CN112862183A - Prediction method of charging difficulty, training method of model, training device of model and equipment - Google Patents

Prediction method of charging difficulty, training method of model, training device of model and equipment Download PDF

Info

Publication number
CN112862183A
CN112862183A CN202110158871.6A CN202110158871A CN112862183A CN 112862183 A CN112862183 A CN 112862183A CN 202110158871 A CN202110158871 A CN 202110158871A CN 112862183 A CN112862183 A CN 112862183A
Authority
CN
China
Prior art keywords
characteristic information
charging station
target charging
sample
information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110158871.6A
Other languages
Chinese (zh)
Inventor
谭雄飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN202110158871.6A priority Critical patent/CN112862183A/en
Publication of CN112862183A publication Critical patent/CN112862183A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • General Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Primary Health Care (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The disclosure relates to a prediction method of charging difficulty, a training method of a model, a device and equipment, relating to the technical field of computers, in particular to the fields of artificial intelligence, intelligent transportation, deep learning and the like. The specific implementation scheme is as follows: determining relevant characteristic information of a target charging station to be predicted, wherein the relevant characteristic information comprises at least one of environmental characteristic information and characteristic information of the target charging station; preprocessing the relevant characteristic information to obtain a preprocessing result; inputting the preprocessing result into a pre-trained charging difficulty prediction model to obtain a charging difficulty prediction result of the target charging station; the charging difficulty prediction result includes a charging difficulty prediction result of the target charging station. The method has the advantages that the charging difficulty is predicted by using the relevant characteristic information of the target charging station, the generalization capability is strong, and the high prediction precision can be realized. When the method is applied to map application programs, richer map use scenes can be provided for car owners.

