CN114139534A - An online car-hailing public opinion monitoring method - Google Patents

Abstract

Translated fromChinese

本发明提供的一种网约车舆情监控方法，所述监控方法包括：向目标站点发起请求，获取响应内容；将所述响应内容进行解析，获得解析数据，将所述解析数据存入数据库；采用结巴词库的分词技术将爬虫抓取的文字信息进行分词整理，并通过词云函数可视化抓取结果，获得可视化图文结果；将所述可视化图文结果发送至钉钉工作群。全面地对消费者关心的信息进行立体监测，及时预警负面、重要、重点信息，实时跟踪突发事件舆情信息。

The present invention provides a public opinion monitoring method for online car-hailing, the monitoring method comprising: initiating a request to a target site to obtain response content; parsing the response content to obtain parsing data, and storing the parsing data in a database; The word segmentation technology of the jiba thesaurus is used to segment the text information captured by the crawler, and visualize the capture results through the word cloud function to obtain visual graphic results; send the visual graphic results to the DingTalk work group. Comprehensively conduct three-dimensional monitoring of information that consumers care about, timely warn of negative, important and key information, and track public opinion information on emergencies in real time.

Description

Internet appointment public opinion monitoring method

Technical Field

The invention relates to the field of online taxi appointment, in particular to a public opinion monitoring method for online taxi appointment.

Background

In the current network car booking major accident handling process, the following problems can exist: the general victim, when improperly challenged, first thinks of going to some larger public media platform exposure victimized experience, hopefully causing a greater range of impact.

Therefore, how to comprehensively carry out three-dimensional monitoring on information concerned by consumers, early warn negative, important and key information in time and track the public sentiment information of the outburst events in real time.

Disclosure of Invention

In view of the above problems, the present invention has been made to provide a cyber-attraction monitoring method that overcomes or at least partially solves the above problems.

According to an aspect of the present invention, there is provided a method for monitoring public opinion of online car appointment, the method comprising:

initiating a request to a target site to acquire response content;

analyzing the response content to obtain analysis data, and storing the analysis data into a database;

word segmentation and arrangement are carried out on the character information captured by the crawler by adopting a word segmentation technology of a word bank of the crust, and a visual image-text result is obtained through a word cloud function visual capture result;

and sending the visual image-text result to a nailing working group.

Optionally, the initiating a request to the target site and acquiring the response content specifically include:

initiating a request to a target station by using an http library, and sending a request, wherein the request comprises a request header and a request body;

and the server normally responds to obtain a response, wherein the response comprises html, json, pictures and videos.

Optionally, the analyzing the response content to obtain analyzed data specifically includes:

installing a word bank of Chinese knot, pip installjieba, in python 3;

screening out a Chinese part from data grabbed by a crawler;

calling a word segmentation module of the ending lexicon, and segmenting the screened Chinese part into words with independent meanings;

and calling a word cloud picture module to visually display the split words according to the occurrence frequency, so that an analyst can easily and quickly read valuable information.

Optionally, sending the visual image-text result to the nailing working group specifically includes:

the major public opinion information is broadcasted to a public opinion real-time monitoring group in a text summary mode in time, and a main responsible person is notified;

broadcasting the cloud pictures of the important public opinion information words in recent days to a public opinion real-time monitoring group to remind relevant responsible persons of recent important public opinion information.

The invention provides a method for monitoring public opinion of online taxi appointment, which comprises the following steps: initiating a request to a target site to acquire response content; analyzing the response content to obtain analysis data, and storing the analysis data into a database; word segmentation and arrangement are carried out on the character information captured by the crawler by adopting a word segmentation technology of a word bank of the crust, and a visual image-text result is obtained through a word cloud function visual capture result; and sending the visual image-text result to a nailing working group. The method comprehensively carries out three-dimensional monitoring on information concerned by consumers, timely pre-warns negative, important and key information, and tracks the public sentiment information of the outburst events in real time.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a diagram illustrating a method for monitoring public opinion of a network appointment according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The terms "comprises" and "comprising," and any variations thereof, in the present description and claims and drawings are intended to cover a non-exclusive inclusion, such as a list of steps or elements.

The technical solution of the present invention is further described in detail with reference to the accompanying drawings and embodiments.

As shown in fig. 1, the application of Python crawler and the ending thesaurus in the monitoring of public opinion of network car appointment is divided into three links. Respectively capturing character information published or commented by a user on a mainstream media by a Python crawler according to keywords in the first step;

the method for the crawler to acquire the network data comprises the following steps: the simulated browser sends a request (get web page code) > extracts useful data- > deposits in a database or file.

The Python crawler captures text information published or commented by a user on the mainstream media according to the keywords.

The method includes the following steps that character information published or commented by a user on a mainstream media is captured, the selection of keywords is important, and the following keywords can be referred for accurately capturing important public opinion information: first car appointment, dripping, Caocao special car, net appointment car, driver, complaint, harassment and the like.

Word segmentation and arrangement are carried out on the character information captured by the crawler through a word segmentation technology of the word bank, and the captured result is visualized through a word cloud function;

the data previously crawled by the crawler is stored in a variable value.

Installing a JieBe word stock: the crust word stock, pip installjieba, was installed in python 3.

