CN-121989717-A - Charging method, device, equipment, vehicle and storage medium

CN121989717ACN 121989717 ACN121989717 ACN 121989717ACN-121989717-A

Abstract

The embodiment of the application provides a charging method, device, equipment, a vehicle and a storage medium, wherein habit data of a user, actual state data of the vehicle, current environment data of an environment where the vehicle is located and real-time information of a power grid are obtained, charging intention probability of the user is determined according to the habit data, the actual state data, the current environment data and the real-time information, the actual intention of the user is determined according to the charging intention probability, and the vehicle is charged in response to the actual intention as the charging intention. According to the application, the multidimensional data composed of habit data, actual state data, current environment data and real-time information are fused, so that the probability of the charging intention is accurately calculated, the charging intention is accurately identified, the accuracy and the foresight of the identification of the charging intention are effectively improved, the misjudgment of the intention caused by single data dimension is avoided, the adaptability to the dynamic change of a scene is enhanced, the intelligence of the identification of the intention of a user is effectively ensured, the viscosity of the user is improved, and the method is more economical and reliable.

Inventors

LIAO JIAHUA
WU XIAOJUN
DENG YUNFEI
LIU XUEWU

Assignees

广州汽车集团股份有限公司

Dates

Publication Date: 20260508
Application Date: 20260402

Claims (10)

1. A vehicle charging method, characterized by comprising the steps of: Acquiring habit data of a user, actual state data of a vehicle, current environment data of an environment where the user is positioned and real-time information of a power grid; determining charging intention probability of the user according to the habit data, the actual state data, the current environment data and the real-time information; And determining the actual intention of the user according to the charging intention probability, and charging the vehicle in response to the actual intention as the charging intention.
2. The method of claim 1, wherein the determining the probability of the user's intent to charge based on the habit data, the actual state data, the current environment data, and the real-time information comprises: Inputting the habit data, the actual state data, the current environment data and the real-time information into a pre-constructed intention calculation model, and extracting at least one feature vector; and calculating the charging intention probability according to the at least one feature vector and the corresponding weight.
3. The method of claim 1, wherein the determining the actual intent of the user based on the charging intent probability comprises: identifying a region in which the charging intention probability is located; If the interval is a first confidence interval, judging that the actual intention is the charging intention; If the interval is a second confidence interval, generating a target interaction action, and executing the target interaction action to respond to the charging instruction of the user and determine that the actual intention is the charging intention; And if the interval is a third confidence interval, judging that the actual intention is the silence monitoring intention.
4. A method according to claim 3, wherein the generating a target interaction comprises: Matching the interaction type according to the charging intention probability; And determining the target interaction action according to the interaction type.
5. The method of claim 1, wherein said charging the vehicle comprises: Determining an optimization objective for the vehicle; Generating a charging action of the vehicle according to the optimization target and at least one of the habit data, the actual state data, the current environment data and the real-time information; And charging the vehicle according to the charging power.
6. The method of claim 5, wherein the charging action comprises at least one of a charging location, a charging period, a charging start time, a charging end time, a charge level, a battery warm-up time, and a charging power.
7. A vehicle charging device, characterized by comprising: The acquisition module is used for acquiring habit data of a user, actual state data of a vehicle, current environment data of an environment where the user is positioned and real-time information of a power grid; the determining module is used for determining the charging intention probability of the user according to the habit data, the actual state data, the current environment data and the real-time information; and the charging module is used for determining the actual intention of the user according to the charging intention probability and charging the vehicle in response to the actual intention as the charging intention.
8. An electronic device comprising a processor and a memory, wherein, A memory for storing a computer program; A processor for executing a program stored on a memory to implement the vehicle charging method according to any one of claims 1 to 6.
9. A vehicle comprising the electronic device of claim 8.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed by a processor, implements the vehicle charging method of any one of claims 1-6.

Description

Charging method, device, equipment, vehicle and storage medium Technical Field The embodiment of the application relates to the technical field of vehicle charging, in particular to a charging method, a device, equipment, a vehicle and a storage medium. Background In the related art, the anxiety state of the user can be analyzed by collecting various biological characteristics such as facial images, physiological signals and sight line data of the user, so as to further predict the charging intention of the user, and the charging intention of the user can be judged based on the temperature of the vehicle battery, the current driving data (such as a navigation terminal point) and historical charging data, and whether the battery is preheated or not can be determined according to the charging intention of the user. However, in the related art, the judgment is performed depending on the biological characteristics of the user or depending on the historical charging data, so that the real intention of the user cannot be accurately identified due to single data dimension, and the charging is not intelligent enough due to single dimension, so that the economical efficiency is poor, and the problem is to be solved. Disclosure of Invention The embodiment of the application provides a charging method, a device, equipment, a vehicle and a storage medium, which aim to solve the problems that the related technology relies on the biological characteristics of a user or relies on historical charging data to judge, the dimension of the data is single, so that the charging intention of the user is effectively identified and met, and in addition, the charging intention of the user is not combined with dynamic information such as the integral load of a power grid, the time-of-use electricity price and the like, so that the energy utilization efficiency is low and the economical efficiency is poor in the charging process. An embodiment of a first aspect of the application provides a vehicle charging method, which comprises the steps of obtaining habit data of a user, actual state data of a vehicle, current environment data of an environment where the vehicle is located and real-time information of a power grid, determining charging intention probability of the user according to the habit data, the actual state data, the current environment data and the real-time information, determining actual intention of the user according to the charging intention probability, and charging the vehicle in response to the actual intention as the charging intention. According to the technical means, the embodiment of the application combines habit data, actual state data, current environment data and real-time information to form multidimensional data for comprehensive research and judgment, thereby effectively improving accuracy and foresight of charge intention recognition, avoiding intention misjudgment caused by single data dimension, further effectively enhancing adaptability to scene dynamic change in the driving process by accurately calculating charge intention probability based on multidimensional data and accurately judging user actual intention, effectively ensuring intelligence of user intention recognition and improving user viscosity, and forming a closed loop for recognition, optimization and execution by responding to charge intention and charging vehicles, thus being more economical and reliable. Optionally, in one embodiment of the present application, the determining the charging intention probability of the user according to the habit data, the actual state data, the current environment data and the real-time information includes inputting the habit data, the actual state data, the current environment data and the real-time information into a pre-constructed intention calculation model, extracting at least one feature vector, and calculating the charging intention probability according to the at least one feature vector and the corresponding weight. According to the technical means, habit data, actual state data, current environment data and real-time information are input into the pre-constructed intention calculation model, multi-source heterogeneous data are effectively integrated, time attenuation can be corrected, endurance safety redundancy is guaranteed, road conditions and weather energy consumption are introduced, and electricity price sensitivity of a user is quantized. Optionally, in one embodiment of the present application, the determining the actual intention of the user according to the charging intention probability includes identifying a location interval of the charging intention probability, determining that the actual intention is the charging intention when the location interval is a first confidence interval, generating a target interaction when the location interval is a second confidence interval, and executing the target interaction to determine that the actual intention is the charging intention in