Description

Prediction method of charging difficulty, training method of model, training device of model and equipment
Technical Field
The present disclosure relates to the field of computer technology, and more particularly to the fields of artificial intelligence, intelligent transportation, deep learning, and the like.
Background
With the high-speed development of the new energy automobile industry, the number of new energy automobiles is increased sharply. The charging problem of new energy vehicles has gradually become a difficult problem in the industry. Because the service condition of the charging pile in the charging station is dynamically changed all the time, the charging pile service condition known by the vehicle owner before arriving at the charging station and the actual service condition of the vehicle owner after arriving often have great access, which results in charging problems.
Disclosure of Invention
The disclosure provides a prediction method for charging difficulty, a training method, a device, equipment and a storage medium of a model.
According to an aspect of the present disclosure, there is provided a method for predicting difficulty of charging, which may include:
determining relevant characteristic information of a target charging station to be predicted, wherein the relevant characteristic information comprises at least one of environmental characteristic information and characteristic information of the target charging station;
preprocessing the relevant characteristic information to obtain a preprocessing result;
inputting the preprocessing result into a pre-trained charging difficulty prediction model to obtain a charging difficulty prediction result of the target charging station; the charging difficulty prediction result comprises a charging difficulty prediction result of the target charging station in at least one time period after the current moment.
According to another aspect of the present disclosure, a training method of a charging difficulty prediction model is provided, which may include the following steps:
acquiring a relevant characteristic information sample of a target charging station; the related characteristic information sample comprises at least one of a characteristic information sample and an environmental characteristic information sample of the target charging station;
preprocessing the related characteristic information sample to obtain a sample preprocessing result;
inputting the sample preprocessing result into a charging difficulty prediction model to be trained to obtain a charging difficulty prediction result of the target charging station;
and adjusting parameters of the charging difficulty prediction model to be trained according to the charging difficulty prediction result of the target charging station and the charging difficulty real result corresponding to the relevant characteristic information sample until the error between the charging difficulty prediction result and the charging difficulty real result is within an allowable range.
According to a third aspect of the present disclosure, there is provided an apparatus for predicting difficulty of charging, the apparatus may include:
the relevant characteristic information determining module is used for determining relevant characteristic information of a target charging station to be predicted, and the relevant characteristic information comprises at least one of environmental characteristic information and characteristic information of the target charging station;
the preprocessing module is used for preprocessing the relevant characteristic information to obtain a preprocessing result;
the charging difficulty prediction result determining module is used for inputting the preprocessing result into a pre-trained charging difficulty prediction model to obtain a charging difficulty prediction result of the target charging station; the charging difficulty prediction result comprises a charging difficulty prediction result of the target charging station in at least one time period after the current moment.
According to a fourth aspect of the present disclosure, the present application provides a training apparatus for a charging difficulty prediction model, which may include:
the relevant characteristic information sample acquisition module is used for acquiring a relevant characteristic information sample of the target charging station; the related characteristic information sample comprises at least one of an environmental characteristic information sample and a characteristic information sample of the target charging station;
the preprocessing module is used for preprocessing the related characteristic information sample to obtain a sample preprocessing result;
the charging difficulty prediction result acquisition module is used for inputting the sample preprocessing result into a charging difficulty prediction model to be trained to obtain a charging difficulty prediction result of the target charging station;
and the model training module is used for adjusting parameters of the charging difficulty prediction model to be trained according to the charging difficulty prediction result of the target charging station and the charging difficulty real result corresponding to the relevant characteristic information sample until the error between the charging difficulty prediction result and the charging difficulty real result is within an allowable range.
According to another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method according to any one of the embodiments of the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method in any of the embodiments of the present disclosure.
According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method in any of the embodiments of the present disclosure.
According to the technology disclosed by the invention, the prediction of the charging difficulty can be realized by utilizing the relevant characteristic information of the target charging station, and the technology has stronger generalization capability and can realize higher prediction precision. When the method is applied to map application programs, richer map use scenes can be provided for car owners.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a flow chart of a method of predicting difficulty of charging according to the present disclosure;
FIG. 2 is a schematic illustration of determining relevant characteristic information of a target charging station to be predicted in accordance with the present disclosure;
FIG. 3 is a schematic illustration of determining relevant characteristic information of a target charging station to be predicted in accordance with the present disclosure;
FIG. 4 is a schematic diagram of a method of predicting difficulty of charging according to the present disclosure;
FIG. 5 is a flow chart of a training method of a charging difficulty prediction model according to the present disclosure;
FIG. 6 is a schematic diagram of a device for predicting difficulty of charging according to the present disclosure;
FIG. 7 is a schematic diagram of a training apparatus for a charging difficulty prediction model according to the present disclosure;
fig. 8 is a block diagram of an electronic device for implementing a method for predicting charging difficulty and a method for training a charging difficulty prediction model according to an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