Extracting Chinese: and screening out the Chinese part from the data grabbed by the crawler.

The word segmentation of the crust: and calling a word segmentation module of the ending lexicon, and splitting the screened Chinese part into words with independent meanings.

Visualization of word cloud: and calling a word cloud picture module to visually display the split words according to the occurrence frequency, so that an analyst can easily and quickly read valuable information.

And thirdly, automatically sending the visual image-text result to a nailing working group to enable staff in charge of public relations to know the latest public opinion information in time.

The important public opinion information is broadcasted to the public opinion real-time monitoring group in a text summary mode in time, and the main responsible person is Artemisia.

Broadcasting the cloud pictures of the important public opinion information words in recent days to a public opinion real-time monitoring group to remind relevant responsible persons of recent important public opinion information.

Word segmentation and arrangement are carried out on the character information captured by the crawler through a word segmentation technology of the ending lexicon, and the captured result is visualized through a word cloud function.

In order to refine the character information captured by the crawler into more valuable information, a Chinese word stock of the Chinese character 'Jieba' is introduced, and long sentences are converted into conventional words.

The word segmentation principle of the word bank of the Chinese crust is as follows: determining the association probability between Chinese characters by using a Chinese word library; the words with high probability among the Chinese characters form word segmentation results.

And then forming a visualized word cloud picture by the words according to the occurrence frequency.

And the visual image-text result is automatically sent to a nailing working group, so that the staff in charge of public relations can know the latest public opinion information in time.

The major public opinion information is timely synchronized to the staff group in public relations through the nailing robot technology. The key words are regarded as important public opinion information as long as the following key words are captured: violation, vehicle jump, sexual disturbance and garbage platform.

Has the advantages that: the crawler, the word segmentation and the robot in the prior art are combined together, so that the system is applied to monitoring important public opinion events in the network appointment car industry, comprehensively carries out three-dimensional monitoring on information concerned by consumers, timely pre-warns negative, important and key information, and tracks public opinion information of sudden events in real time. The reputation and the image of the online car booking enterprise are timely retrieved, and even huge economic loss is avoided.

The above embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, it should be understood that the above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (4)

Translated fromChinese

1.一种网约车舆情监控方法，其特征在于，所述监控方法包括：1. A method for monitoring public opinion on car-hailing, wherein the monitoring method comprises:向目标站点发起请求，获取响应内容；Initiate a request to the target site and get the response content;将所述响应内容进行解析，获得解析数据，将所述解析数据存入数据库；Parsing the response content, obtaining parsing data, and storing the parsing data in a database;采用结巴词库的分词技术将爬虫抓取的文字信息进行分词整理，并通过词云函数可视化抓取结果，获得可视化图文结果；Using the word segmentation technology of the jiba thesaurus, the text information captured by the crawler is divided into words, and the captured results are visualized through the word cloud function to obtain visual graphic and text results;将所述可视化图文结果发送至钉钉工作群。Send the visual image and text results to the DingTalk work group.2.根据权利要求1所述的一种网约车舆情监控方法，其特征在于，所述向目标站点发起请求，获取响应内容具体包括：2 . The method for monitoring public opinion of an online car-hailing vehicle according to claim 1 , wherein the initiating a request to the target site and obtaining the response content specifically include: 2 .使用http库向目标站点发起请求，发送一个请求，所述请求包括请求头和请求体；Use the http library to initiate a request to the target site, and send a request, the request includes a request header and a request body;服务器正常响应，得到一个响应，所述响应包括html，json，图片，视频。The server responds normally and gets a response, and the response includes html, json, pictures, and videos.3.根据权利要求1所述的一种网约车舆情监控方法，其特征在于，所述将所述响应内容进行解析，获得解析数据具体包括：3 . The method for monitoring public opinion on online car-hailing according to claim 1 , wherein the analyzing the response content and obtaining the analysis data specifically comprises: 3 .在python3中安装结巴词库，pip installjieba；Install jieba in python3, pip installjieba;从爬虫抓取到的数据，筛选出中文部分；From the data captured by the crawler, filter out the Chinese part;调用结巴词库分词模块，将筛选出的中文部分，拆分为具备独立意义的词语；Call the word segmentation module of Jaba thesaurus to split the screened Chinese parts into words with independent meanings;调用词云图模块，将拆分开的词语按出现的频次可视化地展示出来，易于分析人员快速读取有价值的信息。Call the word cloud graph module to visually display the split words according to the frequency of occurrence, which is easy for analysts to quickly read valuable information.4.根据权利要求1所述的一种网约车舆情监控方法，其特征在于，所述将所述可视化图文结果发送至钉钉工作群具体包括：4 . The method for monitoring public opinion on car-hailing according to claim 1 , wherein the sending the visualized graphic and text results to the DingTalk work group specifically comprises: 5 .将重大舆情信息以文字概要形式及时播报至舆情实时监控群，并通知主要负责人；Timely broadcast major public opinion information in the form of a text summary to the real-time public opinion monitoring group, and notify the main person in charge;将近几日重大舆情信息词云图，播报至舆情实时监控群，提醒相关负责人近期重大舆情信息。The word cloud map of major public opinion information in recent days is broadcast to the real-time public opinion monitoring group to remind relevant persons in charge of recent major public opinion information.

Images