset convergence condition, to train the prediction model with the current sample data; and using next piece of sample data of the current sample data as the current sample data, and repeating the above operation until the prediction model satisfies the convergence condition.

### Claim 6

An electronic device, comprising:
at least one processor; and
a memory, communicated with the at least one processor,
wherein the memory stores an instruction executable by the at least one processor, and the instruction is executed by the at least one processor, to enable the at least one processor to perform an operation for predicting a destination, comprising:
acquiring personalized data of a user and space-time scenario data of the user at a current moment;
predicting, through a pre-trained prediction model, a target destination of the user at the current moment based on the personalized data, the space-time scenario data and an attribute feature of each pre-determined candidate destination; and
recommending the target destination to the user.

### Claim 7 (depends on 6)

The device according to claim 6, wherein the personalized data comprises at least user feature data and behavior feature data, the user feature data comprises at least one of: a gender, an age, an occupation category, an industry to which the user belongs, a company to which the user belongs, an income level, an asset condition, or a consumption level, the behavior feature data comprises at least one of: a retrieval location, a navigation location, or a arrival location, and the attribute feature comprises at least one of: location coordinates of the each candidate destination, a type of a point of interest, or a location tag.

### Claim 8 (depends on 6)

The device according to claim 6, wherein the predicting comprises:
inputting the personalized data, the space-time scenario data and the attribute feature into a pre-trained machine learning model, the machine learning model comprising a linear model, a tree model, and a neural network model; and
outputting the target destination through the machine learning model.

### Claim 9 (depends on 8)

The device according to claim 8, wherein the outputting comprises:
calculating, through the machine learning model, a probability value of being selected or a probability value of being unselected, corresponding to the each candidate destination; and
sorting all candidate destinations according to the probability value of being selected or the probability of being unselected, and determining the target destination according to the sorting result.

### Claim 10 (depends on 6)

The device according to claim 6, wherein before the acquiring the method further comprises:
using a piece of pre-acquired positive sample data or negative sample data as current sample data; and
inputting the current sample data into the prediction model if the prediction model does not satisfy a preset convergence condition, to train the prediction model with the current sample data; and using next piece of sample data of the current sample data as the current sample data, and repeating the above operation until the prediction model satisfies the convergence condition.

### Claim 11

A non-transitory computer readable storage medium, storing a computer instruction, wherein the computer instruction is used to cause a computer to perform an operation for predicting a destination, comprising:
acquiring personalized data of a user and space-time scenario data of the user at a current moment;
predicting, through a pre-trained prediction model, a target destination of the user at the current moment based on the personalized data, the space-time scenario data and an attribute feature of each pre-determined candidate destination; and
recommending the target destination to the user.

### Claim 12 (depends on 11)

The medium according to claim 11, wherein the personalized data comprises at least user feature data and behavior feature data, the user feature data comprises at least one of: a gender, an age, an occupation category, an industry to which the user belongs, a company to which the user belongs, an income level, an asset condition, or a consumption level, the behavior feature data comprises at least one of: a retrieval location, a navigation location, or a arrival location, and the attribute feature comprises at least one of: location coordinates of the each candidate destination, a type of a point of interest, or a location tag.

### Claim 13 (depends on 11)

The medium according to claim 11, wherein the predicting comprises:
inputting the personalized data, the space-time scenario data and the attribute feature into a pre-trained machine learning model, the machine learning model comprising a linear model, a tree model, and a neural network model; and
outputting the target destination through the machine learning model.

### Claim 14 (depends on 13)

The medium according to claim 13, wherein the outputting comprises:
calculating, through the machine learning model, a probability value of being selected or a probability value of being unselected, corresponding to the each candidate destination; and
sorting all candidate destinations according to the probability value of being selected or the probability of being unselected, and determining the target destination according to the sorting result.

### Claim 15 (depends on 11)

The medium according to claim 11, wherein before the acquiring the method further comprises:
using a piece of pre-acquired positive sample data or negative sample data as current sample data; and
inputting the current sample data into the prediction model if the prediction model does not satisfy a preset convergence condition, to train the prediction model with the current sample data; and using next piece of sample data of the current sample data as the current sample data, and repeating the above operation until the prediction model satisfies the convergence condition.