As shown in fig. 1, the present application provides a method for predicting charging difficulty, which may include the following steps:
s101: determining relevant characteristic information of a target charging station to be predicted, wherein the relevant characteristic information comprises at least one of environmental characteristic information and characteristic information of the target charging station;
s102: preprocessing the relevant characteristic information to obtain a preprocessing result;
s103: inputting the preprocessing result into a pre-trained charging difficulty prediction model to obtain a charging difficulty prediction result of the target charging station; the charging difficulty prediction result comprises a charging difficulty prediction result of the target charging station in at least one time period after the current moment.
The execution main body of the application can be a vehicle machine of a vehicle, or a server of a charging station, or a server of a map application program, and the like. The following description will be given taking a server of a map application as an example.
The target charging station may be a charging station that the owner desires to go to for charging. For example, after the vehicle owner opens the map application, a target charging station selected from the plurality of candidate charging stations (or a target charging station recommended by the map application among the plurality of candidate charging stations) is selected according to a distance, a route plan, a preference, or the like. And the server of the map application program receives the target charging station selected by the vehicle owner, and the target charging station can be analyzed to obtain the characteristic information of the target charging station.
The characteristic information of the target charging station may be information such as a position of the target charging station, road condition information around the position of the target charging station, a property of a parking lot to which the target charging station belongs, and a use frequency (competitive degree) of a charging pile in the target charging station.
In addition, the server of the map application program can also acquire environmental information of the current time period, such as whether the current time period is a morning and evening peak time period, air temperature and the like.
The characteristic information and/or the environmental information of the target charging station may be used as the related characteristic information of the target charging station.
The relevant characteristic information of the target charging station may be represented in the form of a set of characteristic information.
The relevant characteristic information is preprocessed, and the preprocessing can include data analysis, duplicate removal, normalization and other processing.
The parsing of the data may include mapping the characteristic information expressed in the form of words into word vectors.
Deduplication of data may be directed to cases where there are multiple data in the same dimension. For example, the server of the map application may obtain the relevant feature information of the target charging station from different approaches such as a navigation history, the internet, and the like.
For example, the server of the map application program respectively acquires the position information of the road target charging station through map data and internet data, and the difference between the position information acquired in the two ways is within an allowable range, so that only any one of the position information can be retained.
For another example, the server of the map application may detect the ambient temperature by a temperature detection device provided in the vehicle, or may acquire the ambient temperature of the current area via the internet. Under the condition that the difference of the environmental temperatures acquired in different modes exceeds an allowable range, the accuracy of the environmental temperatures can be identified. For example, the ambient temperature obtained from the internet may be used as the standard. The above specific identification process of the accuracy identification is only an exemplary expression and is not limited herein.
The data normalization may convert the relevant characteristic information of the target charging station, which is expressed in numerical values, into the same data range, for example, into a data range of 0 to 1.
And inputting the preprocessing result into the trained charging difficulty prediction model to obtain a charging difficulty prediction result of the target charging station.
The charging difficulty prediction model can adopt a Long Short-Term Memory artificial neural network (LSTM) model. The network can be trained by using the relevant characteristic information samples of the target charging station and the charging difficulty truth value, so that the charging difficulty prediction model can obtain a charging difficulty prediction result of the target charging station in at least one time period after the current time according to the relevant characteristic information of the target charging station. For example, the charging difficulty prediction model may obtain the charging difficulty prediction results of the target charging station at 1 hour, 2 hours, and 3 hours in the future.
Through the scheme, the charging difficulty can be predicted by using the relevant characteristic information of the target charging station, the method has strong generalization capability, and high prediction precision can be realized. When the method is applied to map application programs, richer map use scenes can be provided for car owners.
As shown in fig. 2, in an embodiment, the determining the relevant characteristic information of the target charging station to be predicted in step S101 may include the following steps:
s201: determining a location of a target charging station;
s202: and determining the traffic information within a preset range around the position and the attribute of the position as the characteristic information of the target charging station.
The position of the target charging station can be determined by means of data duplication removal, data analysis and the like. According to the position of the target charging station, traffic information in a preset range around the position, such as a traffic jam index, travel policy information, time required for reaching the target charging station and the like, can be determined.
The traffic jam index can be acquired through the internet, and the time required for reaching the target charging station can be calculated by utilizing the traffic jam index.
The travel policy information may include restricted number travel, temporary traffic control information, and the like.
The attributes of the location of the target charging station may be a label of the location of the target charging station, such as a mall, a movie theater, an office building, and the like. Different tags can correspond different charging information, for example, the charging station arranged in a shopping mall has a high utilization rate, the charging station arranged in a cinema has a high utilization rate at the weekend and evening time period, and the charging station arranged in an office building has a high utilization rate on a working day.
