CN112861002A - Charging station detection method and device, electronic equipment and storage medium - Google Patents
Charging station detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112861002A CN112861002A CN202110191758.8A CN202110191758A CN112861002A CN 112861002 A CN112861002 A CN 112861002A CN 202110191758 A CN202110191758 A CN 202110191758A CN 112861002 A CN112861002 A CN 112861002A
- Authority
- CN
- China
- Prior art keywords
- comment
- charging station
- information
- data
- classification
- 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
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 55
- 230000002159 abnormal effect Effects 0.000 claims abstract description 71
- 238000013145 classification model Methods 0.000 claims abstract description 55
- 238000012549 training Methods 0.000 claims description 67
- 238000000034 method Methods 0.000 claims description 20
- 230000015654 memory Effects 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 9
- 238000012552 review Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 3
- 230000003993 interaction Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000005856 abnormality Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013178 mathematical model Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 208000019901 Anxiety disease Diseases 0.000 description 2
- 241000219198 Brassica Species 0.000 description 2
- 235000003351 Brassica cretica Nutrition 0.000 description 2
- 235000003343 Brassica rupestris Nutrition 0.000 description 2
- 230000036506 anxiety Effects 0.000 description 2
- QKSKPIVNLNLAAV-UHFFFAOYSA-N bis(2-chloroethyl) sulfide Chemical compound ClCCSCCCl QKSKPIVNLNLAAV-UHFFFAOYSA-N 0.000 description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003340 mental effect Effects 0.000 description 2
- 235000010460 mustard Nutrition 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a charging station detection method, a charging station detection device, electronic equipment and a storage medium, and relates to the technical field of data processing, wherein the charging station detection method comprises the following steps: obtaining target comment data of a charging station, wherein the target comment data comprises: comment information and location information; extracting features of the comment information to obtain key information; classifying and detecting the key information by using a preset classification model to obtain a comment type corresponding to the key information; analyzing an abnormal charging station according to the comment type and the position information; and generating abnormal prompt information according to the abnormal charging station. According to the charging station detection method, the satisfaction degree of a user to the charging station can be simply, conveniently and quickly detected on the premise of ensuring the accuracy, and the condition of the charging station can be timely fed back.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a charging station detection method and apparatus, an electronic device, and a storage medium.
Background
The charging stations comprise an electric vehicle charging station, a mobile phone charging station, an electric vehicle charging station and the like, and are high-efficiency equipment for charging a storage battery and a mobile phone. The electric vehicle is a green travel vehicle which is most popular, energy-saving and environment-friendly at present, and the electric vehicle charging station is a station for charging the electric vehicle. The electric automobile charging station can better solve the problem of quick charging of the electric automobile, saves energy and reduces emission, and along with the popularization of the electric automobile, the electric automobile charging station is bound to become the key point of the development of the automobile industry and the energy industry.
At present, in order to meet the charging configuration of electric vehicles, enterprises invest in huge amount on the infrastructure of a charging station, but cannot know whether the service provided by the basic setting of the charging station can meet the public demand or not in time. The conventional charging station performance evaluation research only depends on manual analysis, so that the cost is high, self-reporting investigation is rarely carried out, the analysis result is inaccurate, and the management of the charging station infrastructure is influenced.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the embodiment of the invention provides a charging station detection method, which can simply, conveniently and quickly detect the satisfaction degree of a user on a charging station and feed back the condition of the charging station in time on the premise of ensuring the accuracy.
The embodiment of the invention also provides a charging station detection device.
The embodiment of the invention also provides the electronic equipment.
The embodiment of the invention also provides a computer readable storage medium.
According to a charging station detection method of an embodiment of a first aspect of the present invention, the method includes:
obtaining target comment data of a charging station, wherein the target comment data comprises: comment information and location information;
extracting features of the comment information to obtain key information;
classifying and detecting the key information by using a preset classification model to obtain a comment type corresponding to the key information;
analyzing an abnormal charging station according to the comment type and the position information;
and generating abnormal prompt information according to the abnormal charging station.
According to the charging station detection method of the embodiment of the first aspect of the invention, at least the following beneficial effects are achieved: by acquiring target comment data of the charging station, the target comment data includes: comment information and positional information, then carry out feature extraction to comment information, obtain key information, reuse preset classification model to carry out classification detection to key information, obtain the comment type that key information corresponds, at last according to comment type and positional information analysis out unusual charging station, and according to unusual charging station generate unusual prompt information, can be under the prerequisite of guaranteeing the accuracy, detect out the satisfaction degree of user to the charging station simple and fast, the condition of in time feedback charging station.