Through the position of the target charging station, traffic information and tags in the surrounding environment of the target charging station can be determined, so that the possible use condition of the target charging station can be represented, and accurate prediction of charging difficulty can be realized by utilizing the information.
In one embodiment, the attributes of the location include: leisure, office or residential.
The leisure areas may include shopping malls, movie theaters, scenic spots, and the like. The office space may include office buildings, offices, and the like. The residential site may include a residential building, community, etc.
By dividing the attributes of the location into different attributes, the condition of the target charging station can be more accurately characterized.
As shown in fig. 3, in an embodiment, the determining the relevant characteristic information of the target charging station to be predicted in step S101 may include the following steps:
s301: acquiring climate information and time information;
s302: determining the climate information and the time information as the environmental characteristic information.
The climate information may include season information, temperature information, weather information such as wind, cloud, rain and snow.
The time information may include a current time, and in addition, the time information may further include a tag loaded for the current time. For example, the label may be a week or weekend, morning peak or evening peak, work hours (e.g., 8 am to 8 am), or non-work hours, etc.
The usage rate, the competitive strength, and the like of the target charging station corresponding to different pieces of climate information and time information are also different. Therefore, the possible use condition of the target charging station can be represented by the information, and the accurate prediction of the charging difficulty can be realized by the information.
In one embodiment, the determining the relevant characteristic information of the target charging station to be predicted in step S101 may further include the following steps:
and determining at least one of the number of charging piles contained in the target charging station, the utilization rate of the charging piles in the target charging station and the retrieval heat degree of the target charging station as the relevant characteristic information of the target charging station.
For example, the greater the number of charging piles of the target charging station, the lower the charging difficulty of the target charging station may be indicated. Charging pile utilization rate in the target charging station is higher, or the retrieval heat degree of the target charging station is higher, and the charging difficulty of the target charging station can be represented to be relatively higher.
Taking the current time as 13 pm as an example, the charging pile usage rate in the target charging station can be calculated by using the charging pile usage conditions at 13 pm (or so) every day in the past N days. Or the charging pile utilization rate in the target charging station can be calculated by combining the charging pile utilization conditions at 11 o 'clock, 12 o' clock, or between 12 o 'clock and 13 o' clock in the day and at the past time point or time period.
The retrieval heat of the target charging station can be the total navigation times of the target charging station received by the server of the map application program; or the number of navigations of the target charging station received in the last 1 hour.
Therefore, the possible use conditions of the target charging station can be more abundantly represented.
In one embodiment, the preprocessing the related feature information to obtain a preprocessing result includes:
and carrying out normalization processing on the related characteristic information, and taking the result of the normalization processing as a preprocessing result.
Optionally, the normalization process is performed on the related characteristic information expressed in numerical form. For example, the congestion index around the target charging station may be represented by numerical values of 1 to 10. The use frequency of the charging piles in the target charging station may be represented by 0 to 100%, and the congestion index and the use frequency of the charging piles may be normalized to be in the range of 0 to 1.
The normalization process of the time information may also include converting the time by a sine calculation, a cosine calculation, or the like. For example 23 o' clock and 1 am, are very close in time, but differ significantly in value. After the numerical value is subjected to sine calculation or cosine calculation, the normalization of the numerical value can be realized.
By carrying out normalization processing on the related characteristic information, the characteristic information with larger numerical difference can be adjusted to be in the unified data difference dimension. Therefore, the problem of large prediction output and input caused by overlarge numerical value difference is avoided, and the prediction accuracy is improved.
As shown in fig. 4, the present application provides a method for predicting difficulty in charging, where the method may include:
and under the condition that a charging difficulty prediction request of the target charging station is received, acquiring relevant characteristic information of the target charging station.
And inputting the relevant characteristic information of the target charging station into the small-scale prediction model. And obtaining a charging difficulty prediction result of at least one time period (t +1, t +2, t + N) after the current time node (t) by using an hour-level prediction model. Wherein t can correspond to the current time, and N can stare at a positive integer, representing the number of hours.
The small-scale prediction model may adopt the pre-trained charging difficulty prediction model in the previous embodiment.
In addition, in the current embodiment, the relevant feature information of the target charging station may include the total number of charging piles included in the target charging station, the surrounding road conditions of the target charging station, a POI attribute tag of the target charging station, the remaining number of charging piles at T-1 day and T time, the remaining number of charging piles at T-1 time, the remaining number of charging piles at T-2 time, season, weather, and the like.
As shown in fig. 5, the present application provides a training method of a charging difficulty prediction model, which may include the following steps:
s501: acquiring a relevant characteristic information sample of a target charging station; the related characteristic information sample comprises at least one of an environmental characteristic information sample and a characteristic information sample of a target charging station;
s502: preprocessing the related characteristic information sample to obtain a sample preprocessing result;
s503: inputting the sample preprocessing result into a charging difficulty prediction model to be trained to obtain a charging difficulty prediction result of the target charging station;
s504: and adjusting parameters of the charging difficulty prediction model to be trained according to the charging difficulty prediction result of the target charging station and the charging difficulty real result corresponding to the relevant characteristic information sample until the error between the charging difficulty prediction result and the charging difficulty real result is within an allowable range.
The characteristic information sample of the target charging station may include a location of the target charging station, historical data of traffic information around the target charging station, attributes of a parking lot to which the target charging station belongs, historical data of a usage frequency (competitive degree) of the target charging station, and the like.
The environmental characteristic information sample may include climate history data or the like.
The environmental characteristic information sample and the characteristic information sample of the target charging station may be divided into time intervals, for example, 24 time intervals may be divided into 24 time intervals in 24 hours a day. Alternatively, the time interval may be divided into 48 time intervals by 0.5 hour. The historical data may be selected from data of past 6 months and 12 months, and is not particularly limited.
And for each time interval, respectively counting the charging difficulty historical data of the target charging station in at least one future time interval. For example, for the time interval of 17 pm to 18 pm, the charging difficulty history data corresponding to the time intervals of 18 pm to 19 pm, 19 pm to 20 pm, and 20 pm to 21 pm may be used as the charging difficulty actual result. That is, the charging difficulty true result corresponds to the relevant characteristic information sample.
The charging difficulty can be divided into three categories of easy, general and difficult. The above-mentioned degrees may correspond to the target charging station being idle, the target charging station needing to wait for a short time (normal), the target charging station needing to wait for a long time (tension), etc., respectively. In addition, the charging difficulty can be classified into finer-grained categories, and the detailed description is omitted here.
And inputting the relevant characteristic information sample of the target charging station into the charging difficulty prediction model to be trained, so as to obtain the charging difficulty prediction result of the target charging station. An error exists when the charging difficulty prediction result is compared with the charging difficulty real result. The error is propagated backwards in each layer of the charging difficulty prediction model to be trained, and the parameters of each layer are adjusted according to the error until the output of the charging difficulty prediction model to be trained converges or a desired effect is achieved.
80% of samples of the relevant characteristic information of the target charging station can be used for making a training set to train the charging difficulty prediction model, and 20% of samples can be used for making a testing set to check the generalization capability of the charging difficulty prediction model.
In one embodiment, obtaining a sample of relevant characteristic information of a target charging station includes:
acquiring the position of a target charging station;
and determining the historical data of the traffic information within a preset range around the position and the attributes of the position as relevant characteristic information samples of the target charging station.
According to the position of the target charging station, historical traffic information data in a preset range around the position, such as historical data of traffic jam indexes and historical data of travel policy information, can be determined.
The history data of the travel policy information may include limited number travel, temporary traffic control information, and the like.
The attributes of the location of the target charging station may be a label of the location of the target charging station, such as a mall, a movie theater, an office building, and the like.
In one embodiment, obtaining a sample of relevant characteristic information of a target charging station includes:
acquiring historical climate information data and historical time information data;
and determining the climate information historical data and the time information historical data as environmental characteristic information samples.
The weather information historical data can comprise season information historical data, temperature information historical data, weather information historical data such as wind, cloud, rain and snow and the like.
The time information history data may include time tags such as the week or weekend, morning or evening peak, work or non-work hours, etc.
In one embodiment, obtaining a sample of relevant characteristic information of a target charging station may further include:
and determining at least one of the number of charging piles contained in the target charging station, the charging pile utilization rate historical data in the target charging station and the retrieval heat degree historical data of the target charging station as a characteristic information sample of the target charging station.
Taking the current time as 13 pm as an example, the usage rate of the charging piles in the target charging station can be calculated by using the usage conditions of the charging piles at 13 pm every day in the past N days. Or the charging pile utilization rate in the target charging station can be obtained by calculating the average use condition of the charging piles in N days.
The retrieval heat history data of the target charging station is the total navigation times of the target charging station received by the server of the map application program.
In one embodiment, a sample of the relevant characteristic information is preprocessed to obtain a sample preprocessing result; the method comprises the following steps:
and carrying out normalization processing on the relevant characteristic information sample, and taking the result of the normalization processing as a sample preprocessing result.
Optionally, the normalization process is performed on the related characteristic information sample expressed in numerical form. For example, the congestion index sample of the periphery of the target charging station may be represented by values of 1 to 10. The usage frequency sample of the charging pile in the target charging station may be represented by 0 to 100%, and the congestion index sample and the usage frequency sample of the charging pile in the target charging station may be normalized to be in a range of 0 to 1.
The normalization process of the time interval may include converting the time interval by a method such as sine calculation or cosine calculation.
As shown in fig. 6, the present application provides a device for predicting difficulty of charging, which may include:
a relevant characteristic information determining module 601, configured to determine relevant characteristic information of a target charging station to be predicted, where the relevant characteristic information includes at least one of environmental characteristic information and characteristic information of the target charging station;
a preprocessing module 602, configured to preprocess the relevant feature information to obtain a preprocessing result;