According to some embodiments of the invention, after the obtaining the target comment data of the charging station, the method further comprises: if the target comment data are preset standard comment data, determining a comment type corresponding to the preset standard comment data; and skipping to the step of analyzing the abnormal charging station according to the comment type and the position information.
According to some embodiments of the invention, the method further comprises: and if the target comment data are target text comment data, skipping to the step of extracting the characteristics of the comment information to obtain key information.
According to some embodiments of the present invention, the classifying and detecting the key information by using a classification model and outputting a comment type corresponding to the key information includes: acquiring target classification data output by the classification model; acquiring a classification label corresponding to the target classification data; and determining the comment type corresponding to the key information according to the classification label.
According to some embodiments of the invention, the method further comprises: obtaining the classification model specifically includes: obtaining historical comment data, and extracting comment data to be trained from the historical comment data; constructing an initial training model according to the comment data to be trained; extracting features of the comment data to be trained to obtain training key features; and training the initial training model according to the training key characteristics to obtain the classification model.
According to some embodiments of the invention, the training the initial training model according to the training key features to obtain the classification model comprises: acquiring a preset iteration number; updating the initial training model according to the preset iteration times and the training key features; and selecting the classification model from the plurality of updated initial training models.
According to some embodiments of the invention, the method further comprises: extracting comment data to be tested from the historical comment data; training the comment data to be tested according to the classification model, and outputting preset classification data; and determining the comment type corresponding to the comment data to be tested according to the preset label corresponding to the preset classification data.
According to a second aspect embodiment of the present invention, a charging station detection apparatus includes:
the acquisition module is used for acquiring target comment data of the charging station, wherein the target comment data comprise: comment information and location information;
the extraction module is used for extracting the characteristics of the comment information to obtain key information;
the classification module is used for carrying out classification detection on the key information by using a preset classification model to obtain a comment type corresponding to the key information;
the analysis module is used for analyzing an abnormal charging station according to the comment type and the position information;
and the prompt module is used for generating abnormal prompt information according to the abnormal charging station.
According to the charging station detection device of the embodiment of the second aspect of the invention, at least the following beneficial effects are achieved: by executing the charging station detection method of the embodiment of the first aspect of the invention, the satisfaction degree of a user on the charging station can be simply, conveniently and quickly detected on the premise of ensuring the accuracy, and the condition of the charging station can be timely fed back.
An electronic device according to an embodiment of the third aspect of the invention includes: at least one processor, and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions that are executable by the at least one processor to cause the at least one processor to implement the charging station detection method of the first aspect when executing the instructions.
According to the electronic device of the embodiment of the third aspect of the invention, at least the following beneficial effects are achieved: by executing the charging station detection method of the embodiment of the first aspect of the invention, the satisfaction degree of a user on the charging station can be simply, conveniently and quickly detected on the premise of ensuring the accuracy, and the condition of the charging station can be timely fed back.
According to a fourth aspect of the present invention, there is provided a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the charging station detection method of the first aspect.
The computer-readable storage medium according to the fourth aspect of the present invention has at least the following advantages: by executing the charging station detection method of the embodiment of the first aspect of the invention, the satisfaction degree of a user on the charging station can be simply, conveniently and quickly detected on the premise of ensuring the accuracy, and the condition of the charging station can be timely fed back.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flow chart of a charging station detection method according to an embodiment of the invention;
FIG. 2 is a schematic structural diagram of a charging station detection apparatus according to an embodiment of the present invention;
fig. 3 is a functional block diagram of an electronic device according to an embodiment of the invention.
Reference numerals:
the device comprises an acquisition module 200, an extraction module 210, a classification module 220, an analysis module 230, a prompt module 240, a processor 300, a memory 310, a data transmission module 320, a camera 330 and a display screen 340.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
1. APP: application, namely mobile phone software, mainly refers to software installed on a smart phone, and overcomes the defects and individuation of an original system.
2. KNN algorithm: the neighbor algorithm, or K-nearest neighbor (KNN) classification algorithm, is one of the simplest methods in data mining classification techniques. By K nearest neighbors is meant the K nearest neighbors, meaning that each sample can be represented by its nearest K neighbors. The neighbor algorithm is a method for classifying each record in the data set. And the mathematical model adopting the KNN algorithm is the KNN model.