a charging difficulty prediction result determining module 603, configured to input the preprocessing result into a pre-trained charging difficulty prediction model to obtain a charging difficulty prediction result of the target charging station; the charging difficulty prediction result comprises a charging difficulty prediction result of the target charging station in at least one time period after the current moment.
In one embodiment, the related feature information determining module 601 may further include:
a position determination submodule for determining a position of a target charging station;
and the related characteristic information determination execution sub-module is used for determining the traffic information in the preset range around the position and the attribute of the position as the characteristic information of the target charging station.
In one embodiment, the attributes of the location include: leisure, office or residential.
In one embodiment, the related feature information determining module 601 may further include:
the climate information and time information acquisition submodule is used for acquiring climate information and time information;
and the related characteristic information determination execution sub-module is used for determining the climate information and the time information as the environmental characteristic information.
In one embodiment, the related feature information determining module 601 may further be configured to: and determining at least one of the number of charging piles contained in the target charging station, the utilization rate of the charging piles in the target charging station and the retrieval heat degree of the target charging station as the relevant characteristic information of the target charging station.
In one embodiment, the preprocessing module 602 is specifically configured to: and carrying out normalization processing on the related characteristic information, and taking the result of the normalization processing as a preprocessing result.
As shown in fig. 7, the present application provides a training apparatus for a charging difficulty prediction model, which may include:
a relevant feature information sample obtaining module 701, configured to obtain a relevant feature information sample of the target charging station; the related characteristic information sample comprises at least one of an environmental characteristic information sample and a characteristic information sample of the target charging station;
a preprocessing module 702, configured to preprocess the relevant feature information sample to obtain a sample preprocessing result;
a charging difficulty prediction result obtaining module 703, configured to input the sample preprocessing result into a charging difficulty prediction model to be trained, so as to obtain a charging difficulty prediction result of the target charging station;
and the model training module 704 is configured to adjust parameters of the charging difficulty prediction model to be trained according to the charging difficulty prediction result of the target charging station and the charging difficulty real result corresponding to the relevant characteristic information sample until an error between the charging difficulty prediction result and the charging difficulty real result is within an allowable range.
In one embodiment, the related feature information sample obtaining module 701 may further include:
the position acquisition submodule is used for acquiring the position of the target charging station;
and the related characteristic information sample acquisition execution submodule is used for determining the traffic information historical data in a preset range around the position and the attribute of the position as the related characteristic information sample of the target charging station.
In one embodiment, the related feature information sample obtaining module 701 may further include:
the climate information historical data and time information historical data acquisition submodule is used for acquiring climate information historical data and time information historical data;
and the related characteristic information sample acquisition execution submodule is used for determining the climate information historical data and the time information historical data as the environmental characteristic information sample.
In an embodiment, the related feature information sample obtaining module 701 is specifically configured to: and determining at least one of the number of charging piles contained in the target charging station, historical data of the usage rate of the charging piles in the target charging station and historical data of the retrieval heat degree of the target charging station as a characteristic information sample of the target charging station.
In one embodiment, the preprocessing module 702 is specifically configured to: and carrying out normalization processing on the relevant characteristic information sample, and taking the normalization processing result as a sample preprocessing result.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 8 illustrates a schematic block diagram of an electronic device 800 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 8, electronic device 800 includes a computing unit 810 that may perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM)820 or a computer program loaded from a storage unit 880 into a Random Access Memory (RAM) 830. In the RAM 830, various programs and data required for the operation of the device 800 can also be stored. The computing unit 810, the ROM 820 and the RAM 830 are connected to each other by a bus 840. An input/output (I/O) interface 850 is also connected to bus 840.
A number of components in the electronic device 800 are connected to the I/O interface 850, including: an input unit 860 such as a keyboard, a mouse, and the like; an output unit 870 such as various types of displays, speakers, and the like; a storage unit 880 such as a magnetic disk, optical disk, or the like; and a communication unit 890 such as a network card, modem, wireless communication transceiver, or the like. The communication unit 890 allows the electronic device 800 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
Computing unit 810 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 810 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 810 performs various methods and processes described above, such as a prediction method of the charging difficulty, a training method of a charging difficulty prediction model. For example, in some embodiments, the method of predicting the difficulty of charging, the method of training the model of predicting the difficulty of charging, may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 880. In some embodiments, some or all of the computer program may be loaded onto and/or installed onto electronic device 800 via ROM 820 and/or communications unit 890. When the computer program is loaded into the RAM 830 and executed by the computing unit 810, one or more steps of the prediction method of the charging difficulty, the training method of the charging difficulty prediction model described above may be performed. Alternatively, in other embodiments, the computing unit 810 may be configured to perform the prediction method of the charging difficulty, the training method of the charging difficulty prediction model, by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims (25)

1. A method for predicting difficulty of charging includes:
determining relevant characteristic information of a target charging station to be predicted, wherein the relevant characteristic information comprises at least one of environmental characteristic information and characteristic information of the target charging station;
preprocessing the relevant characteristic information to obtain a preprocessing result;
inputting the preprocessing result into a pre-trained charging difficulty prediction model to obtain a charging difficulty prediction result of the target charging station; the charging difficulty prediction result comprises a charging difficulty prediction result of the target charging station at least one time period after the current time.
2. The method of claim 1, wherein the determining relevant characteristic information of the target charging station to be predicted comprises:
determining a location of the target charging station;
determining traffic information within a predetermined range around the location and an attribute of the location as characteristic information of the target charging station.
3. The method of claim 2, wherein the attributes of the location comprise: leisure, office or residential.
4. The method of claim 1, wherein the determining relevant characteristic information of the target charging station to be predicted comprises:
acquiring climate information and time information;
and determining the climate information and the time information as the environmental characteristic information.
5. The method of any one of claims 1 to 4, wherein the determining the relevant characteristic information of the target charging station to be predicted further comprises:
and determining at least one of the number of charging piles contained in the target charging station, the charging pile utilization rate in the target charging station and the retrieval heat degree of the target charging station as the characteristic information of the target charging station.
6. The method according to any one of claims 1 to 4, wherein the preprocessing the related feature information to obtain a preprocessing result comprises:
and carrying out normalization processing on the related characteristic information, and taking the result of the normalization processing as the preprocessing result.
7. A training method of a charging difficulty prediction model comprises the following steps:
acquiring a relevant characteristic information sample of a target charging station; the relevant characteristic information sample comprises at least one of an environmental characteristic information sample and a characteristic information sample of the target charging station;
preprocessing the related characteristic information sample to obtain a sample preprocessing result;
inputting the sample preprocessing result into a charging difficulty prediction model to be trained to obtain a charging difficulty prediction result of the target charging station;
and adjusting parameters of the charging difficulty prediction model to be trained according to the charging difficulty prediction result of the target charging station and the charging difficulty real result corresponding to the relevant characteristic information sample until the error between the charging difficulty prediction result and the charging difficulty real result is within an allowable range.
8. The method of claim 7, wherein the obtaining a sample of relevant characteristic information of a target charging station comprises:
acquiring the position of the target charging station;
determining traffic information historical data within a predetermined range around the location and attributes of the location as relevant characteristic information samples of the target charging station.
9. The method of claim 7, wherein the obtaining a sample of relevant characteristic information of a target charging station comprises:
acquiring historical climate information data and historical time information data;
and determining the historical climate information data and the historical time information data as the environmental characteristic information sample.
10. The method of any one of claims 7 to 9, wherein the obtaining of the relevant characteristic information sample of the target charging station further comprises:
determining at least one of the number of charging piles contained in the target charging station, historical data of the usage rate of the charging piles in the target charging station and historical data of the retrieval heat degree of the target charging station as a relevant characteristic information sample of the target charging station.
11. The method according to any one of claims 7 to 9, wherein the relevant characteristic information sample is preprocessed to obtain a sample preprocessing result; the method comprises the following steps:
and carrying out normalization processing on the related characteristic information, and taking the result of the normalization processing as the preprocessing result.
12. An apparatus for predicting difficulty of charging, comprising:
the relevant characteristic information determining module is used for determining relevant characteristic information of a target charging station to be predicted, wherein the relevant characteristic information comprises at least one of environmental characteristic information and characteristic information of the target charging station;
the preprocessing module is used for preprocessing the related characteristic information to obtain a preprocessing result;
the charging difficulty prediction result determining module is used for inputting the preprocessing result into a pre-trained charging difficulty prediction model to obtain a charging difficulty prediction result of the target charging station; the charging difficulty prediction result comprises a charging difficulty prediction result of the target charging station at least one time period after the current time.
13. The apparatus of claim 12, wherein the relevant feature information determination module comprises:
a location determination submodule for determining a location of the target charging station;
and the related characteristic information determination execution sub-module is used for determining the traffic information in the preset range around the position and the attribute of the position as the characteristic information of the target charging station.
14. The apparatus of claim 13, wherein the attributes of the location comprise: leisure, office or residential.
15. The apparatus of claim 12, wherein the relevant feature information determination module comprises:
the climate information and time information acquisition submodule is used for acquiring climate information and time information;
and the related characteristic information determination execution sub-module is used for determining the climate information and the time information as the environmental characteristic information.
16. The apparatus of any of claims 12 to 15, wherein the relevant feature information determination module is further configured to: and determining at least one of the number of charging piles contained in the target charging station, the charging pile utilization rate in the target charging station and the retrieval heat degree of the target charging station as the characteristic information of the target charging station.
17. The apparatus according to any one of claims 12 to 15, wherein the preprocessing module is specifically configured to: and carrying out normalization processing on the related characteristic information, and taking the result of the normalization processing as the preprocessing result.
18. A training apparatus for a charging difficulty prediction model, comprising:
the relevant characteristic information sample acquisition module is used for acquiring a relevant characteristic information sample of the target charging station; the relevant characteristic information sample comprises at least one of an environmental characteristic information sample and a characteristic information sample of the target charging station;
the preprocessing module is used for preprocessing the related characteristic information sample to obtain a sample preprocessing result;
the charging difficulty prediction result acquisition module is used for inputting the sample preprocessing result into a charging difficulty prediction model to be trained to obtain a charging difficulty prediction result of the target charging station;
and the model training module is used for adjusting the parameters of the charging difficulty prediction model to be trained according to the charging difficulty prediction result of the target charging station and the charging difficulty real result corresponding to the relevant characteristic information sample until the error between the charging difficulty prediction result and the charging difficulty real result is within an allowable range.
19. The apparatus of claim 18, wherein the related feature information sample obtaining module comprises:
the position acquisition submodule is used for acquiring the position of the target charging station;
and the related characteristic information sample acquisition execution submodule is used for determining the traffic information historical data in a preset range around the position and the attribute of the position as the related characteristic information sample of the target charging station.
20. The apparatus of claim 18, wherein the related feature information sample obtaining module comprises:
the climate information historical data and time information historical data acquisition submodule is used for acquiring climate information historical data and time information historical data;
and the related characteristic information sample acquisition execution submodule is used for determining the climate information historical data and the time information historical data as the environmental characteristic information sample.
21. The apparatus according to claims 18 to 20, wherein the relevant feature information sample obtaining module is specifically configured to: determining at least one of the number of charging piles contained in the target charging station, historical data of the usage rate of the charging piles in the target charging station and historical data of the retrieval heat degree of the target charging station as a relevant characteristic information sample of the target charging station.
22. The apparatus according to any one of claims 18 to 20, wherein the preprocessing module is specifically configured to: and carrying out normalization processing on the related characteristic information sample, and taking the result of the normalization processing as the sample preprocessing result.
23. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 11.
24. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 11.
25. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 11.
CN202110158871.6A 2021-02-04 2021-02-04 Prediction method of charging difficulty, training method of model, training device of model and equipment Pending CN112862183A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110158871.6A CN112862183A (en) 2021-02-04 2021-02-04 Prediction method of charging difficulty, training method of model, training device of model and equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110158871.6A CN112862183A (en) 2021-02-04 2021-02-04 Prediction method of charging difficulty, training method of model, training device of model and equipment