At present, in order to meet the charging configuration of electric vehicles, enterprises invest in huge amount on the infrastructure of a charging station, but cannot know whether the service provided by the basic setting of the charging station can meet the public demand or not in time. The conventional charging station performance evaluation research only depends on manual analysis, so that the cost is high, self-reporting investigation is rarely carried out, the analysis result is inaccurate, and the management of the charging station infrastructure is influenced.
Based on this, the embodiment of the invention provides a charging station detection method, a charging station detection device, an electronic device and a storage medium, which can simply, conveniently and quickly detect the satisfaction degree of a user on a charging station and timely feed back the condition of the charging station on the premise of ensuring the accuracy.
Referring to fig. 1, a charging station detection method according to an embodiment of a first aspect of the present invention includes:
step S100, obtaining target comment data of the charging station, wherein the target comment data comprises: comment information and location information.
The charging station can be equipment which is similar to an electric vehicle charging station, a mobile phone charging station and an automobile gas station and is used for powering up a battery and a mobile phone; the target comment data may be related data for evaluating the charging station; the comment information can be speech information in the target comment data, and the comment information can be character comment information; the location information may be location information where the user was commenting. Optionally, target comment data about the charging station may be extracted from each APP comment area or each comment area of the large platform in the internet, for example, comment information of the user on the charging station may be acquired from travel APPs (such as a gold map, a Baidu map, a drip taxi, and the like), charging APPs (such as a star charging, a special incoming call, and the like), other media (microblogs, WeChats, forums, website messages, and the like), and meanwhile, a geographic location of the user when making a comment is acquired, that is, comment information and location information are acquired, so that the target comment data is acquired; and target comment data of the user on the charging station can be acquired in a street interview, paper return visit or telephone visit mode.
And step S110, extracting the characteristics of the comment information to obtain key information.
The key information may be a core keyword in the comment information. Optionally, the key information may be a keyword that plays an evaluation role in the comment information on the charging station, for example, if the comment information is "the charging station is so remote that the place is far away", the core keyword "remote" may be extracted to determine that the comment information evaluates the position of the charging station, so the key information "remote" may be extracted; if the comment information is "expensive to charge", a core keyword "expensive" can be extracted to determine that the comment information evaluates the charging cost of the charging station, so that key information "expensive" can be extracted; if the comment information is 'the charging pile is bad after the charging pile runs so far away', core keywords 'bad' and 'far' can be extracted to determine that the comment information evaluates the availability and the position of the charging pile, and therefore the key information 'bad' and 'far' can be extracted.
And step S120, carrying out classification detection on the key information by using a preset classification model to obtain a comment type corresponding to the key information.
Optionally, the classification model may be a pre-trained mathematical model for classifying the key information; the comment type may be a standard comment category set in advance. Optionally, the comment types may be set according to requirements, for example, the comment types may be divided into eight categories of functionality, availability, cost, location, right to deal, user interaction, service time, and scope anxiety. Taking the KNN model as an example, the classification model may be a KNN model, and the key information may be used as input of the KNN model, and the classification detection is performed on the key information by the KNN model, and a comment type corresponding to the key information output by the KNN model is obtained, for example, if the key information input into the KNN model is "noble", the key information may be classified by the pre-trained KNN model, and the comment type corresponding to the key information output by the KNN model is obtained as a cost type.
And S130, analyzing an abnormal charging station according to the comment type and the position information.
The abnormal charging station can be a charging station with abnormal conditions fed back by the user through comment information. Optionally, if the comment information is "the charging pile is bad after running so far", extracting the key information "bad", performing classification detection on the key information through a preset classification model, and judging that the comment type corresponding to the key information is the availability type. Therefore, the geographical position of a 'bad' charging station (charging pile) can be determined according to the position information when the user gives comments, and the charging station with abnormity, which is commented by the user, is judged, namely the abnormal charging station is determined.
And generating abnormal prompt information according to the abnormal charging station.
Wherein, unusual prompt message can be used for the charging station manager this charging station of suggestion unusual. Optionally, for the charging station that is reviewed by the user and has the abnormality, the background manager may verify the situation of the abnormal charging station according to the abnormality prompt information, and determine whether the abnormal charging station really has the abnormality reviewed by the user, for example: the position information of the abnormal charging station can be analyzed firstly according to the abnormal prompt information, and whether the geographical position of the abnormal charging station is remote or not is judged; the payment record uploaded by the abnormal charging station can be analyzed, and whether the charge of the abnormal charging station is 'noble' or not can be judged; and the abnormal charging station can also be fed back to maintenance personnel according to the abnormal prompt information, so that the maintenance personnel can check the abnormal charging station on the spot and judge whether the abnormal charging station is damaged or not. In some specific embodiments, if the abnormal condition of the abnormal charging station is detected to be substantial according to the abnormal prompt information, the user who issues the comment information may be awarded, for example, the user may be subsidized in other manners such as a coupon, so as to eliminate the user's mental and mustard base; if the abnormal condition of the abnormal charging station is detected to be not true according to the abnormal prompt information, the user can be contacted in time, and after the communication and verification with the user are carried out, the client with malicious comments is warned or forbidden.
According to the charging station detection method, the target comment data of the charging station are obtained, and the target comment data comprise: comment information and positional information, then carry out feature extraction to comment information, obtain key information, reuse preset classification model to carry out classification detection to key information, obtain the comment type that key information corresponds, at last according to comment type and positional information analysis out unusual charging station, and according to unusual charging station generate unusual prompt information, can be under the prerequisite of guaranteeing the accuracy, detect out the satisfaction degree of user to the charging station simple and fast, the condition of in time feedback charging station.
In some embodiments of the present invention, after obtaining the target comment data of the charging station, the method further includes:
and if the target comment data are the preset standard comment data, determining the comment type corresponding to the preset standard comment data. The preset standard comment data can be preset standard comments for the user to select, and the preset standard comments can be selected by the user in a standard comment option mode. Optionally, it is assumed that the preset standard comment may be set corresponding to a preset comment type, for example, it is assumed that the comment type is eight types, respectively, of functionality, availability, cost, location, right to deal, user interaction, service time, and range anxiety, and then the corresponding preset standard comment data may be set for each comment type, for example, the preset standard comment data may be set for a comment type of "functionality" as: convenient, unchangeable, to be improved, and the like; the preset standard comment data can be set for the comment type of "availability" as follows: can be used, can not be used, can be used intermittently or can be used for other purposes; the preset standard comment data can be set for the comment type of "cost" as follows: high, low, mid-range, other, etc. Therefore, if the user only selects the preset standard comment data of "unavailable" when publishing the target comment data, it can be determined that the comment type corresponding to the preset standard comment data is "available"; if the user selects two preset standard comment data, namely 'unavailable' and 'invariable', when publishing the target comment data, the comment types corresponding to the preset standard comment data can be determined to be 'availability' and 'functionality'.
And skipping to the step of analyzing the abnormal charging station according to the comment type and the position information. Optionally, when the target comment data is the preset standard comment data, a comment type corresponding to the preset standard comment data may be determined, so that the step of abnormality detection may be skipped according to the determined comment type, that is, the step of analyzing an abnormal charging station according to the comment type and the position information, and an abnormal charging station may be analyzed. When the target comment data are the preset standard comment data, the comment type corresponding to the preset standard comment data can be directly determined, and then the step of analyzing the abnormal charging station according to the comment type and the position information is directly skipped, so that the satisfaction degree of the user on the charging station can be detected simply, conveniently and quickly, the analysis complexity is reduced, and the use experience of the user is improved.
In some embodiments of the invention, the charging station detection method further comprises:
and if the target comment data are the target text comment data, skipping to the step of extracting the features of the comment information to obtain the key information. The target text comment data may be text comment data input by a user. Optionally, if the target comment data is the target text comment data, for example, "the charging station is bad" or "the charging station charges too expensive", it is necessary to extract key information from the target text comment data, and determine a keyword included in the target text comment data and evaluating the charging station, so that a step of extracting features of the comment information to obtain the key information may be skipped. When the target comment data are the target text comment data, the step of extracting the features of the comment information to obtain the key information is skipped to, so that the satisfaction degree of the user on the charging station can be detected simply, conveniently and quickly, the analysis complexity is reduced, and the use experience of the user is improved.
In some embodiments of the present invention, the classifying the key information by using the classification model, and outputting the comment type corresponding to the key information includes:
and acquiring target classification data output by the classification model, and acquiring a classification label corresponding to the target classification data. The target classification data can be data with classification labels obtained by training key information by using a classification model; the classification tags may be used to mark the types of reviews to which the target classification data pertains. Optionally, the classification model may be used to train the key information, classify the key information, and extract the classification label of the target classification data output by the classification model. For example, assuming that the classification model is a trained KNN model, assuming that the key information is "bad", the key information may be classified by the KNN model, assuming that the classification label corresponding to the key information "bad" is "unavailable", thereby obtaining the target classification information, and extracting the classification label "unavailable"; assuming that the key information is "noble", the key information may be classified by the KNN model, assuming that the classification label corresponding to the key information "noble" is "costly", thereby obtaining the target classification information, and extracting the classification label "costly".
And determining the comment type corresponding to the key information according to the classification label. Optionally, the target classification information may be classified according to the classification label, and a comment type corresponding to the key information is determined. For example, assuming that the classification label corresponding to the key information "bad" is "unavailable", the classification of the key information may be determined as "availability" according to the classification label "unavailable"; assuming that the classification label corresponding to the key information "far" is "far", the classification of the key information as "location" can be determined according to the classification label "far". By acquiring the target classification data output by the classification model, then acquiring the classification labels corresponding to the target classification data, and finally determining the comment types corresponding to the key information according to the classification labels, the classification accuracy can be ensured, and the analysis complexity is reduced.
In some embodiments of the invention, the charging station detection method further comprises: obtaining a classification model, specifically comprising:
and obtaining historical comment data, and extracting comment data to be trained from the historical comment data. The historical comment data can be historical comments about the charging station, which are collected through big data analysis; the comment data to be trained can be comment data used for training the classification model in the historical comment data.
And constructing an initial training model according to the comment data to be trained. The initial training model may be an initial mathematical model for classification constructed according to the comment data to be trained. Optionally, an initial KNN model is constructed by combining the comment data to be trained with the KNN algorithm, so that the initial training model is obtained.
And extracting the features of the comment data to be trained to obtain training key features. The training key features can be extracted keywords in the comment data to be trained. Optionally, if the comment data to be trained is "charging station response slowness", the keyword "response slowness" may be extracted, and thus the obtained training key feature is "response slowness", and the comment type corresponding to the training key feature is "user interaction".
And training the initial training model according to the training key characteristics to obtain a classification model. Optionally, a plurality of training key features may be used as input of the initial training model, and the training key features are subjected to classification training according to the comment types corresponding to the training key features, and a trained classification model is obtained through multiple iterative training. Specifically, when the initial training model reaches a predetermined precision or reaches a predetermined number of iterations, it may be determined that the initial training model is completely trained, and thus a trained training model may be obtained. The method comprises the steps of extracting comment data to be trained in historical comment data, constructing an initial training model according to the comment data to be trained, extracting features of the comment data to be trained to obtain training key features, and finally training the initial training model according to the training key features to obtain a classification model, so that the precision of the classification model can be improved, and the detection efficiency of a charging station can be improved.
In some embodiments of the present invention, training the initial training model according to the training key features to obtain a classification model, including:
and acquiring preset iteration times. The preset iteration number may be a preset iteration number of the initial training model. Optionally, the preset iteration number may be set according to a requirement, for example, it is assumed that the iteration number is set to n according to a model precision requirement.
And updating the initial training model according to the preset iteration times and the training key characteristics. Optionally, the accuracy of the classification model obtained by training may be controlled by the iteration number of the initial training model, and therefore, assuming that the preset iteration number is n, the training key features may be used as the input of the initial training model, and the initial training model is updated n times to obtain n updated initial training models.
And selecting a classification model from the plurality of updated initial training models. Optionally, assuming that n updated initial training models are obtained through n iterations, since the model accuracy corresponding to each updated initial training model is different, one of the updated n initial training models with the highest model accuracy may be selected as the classification model, so that the accuracy of the classification model may be improved.
In some embodiments of the invention, the method of obtaining a classification model further comprises:
and extracting the comment data to be tested from the historical comment data. The comment data to be tested can be comment data used for testing the classification model in the historical comment data. Optionally, the historical comment data may be divided into to-be-trained comment data and to-be-tested comment data, and the to-be-trained comment data and the to-be-tested comment data may be obtained by randomly dividing the historical comment data or by dividing the historical comment data according to a preset proportion. Assuming that the ratio between the comment data to be trained and the comment data to be tested is 7:3, the comment data to be tested of 3/10 can be extracted from the historical comment data.
And training the comment data to be tested according to the classification model, and outputting preset classification data. The preset classification data may be classified data output by the classification model after the comment data to be tested is input by the classification model, and the preset classification data may be data with a classification label. Optionally, feature extraction may be performed on the comment data to be tested to obtain a keyword of the comment data to be tested, then the comment data to be tested after feature extraction is used as input of the classification model, and data with a classification label output by the classification model is obtained, so that preset classification data can be obtained.
And determining the comment type corresponding to the comment data to be tested according to the preset label corresponding to the preset classification data. The preset label may be a classification label corresponding to preset classification data. Optionally, if a preset tag corresponding to a keyword "bad" of preset classification data is "unavailable", determining that a comment type corresponding to the comment data to be tested is "unavailable" according to the preset tag; assuming that a preset label corresponding to the keyword 'good interaction experience' of the preset classification data is 'comfortable', the comment type corresponding to the comment data to be tested can be determined as 'user interaction' according to the preset label. The classification model is tested through the to-be-tested comment data, so that the accuracy of the classification model can be further improved.
The following describes the process of the charging station detection method according to an embodiment of the present invention in detail. It is to be understood that the following description is only exemplary, and not a specific limitation of the invention.
The charging station detection method comprises the following steps:
firstly, obtaining user comment data.
In order to obtain the evaluation of the user on each charging station infrastructure, target comment data about the charging station can be extracted from each APP comment area or each comment area of a large platform in the internet, for example, comment information about the charging station by the user can be obtained from travel APPs (such as a gold map, a hectic map, a drip taxi, and the like), charging APPs (such as a star charge, a special incoming call, and the like), other media (such as microblogs, WeChats, forums, website messages, and the like), and meanwhile, the geographical position of the user when the user makes a comment can be obtained, so that the comment data about the charging station by the user can be obtained, and the comment data about the charging station by the user can also be obtained in a street interview, paper return interview, or telephone interview.
And secondly, analyzing the user comment data and judging the comment type of the user comment data.
Optionally, if the user comment data is preset standard comment data, for example, a user inputs two standard comment options of "high" and "intermittent", the comment types of the user comment data may be determined to be a "cost" type and an "availability" type, respectively, directly according to the standard comment options; if the user comment data is target text comment data, namely text comment data input by the user, the target text comment data needs to be analyzed through a pre-trained classification model, and the comment type corresponding to the target text comment data is judged. For example, taking the classification model as the KNN model as an example, assuming that the user comment data is "insensitive to touch screen operation of the charging station", the key information of the user comment data may be extracted as "insensitive", the key information may be used as the input of the KNN model, and the comment type output by the KNN model is obtained (the comment type may be determined by the classification tag corresponding to the target classification data output by the KNN model), and assuming that the comment type output by the KNN model is "user interaction"; in some specific embodiments, if the user comment data includes both preset standard comment data and target text comment data, comment types corresponding to the preset standard comment data and the target text comment data may be determined respectively, so as to obtain a plurality of comment types corresponding to the user comment data.
And thirdly, generating abnormal prompt information according to the comment type of the comment data of the user and the geographical position of the user when the user makes a comment so as to prompt a manager to perform abnormal detection on the charging station.
For the charging station with the abnormal charging station reviewed by the user, the background manager can verify the situation of the abnormal charging station according to the abnormal prompt information, and determine whether the abnormal charging station really has the abnormal situation reviewed by the user, for example: the position information of the abnormal charging station can be analyzed firstly according to the abnormal prompt information, and whether the geographical position of the abnormal charging station is remote or not is judged; the payment record uploaded by the abnormal charging station can be analyzed, and whether the charge of the abnormal charging station is 'noble' or not can be judged; and the abnormal charging station can also be fed back to maintenance personnel according to the abnormal prompt information, so that the maintenance personnel can check the abnormal charging station on the spot and judge whether the abnormal charging station is damaged or not. In some specific embodiments, if the abnormal condition of the abnormal charging station is detected to be substantial according to the abnormal prompt information, the user who issues the comment information may be awarded, for example, the user may be subsidized in other manners such as a coupon, so as to eliminate the user's mental ties and mustard pedicles, and the user may also be subsidized; if the abnormal condition of the abnormal charging station is detected to be not true according to the abnormal prompt information, the user can be contacted in time, and after the communication and verification with the user are carried out, the client with malicious comments is warned or forbidden. In some specific embodiments, the abnormal prompt information may be counted, and an alarm may be generated according to the statistical condition to remind the manager to optimize and improve the charging station with multiple abnormal situations.
According to the charging station detection method, the satisfaction degree of a user to the charging station can be simply, conveniently and quickly detected on the premise of ensuring the accuracy, and the condition of the charging station can be timely fed back.
Referring to fig. 2, a charging station detection apparatus according to an embodiment of a second aspect of the present invention includes:
the obtaining module 200 is configured to obtain target comment data of the charging station, where the target comment data includes: comment information and location information;
the extraction module 210 is configured to perform feature extraction on the comment information to obtain key information;
the classification module 220 is configured to perform classification detection on the key information by using a preset classification model to obtain a comment type corresponding to the key information;
the analysis module 230 is used for analyzing an abnormal charging station according to the comment type and the position information;
and the prompt module 240 is configured to generate an abnormal prompt message according to the abnormal charging station.
By implementing the charging station detection method of the embodiment of the first aspect of the invention, the charging station detection device can simply, conveniently and quickly detect the satisfaction degree of the user on the charging station on the premise of ensuring the accuracy, and timely feed back the condition of the charging station.
Referring to fig. 3, an embodiment of the third aspect of the present invention further provides a functional module diagram of an electronic device, including: at least one processor 300, and a memory 310 communicatively coupled to the at least one processor 300; the system also comprises a data transmission module 320, a camera 330 and a display screen 340.
Wherein the processor 300 is adapted to perform the charging station detection method in the first embodiment by invoking a computer program stored in the memory 310.
The data transmission module 320 is connected to the processor 300, and is used for implementing data interaction between the data transmission module 320 and the processor 300.
The cameras 330 may include front cameras and rear cameras. Generally, a front camera is disposed at a front panel of the terminal, and a rear camera is disposed at a rear surface of the terminal. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera 330 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.
The display screen 340 may be used to display information entered by the user or provided to the user. The Display screen 340 may include a Display panel, and optionally, the Display panel may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like. Further, the touch panel may cover the display panel, and when the touch panel detects a touch operation thereon or nearby, the touch panel transmits the touch operation to the processor 300 to determine the type of the touch event, and then the processor 300 provides a corresponding visual output on the display panel according to the type of the touch event. In some embodiments, the touch panel may be integrated with the display panel to implement input and output functions.
The memory, as a non-transitory storage medium, may be used to store non-transitory software programs and non-transitory computer-executable programs, such as the charging station detection method in the embodiment of the first aspect of the present invention. The processor implements the charging station detection method in the above-described first aspect embodiment by executing a non-transitory software program and instructions stored in the memory.
The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store a data for performing the charging station detection method in the embodiment of the first aspect described above. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and these remote memories may be connected to the terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Non-transitory software programs and instructions required to implement the charging station detection method in the first aspect embodiment described above are stored in a memory and, when executed by one or more processors, perform the charging station detection method in the first aspect embodiment described above.
Embodiments of the fourth aspect of the present invention also provide a computer-readable storage medium storing computer-executable instructions for: the charging station detection method in the first aspect embodiment is performed.
In some embodiments, the storage medium stores computer-executable instructions, which are executed by one or more control processors, for example, by one of the processors in the electronic device of the embodiment of the third aspect, may cause the one or more processors to perform the charging station detection method of the embodiment of the first aspect.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
The above-described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may also be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
One of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. The charging station detection method is characterized by comprising the following steps:
obtaining target comment data of a charging station, wherein the target comment data comprises: comment information and location information;
extracting features of the comment information to obtain key information;
classifying and detecting the key information by using a preset classification model to obtain a comment type corresponding to the key information;
analyzing an abnormal charging station according to the comment type and the position information;
and generating abnormal prompt information according to the abnormal charging station.
2. The method of claim 1, wherein after the obtaining target review data for the charging station, further comprising:
if the target comment data are preset standard comment data, determining a comment type corresponding to the preset standard comment data;
and skipping to the step of analyzing the abnormal charging station according to the comment type and the position information.
3. The method of claim 2, further comprising:
and if the target comment data are target text comment data, skipping to the step of extracting the characteristics of the comment information to obtain key information.
4. The method of claim 1, wherein the classifying and detecting the key information by using a classification model and outputting a comment type corresponding to the key information comprises:
acquiring target classification data output by the classification model;
acquiring a classification label corresponding to the target classification data;
and determining the comment type corresponding to the key information according to the classification label.
5. The method of claim 1, further comprising: obtaining the classification model specifically includes:
obtaining historical comment data, and extracting comment data to be trained from the historical comment data;
constructing an initial training model according to the comment data to be trained;
extracting features of the comment data to be trained to obtain training key features;
and training the initial training model according to the training key characteristics to obtain the classification model.
6. The method of claim 5, wherein the training the initial training model according to the training key features to obtain the classification model comprises:
acquiring a preset iteration number;
updating the initial training model according to the preset iteration times and the training key features;
and selecting the classification model from the plurality of updated initial training models.
7. The method of claim 6, further comprising:
extracting comment data to be tested from the historical comment data;
training the comment data to be tested according to the classification model, and outputting preset classification data;
and determining the comment type corresponding to the comment data to be tested according to the preset label corresponding to the preset classification data.
8. Charging station detection device, its characterized in that includes:
the acquisition module is used for acquiring target comment data of the charging station, wherein the target comment data comprise: comment information and location information;
the extraction module is used for extracting the characteristics of the comment information to obtain key information;
the classification module is used for carrying out classification detection on the key information by using a preset classification model to obtain a comment type corresponding to the key information;
the analysis module is used for analyzing an abnormal charging station according to the comment type and the position information;
and the prompt module is used for generating abnormal prompt information according to the abnormal charging station.
9. An electronic device, comprising:
at least one processor, and,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions for execution by the at least one processor to cause the at least one processor to implement the charging station detection method of any of claims 1-7 when executing the instructions.
10. A computer-readable storage medium, characterized in that the storage medium stores computer-executable instructions for causing a computer to perform the charging station detection method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110191758.8A CN112861002A (en) | 2021-02-20 | 2021-02-20 | Charging station detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110191758.8A CN112861002A (en) | 2021-02-20 | 2021-02-20 | Charging station detection method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112861002A true CN112861002A (en) | 2021-05-28 |
Family
ID=75988238
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110191758.8A Pending CN112861002A (en) | 2021-02-20 | 2021-02-20 | Charging station detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112861002A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110162621A (en) * | 2019-02-22 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Disaggregated model training method, abnormal comment detection method, device and equipment |
| CN111738541A (en) * | 2020-05-08 | 2020-10-02 | 北京三快在线科技有限公司 | Method and device for acquiring store food quality information and electronic equipment |
-
2021
- 2021-02-20 CN CN202110191758.8A patent/CN112861002A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110162621A (en) * | 2019-02-22 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Disaggregated model training method, abnormal comment detection method, device and equipment |
| CN111738541A (en) * | 2020-05-08 | 2020-10-02 | 北京三快在线科技有限公司 | Method and device for acquiring store food quality information and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11308719B2 (en) | System and method for capture and distribution of information collected from signs | |
| US9607515B2 (en) | System and method for interacting with digital signage | |
| CN205920517U (en) | Intelligent movement routing inspection terminal based on thing networking | |
| US9533688B1 (en) | Platform for acquiring driver behavior data | |
| CN106056695A (en) | Internet-of-Things-based intelligent mobile patrol inspection terminal | |
| US20210124967A1 (en) | Method and apparatus for sample labeling, and method and apparatus for identifying damage classification | |
| US11010640B1 (en) | Automated training data quality process | |
| CN105787133B (en) | Advertisement information filtering method and device | |
| CN102801817A (en) | Subscriber context-based pushing method and device | |
| EP3994423B1 (en) | Collecting user-contributed data relating to a navigable network | |
| CN111222375A (en) | Vehicle driving track generation method, system and server | |
| CN107705576A (en) | Vehicle fake-license detection method, server and storage medium | |
| CN113899355A (en) | Map updating method and device, cloud server and shared riding equipment | |
| US20220210621A1 (en) | Methods and systems for detecting delivery trip events and improving delivery driver safety | |
| CN110930537A (en) | Vehicle data acquisition method, device and equipment based on big data and storage medium | |
| CN113391801A (en) | Recommendation engine architecture based on cloud service | |
| CN105243100A (en) | Map rendering method, and method and apparatus for providing rendering target information | |
| CN113240480A (en) | Order processing method and device, electronic terminal and storage medium | |
| CN107861980A (en) | A kind of vehicle identification method and its terminal | |
| CN112861002A (en) | Charging station detection method and device, electronic equipment and storage medium | |
| CN111782973A (en) | Interest point state prediction method and device, electronic equipment and storage medium | |
| CN114550129B (en) | Machine learning model processing method and system based on data set | |
| CN115273025A (en) | Traffic asset checking method, device, medium and electronic equipment | |
| CN112810489B (en) | Safe charging management system for new energy automobile | |
| CN112232723B (en) | Method and device for detecting abnormal behaviors in real time, 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210528 |
|
| WD01 | Invention patent application deemed withdrawn after publication |