Publications (1)

Publication Number Publication Date
CN112862183A true CN112862183A (en) 2021-05-28

Family

ID=75988967

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110158871.6A Pending CN112862183A (en) 2021-02-04 2021-02-04 Prediction method of charging difficulty, training method of model, training device of model and equipment

Country Status (1)

Country Link
CN (1) CN112862183A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113344277A (en) * 2021-06-17 2021-09-03 北京百度网讯科技有限公司 Prediction model training method, state updating method, device, equipment and medium
CN113379139A (en) * 2021-06-22 2021-09-10 阳光电源股份有限公司 Charging station management method and application device thereof

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3480692A1 (en) * 2017-11-06 2019-05-08 Guangdong OPPO Mobile Telecommunications Corp., Ltd. Methods and systems for preloading applications and generating prediction models
CN111757272A (en) * 2020-06-29 2020-10-09 北京百度网讯科技有限公司 Subway congestion degree prediction method, model training method and device
CN112036598A (en) * 2020-06-24 2020-12-04 国网天津市电力公司电力科学研究院 Charging pile use information prediction method based on multi-information coupling

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3480692A1 (en) * 2017-11-06 2019-05-08 Guangdong OPPO Mobile Telecommunications Corp., Ltd. Methods and systems for preloading applications and generating prediction models
CN112036598A (en) * 2020-06-24 2020-12-04 国网天津市电力公司电力科学研究院 Charging pile use information prediction method based on multi-information coupling
CN111757272A (en) * 2020-06-29 2020-10-09 北京百度网讯科技有限公司 Subway congestion degree prediction method, model training method and device

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113344277A (en) * 2021-06-17 2021-09-03 北京百度网讯科技有限公司 Prediction model training method, state updating method, device, equipment and medium
CN113344277B (en) * 2021-06-17 2024-03-12 北京百度网讯科技有限公司 Predictive model training method, state updating method, device, equipment and medium
CN113379139A (en) * 2021-06-22 2021-09-10 阳光电源股份有限公司 Charging station management method and application device thereof

Similar Documents

Publication Publication Date Title
CN110260870B (en) Map matching method, device, equipment and medium based on hidden Markov model
CN105589939B (en) Method and device for identifying group motion trail
CN111582559B (en) Arrival time estimation method and device
CN112862183A (en) Prediction method of charging difficulty, training method of model, training device of model and equipment
CN114626169B (en) Traffic network optimization method, device, equipment, readable storage medium and product
CN112763995A (en) Radar calibration method and device, electronic equipment and road side equipment
CN106855878B (en) Historical driving track display method and device based on electronic map
CN112884837A (en) Road positioning method, device, equipment and storage medium
CN114036253A (en) High-precision map data processing method and device, electronic equipment and medium
CN115585816A (en) Lane-level map matching method and device
CN113837268A (en) Method, device, equipment and medium for determining track point state
CN113344277B (en) Predictive model training method, state updating method, device, equipment and medium
US20240169462A1 (en) Online ride-hailing information processing method, device and computer storage medium
CN113284337B (en) OD matrix calculation method and device based on vehicle track multidimensional data
CN114543829A (en) Model training method, navigation track recommendation method and device and vehicle
CN113899381A (en) Method, apparatus, device, medium and product for generating route information
CN117056446A (en) Track data query method and device, electronic equipment and medium
CN115046564B (en) Navigation processing method, device, equipment and storage medium
CN115206102A (en) Method, apparatus, electronic device, and medium for determining traffic path
CN113850297B (en) Road data monitoring method and device, electronic equipment and storage medium
CN116030616A (en) Method and device for predicting traffic volume by using big data
CN113257030A (en) Parking lot attribute prediction model training method, parking lot recommendation method and device
CN112735130A (en) Traffic data processing method and device, electronic equipment and medium
Fanani et al. Bus Arrival Prediction-to Ensure Users not to Miss the Bus
CN113868532B (en) Location recommendation method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination