CN117575687A

CN117575687A - Method and device for monitoring new media operation effect of automobile based on big data

Info

Publication number: CN117575687A
Application number: CN202311626554.8A
Authority: CN
Inventors: 黄为伟
Original assignee: Beijing Extreme Vehicle Network Technology Co ltd
Current assignee: Beijing Extreme Vehicle Network Technology Co ltd
Priority date: 2023-11-30
Filing date: 2023-11-30
Publication date: 2024-02-20

Abstract

The application provides a method and a device for monitoring an operation effect of a new automobile media based on big data, wherein real-time evaluation contents aiming at a preset automobile brand on a webpage are extracted according to a preset mode; judging whether a plurality of pre-stored first evaluation contents of a preset database exist first evaluation contents which are the same as the real-time evaluation contents or not, and if the first evaluation contents which are the same as the real-time evaluation contents exist in the plurality of first evaluation contents, determining that the real-time evaluation contents are positive evaluation; acquiring a first change trend of positive evaluation; determining a second trend of change in positive rating during implementation of a new media operation activity for a preset car brand; if the first change trend is determined to be the stable evaluation number trend or the reduced evaluation number trend, and the second change trend is determined to be the increasing evaluation number trend, recording the operation effect of the new media operation activity as reaching the first operation effect. The method and the device can monitor the effect of the new media operation activity according to the evaluation of the user on the automobile brand.

Description

Method and device for monitoring new media operation effect of automobile based on big data

Technical Field

The application relates to the technical field of data processing, in particular to a method and a device for monitoring an operation effect of a new medium of an automobile based on big data.

Background

New media operation is a strategy for real-time interaction, brand promotion and user participation with target audience through digital platforms such as social media, blogs, online forums and the like by utilizing various content forms. The method covers various aspects of content creation, community management, data analysis and the like, and aims to construct positive brand images, promote user interaction and realize continuous development of brands in the digital age by means of real-time data monitoring and optimizing strategies. New media operations emphasize creative, communication and close contact with the audience, an indispensable ring in modern digital marketing.

The evaluation of the internet for the brand of motor vehicles has a great influence in the current digital age, which not only directly shapes the consumer's impressions of vehicle performance, quality and service, but also has a profound effect on brand image and market competition. Positive ratings help build trust, promote brand reputation, attract potential buyers, while negative ratings may lead to consumer doubts and impact on car purchasing decisions, so promotion of car brand ratings through new media operations is critical because consumers increasingly rely on the internet to obtain information and share experience in today's digital age. Through active and strategic new media operation, the automobile brands can interact users in real time, transfer accurate brand information and build active brand images, so that the satisfaction and loyalty of the users are improved. The effective new media operation not only can shape the brand story and attract target audiences, but also is helpful for controlling public opinion and responding to user concerns, and finally enhances the competitive power of the brand in the competitive automobile market, and promotes the continuous growth of sales and performance.

Currently, the evaluation and monitoring of the effects of new media operation activities is mainly focused on indicators of various aspects. On a social media platform, the focus points include fan growth, interaction rate, sharing times, and exposure of posts. In addition, correlating sales and performance data, as well as knowing user satisfaction through surveys and feedback, are important means for comprehensive assessment of the effectiveness of new media operations. There are few related art that mention how to evaluate and monitor the effects of new media operations based on a user's evaluation of the brand of car.

Disclosure of Invention

The application provides a method and a device for monitoring the operation effect of new media of an automobile based on big data, which can evaluate and monitor the effect of the operation activity of the new media according to the evaluation of a user on the brand of the automobile.

In a first aspect of the present application, a method for monitoring an operation effect of a new media of an automobile based on big data is provided, the method comprising:

extracting real-time evaluation content aiming at a preset automobile brand on a webpage according to a preset mode;

judging whether a plurality of pre-stored first evaluation contents of a preset database exist first evaluation contents which are the same as the real-time evaluation contents, if so, determining that the real-time evaluation contents are positive evaluation contents, wherein the first evaluation contents are pre-stored positive evaluation contents;

Acquiring a first variation trend of the positive evaluation, wherein the first variation trend is one of an evaluation quantity increasing trend, an evaluation quantity stabilizing trend and an evaluation quantity reducing trend;

determining a second trend of change of the aggressive rating during implementation of a new media operation campaign for the preset auto brand, the second trend of change being one of the rating amount increasing trend, the rating amount stabilizing trend, and the rating amount decreasing trend;

if the first change trend is determined to be the stable evaluation number trend or the decreasing evaluation number trend, and the second change trend is determined to be the increasing evaluation number trend, the operation effect of the new media operation activity is recorded to be a first operation effect, and the first operation effect is an effect of increasing the positive evaluation number.

By adopting the technical scheme, the real-time evaluation of the user on the preset automobile brand is obtained during the implementation of the new media operation activity, and the evaluation and monitoring of the new media operation effect are realized by combining the pre-stored evaluation content in the preset database. Firstly, by extracting real-time evaluation contents aiming at automobile brands on a webpage, judging whether the real-time evaluation contents are matched with prestored positive evaluation contents in a preset database. If there is a match, i.e., the real-time evaluation content is the same as the pre-stored aggressive evaluation content, the real-time evaluation content is determined to be an aggressive evaluation. Next, a first trend of change positively toward evaluation, that is, a trend of increase, stabilization, or decrease in the number of evaluation is analyzed. During the new media operation campaign, a second trend of change towards the rating, i.e. increasing, stabilizing or decreasing trend of the number of ratings, is further determined. If the first change trend is that the evaluation number is stable or reduced, and the second change trend is that the evaluation number is increased, the operation effect of the new media operation activity is recorded to reach the first operation effect, namely, the positive evaluation number is successfully increased. The technical scheme has the advantages that the evaluation of the automobile brands can be captured from the real-time feedback of the user, and the emotion tendencies of the feedback of the user can be judged by comparing the positive evaluation in the preset database. By analyzing the change trend of the evaluation quantity, the attitude change of the user to the preset automobile brand can be comprehensively considered, and then the effect of the new media operation activity can be evaluated.

Optionally, extracting the real-time evaluation content specific to the preset automobile brand on the web page according to the preset mode specifically includes:

directionally acquiring a plurality of first webpage contents, wherein the first webpage contents are webpage contents of related automobile websites;

screening at least one second webpage content from the plurality of first webpage contents, wherein the second webpage content is related to the preset automobile brand;

extracting text content from at least one second webpage content to obtain a plurality of preset evaluation contents, wherein the preset evaluation contents are text evaluation contents related to the preset automobile brands;

judging whether a first evaluation content or a second evaluation content which is the same as the preset evaluation content exists in a plurality of first evaluation contents and a plurality of second evaluation contents which are pre-stored in the preset database, wherein the second evaluation content is a pre-stored negative evaluation content;

and if the first evaluation content or the second evaluation content which is the same as the preset evaluation content exists in the first evaluation contents and the second evaluation contents, determining that the preset evaluation content is the real-time evaluation content.

By adopting the technical scheme, the plurality of first webpage contents of the automobile related websites are obtained in a directed way, and at least one second webpage content related to the preset automobile brand is further screened out. By directionally acquiring and screening a plurality of webpage contents related to a preset automobile brand, real-time evaluation issued by a user on the Internet can be captured in time, and timeliness of evaluation data is ensured. Then, text content is extracted from the second webpage content to form a plurality of preset evaluation contents, wherein the contents are user evaluation related to preset automobile brands. Judging whether the first evaluation content or the second evaluation content which is the same as the preset evaluation content exists or not by comparing the plurality of first evaluation contents with a plurality of second evaluation contents which are prestored in a preset database, wherein the second evaluation content is preset as negative evaluation. If the same evaluation contents exist, it is determined that these contents are real-time evaluation contents. This process enables efficient extraction and screening of real-time ratings of a user for a particular brand of automobile over the internet.

Optionally, after determining the second trend of change of the aggressive rating during implementation of the new media operation activity for the preset auto brand, the method further comprises:

And if the first change trend is the evaluation number stabilizing trend or the evaluation number increasing trend, the second change trend is the evaluation number reducing trend, recording the operation effect as a second operation effect, and the second operation effect is an effect of reducing the positive evaluation number.

By adopting the technical scheme, the effect of the new media operation activity can be more comprehensively evaluated. By examining the trend of the positive evaluation number, the overall trend of the positive evaluation of the automobile brand by the user can be identified. By analyzing the second trend, the reasons behind the user evaluation number can be known more deeply, and more specific feedback is provided for the operation activity effect especially under the condition that the evaluation number is reduced. This helps businesses discover and resolve problems in time that may lead to a reduction in positive ratings, thereby improving brand image and user satisfaction.

and if the first change trend is determined to be the evaluation number stable trend, the second change trend is determined to be the evaluation number stable trend, or if the first change trend is determined to be the evaluation number reduction trend, the second change trend is determined to be the evaluation number reduction trend, the operation effect is recorded as a third operation effect, and the third operation effect is an effect of stabilizing and actively evaluating the number.

By adopting the technical scheme, the influence of the new media operation activities on the positive evaluation can be more comprehensively evaluated. The record of the third operational effect indicates that the operational activity is able to maintain a positive rating level for the user for the car brand while the number of positive ratings remains stable. This result is critical to maintaining good reputation for brands, stabilizing user satisfaction, as it suggests that the operational activity not only successfully attracts positive evaluations, but also maintains the stability of this positive situation.

if the first change trend is determined to be the evaluation number increasing trend, the second change trend is determined to be the evaluation number increasing trend, a first evaluation increasing speed based on the first change trend is determined, and a second evaluation increasing speed based on the second change trend is determined, wherein the first evaluation increasing speed is the increasing speed of the number of active evaluations before the new media operation activity is implemented, and the second evaluation increasing speed is the increasing speed of the number of active evaluations during the new media operation activity is implemented;

Judging whether the second evaluation increasing speed is greater than the first evaluation increasing speed, and if the second evaluation increasing speed is greater than the first evaluation increasing speed, recording the operation effect of the new media operation activity as reaching the first operation effect.

By adopting the technical scheme, the change speed of the evaluation quantity is considered, and the effect of the new media operation activity in promoting the positive evaluation is highlighted. When a new media operation activity is performed, if the rate of increase in the number of ratings is significantly higher than before the operation activity, this indicates that the operation activity successfully promotes the increasing potential for users to actively rate. This not only demonstrates the positive effect of the operational activity, but also emphasizes its contribution in accelerating the user's positive feedback.

Optionally, the acquiring the first trend of change of the positive evaluation specifically includes:

acquiring release time stamps of the positive evaluations;

according to the release time stamps, sequencing the active evaluations according to a time sequence to form a time sequence, wherein each time point corresponds to at least one active evaluation;

and analyzing the number of positive evaluations of each time point of the time sequence to generate the first change trend.

By adopting the technical scheme, firstly, the time sequence of the positive evaluation is constructed by acquiring the release time stamps and sorting the release time stamps according to time, and the change of the positive evaluation along with time is clearly presented. This enables the time distribution of user ratings to be captured intuitively, thereby tracking the trend of ratings. Next, by analyzing the time series, a first trend of change in positive evaluation is generated. The change trend reflects the evolution of the positive evaluation quantity along with time, and can help enterprises to more comprehensively know the evaluation trend of users on the automobile brands. For example, if the number of ratings is in a gradual trend, this may indicate that the new media operation activity has a positive effect, causing the user to participate actively and feedback.

Optionally, the determining the second evaluation increasing speed based on the second variation trend specifically includes:

determining a preset duration during which the new media operation activity is implemented;

calculating the second evaluation increasing speed within the preset time length, specifically by the following formula:

;

wherein N is the second rate of increase, β _i X is the coefficient of the linear item corresponding to the ith time point in the preset time length _i For the number of positive evaluations corresponding to the ith time point in the preset time period, delta _i And T is the preset duration, wherein the error term corresponds to the ith time point in the preset duration.

By adopting the technical scheme, in the multiple linear regression model, the parameters of the coefficient model of the linear term represent the influence of the number of positive evaluations at each time point on the increasing speed of the second evaluation. The coefficients of these linear terms are estimated by minimizing the sum of squares of the residuals. Error terms are random parts of the model that cannot be interpreted, representing the differences between the model and the actual observations due to not taking into account all possible influencing factors. The error term is present in order to make the model more flexible, adapting to complex changes in the real world. By minimizing the sum of squares of the residuals, the parameters of the model are estimated, optimizing the fit of the model to the observations. Analysis of the residuals may help verify assumptions of the model, such as the normality, co-variance, etc. of the errors. The presence of the error term means that the model cannot fully predict the change in the second evaluation increase rate, so the uncertainty of the error term can be evaluated by analysis of the residual.

In a second aspect of the present application, a new media operation effect monitoring device for an automobile based on big data is provided, including an acquisition module, a judgment module, a processing module and a recording module, where:

the acquisition module is used for extracting real-time evaluation contents aiming at a preset automobile brand on a webpage according to a preset mode;

the judging module is used for judging whether a plurality of pre-stored first evaluation contents of a preset database exist first evaluation contents which are the same as the real-time evaluation contents, if the first evaluation contents which are the same as the real-time evaluation contents exist in the plurality of first evaluation contents, the real-time evaluation contents are determined to be positive evaluation, and the first evaluation contents are pre-stored positive evaluation contents;

the acquisition module is used for acquiring a first change trend of the positive evaluation, wherein the first change trend is one of an evaluation quantity increasing trend, an evaluation quantity stabilizing trend and an evaluation quantity reducing trend;

the processing module is configured to determine, during implementation of a new media operation activity for the preset brand of automobile, a second trend of change of the aggressive evaluation, where the second trend of change is one of the evaluation amount increasing trend, the evaluation amount stabilizing trend, and the evaluation amount decreasing trend;

The recording module is configured to record an operation effect of the new media operation activity as a first operation effect if it is determined that the first variation trend is the stable evaluation number trend or the decreasing evaluation number trend, and the second variation trend is the increasing evaluation number trend, where the first operation effect is an effect of increasing the positive evaluation number.

Optionally, the acquiring module is configured to directionally acquire a plurality of first web content, where the first web content is web content of an automobile related website;

the judging module is used for screening at least one second webpage content from the plurality of first webpage contents, wherein the second webpage content is related to the preset automobile brand;

the processing module is used for extracting text content from at least one second webpage content to obtain a plurality of preset evaluation contents, wherein the preset evaluation contents are text evaluation contents related to the preset automobile brands;

the judging module is used for judging whether first evaluation contents or second evaluation contents which are the same as the preset evaluation contents exist in a plurality of first evaluation contents and a plurality of second evaluation contents which are pre-stored in the preset database, wherein the second evaluation contents are pre-stored negative evaluation contents;

The recording module is configured to determine that the preset evaluation content is the real-time evaluation content if there is a first evaluation content or a second evaluation content that is the same as the preset evaluation content in the plurality of first evaluation contents and the plurality of second evaluation contents.

Optionally, the recording module is configured to record the operation effect as a second operation effect if it is determined that the first variation trend is the stable trend of the evaluation number or the increasing trend of the evaluation number, and the second variation trend is the decreasing trend of the evaluation number, where the second operation effect is an effect of reducing the number of active evaluations.

Optionally, the recording module is configured to record the operation effect as a third operation effect if it is determined that the first variation trend is the evaluation number stabilizing trend, the second variation trend is the evaluation number stabilizing trend, or if it is determined that the first variation trend is the evaluation number reducing trend, the second variation trend is the evaluation number reducing trend, and the third operation effect is an effect of stabilizing and actively directing the evaluation number.

Optionally, if the processing module is configured to determine that the first trend of change is the trend of increasing the estimated quantity, and the second trend of change is the trend of increasing the estimated quantity, determine a first rate of increase of the estimated quantity based on the first trend of change, and determine a second rate of increase of the estimated quantity based on the second trend of change, where the first rate of increase of the estimated quantity is the rate of increase of the estimated quantity before the new media operation activity is implemented, and the second rate of increase of the estimated quantity is the rate of increase of the estimated quantity during the new media operation activity is implemented;

The judging module is configured to judge whether the second evaluation increasing speed is greater than the first evaluation increasing speed, and if the second evaluation increasing speed is greater than the first evaluation increasing speed, record that the operation effect of the new media operation activity is the first operation effect.

Optionally, the acquiring module is configured to acquire a release timestamp of each positive evaluation;

the processing module is used for sorting the active evaluations according to the issuing time stamps and time sequence to form a time sequence, and each time point corresponds to at least one active evaluation;

the processing module is used for analyzing the number of the positive evaluations of each time point of the time sequence and generating the first change trend.

Optionally, the recording module is configured to determine a preset duration during implementation of the new media operation activity;

the processing module is configured to calculate the second evaluation increasing speed within the preset duration, specifically by the following formula:

;

In a third aspect the present application provides an electronic device comprising a processor, a memory for storing instructions, a user interface and a network interface, both for communicating with other devices, the processor being for executing the instructions stored in the memory to cause the electronic device to perform a method as claimed in any one of the preceding claims.

In a fourth aspect of the present application, there is provided a computer readable storage medium storing instructions that, when executed, perform a method as claimed in any one of the preceding claims.

In summary, one or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:

and acquiring real-time evaluation of a user on a preset automobile brand during implementation of the new media operation activity, and realizing evaluation and monitoring of the new media operation effect by combining pre-stored evaluation contents in a preset database. Firstly, by extracting real-time evaluation contents aiming at automobile brands on a webpage, judging whether the real-time evaluation contents are matched with prestored positive evaluation contents in a preset database. If there is a match, i.e., the real-time evaluation content is the same as the pre-stored aggressive evaluation content, the real-time evaluation content is determined to be an aggressive evaluation. Next, a first trend of change positively toward evaluation, that is, a trend of increase, stabilization, or decrease in the number of evaluation is analyzed. During the new media operation campaign, a second trend of change towards the rating, i.e. increasing, stabilizing or decreasing trend of the number of ratings, is further determined. If the first change trend is that the evaluation number is stable or reduced, and the second change trend is that the evaluation number is increased, the operation effect of the new media operation activity is recorded to reach the first operation effect, namely, the positive evaluation number is successfully increased. The technical scheme has the advantages that the evaluation of the automobile brands can be captured from the real-time feedback of the user, and the emotion tendencies of the feedback of the user can be judged by comparing the positive evaluation in the preset database. By analyzing the change trend of the evaluation quantity, the attitude change of the user to the preset automobile brand can be comprehensively considered, and then the effect of the new media operation activity can be evaluated.

Drawings

Fig. 1 is a schematic flow chart of a method for monitoring an operation effect of a new media of an automobile based on big data, which is disclosed in an embodiment of the present application;

fig. 2 is a schematic structural diagram of an automotive new media operation effect monitoring device based on big data according to an embodiment of the present application;

fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Reference numerals illustrate: 201. an acquisition module; 202. a judging module; 203. a processing module; 204. a recording module; 301. a processor; 302. a communication bus; 303. a user interface; 304. a network interface; 305. a memory.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present application, but not all embodiments.

In the description of embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described herein as "such as" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "or" for example "is intended to present related concepts in a concrete fashion.

In the description of the embodiments of the present application, the term "plurality" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating an indicated technical feature. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

The embodiment discloses a method for monitoring the operation effect of new media of an automobile based on big data, referring to fig. 1, comprising the following steps S110-S150:

s110, extracting real-time evaluation contents aiming at a preset automobile brand on the webpage according to a preset mode.

The method for monitoring the operation effect of the new media of the automobile based on the big data is applied to a server, and the server comprises but is not limited to electronic equipment such as a mobile phone, a tablet personal computer, wearable equipment, a PC (Personal Computer ) and the like, and can also be a background server for running the method for monitoring the operation effect of the new media of the automobile based on the big data. The server may be implemented as a stand-alone server or as a server cluster composed of a plurality of servers.

Firstly, selecting some websites related to automobiles, and acquiring webpage content containing automobile brand evaluation by using web crawler tools such as Beautiful Soup, scrapy and the like, wherein crawling behavior is required to be ensured to comply with related regulations and use protocols of websites. And screening information related to the preset automobile brand in the plurality of first webpage contents by utilizing a text analysis technology, and determining at least one second webpage content, namely the webpage content related to the preset automobile brand, by means of keyword matching, entity identification and the like. Text content, including comments, scores, user names, etc., is then extracted from the second web page content, for example, text information may be extracted from the web page using an HTML parsing tool. And filtering by using keywords or phrases, and only reserving comments related to the preset automobile brands to obtain a plurality of preset evaluation contents.

In order to screen out that the preset evaluation content is the first evaluation content, the first evaluation content is positive evaluation content, that is, evaluation on the deviation of the preset automobile brand, for example, "good brand", "good quality" or "purchasing-worthy" and the like. The preset evaluation content is also second evaluation content, and the second evaluation content is pre-stored negative evaluation content, namely, the evaluation on the bias direction of the preset automobile brand, such as 'who buys who regresses' or 'overtake avoidance'. A preset database is required to be established in advance, a large amount of data of the first evaluation content and the second evaluation content are stored in the preset database, the database is required to be updated in real time, and the data of the evaluation content aiming at a preset automobile brand on the Internet is updated and calibrated to be the first evaluation content or the second evaluation content.

Comparing the extracted evaluation content with the evaluation content in a preset database, and judging whether the same or similar content exists or not by adopting a text matching algorithm such as an edit distance algorithm, a cosine similarity algorithm and the like. And judging whether the first evaluation content or the second evaluation content which is the same as the preset evaluation content exists in a plurality of first evaluation contents and a plurality of second evaluation contents in the preset database. And if the content which is the same as the preset evaluation content exists in the first evaluation contents and the second evaluation contents, determining the preset evaluation content as the real-time evaluation content.

And further screening at least one second webpage content related to the preset automobile brand by directionally acquiring a plurality of first webpage contents of the automobile related websites. By directionally acquiring and screening a plurality of webpage contents related to a preset automobile brand, real-time evaluation issued by a user on the Internet can be captured in time, and timeliness of evaluation data is ensured. Then, text content is extracted from the second webpage content to form a plurality of preset evaluation contents, wherein the contents are user evaluation related to preset automobile brands. Judging whether the first evaluation content or the second evaluation content which is the same as the preset evaluation content exists or not by comparing the plurality of first evaluation contents with a plurality of second evaluation contents which are prestored in a preset database, wherein the second evaluation content is preset as negative evaluation. If the same evaluation contents exist, it is determined that these contents are real-time evaluation contents. This process enables efficient extraction and screening of real-time ratings of a user for a particular brand of automobile over the internet.

S120, judging whether a first evaluation content identical to the real-time evaluation content exists in a plurality of pre-stored first evaluation contents of a preset database, and if the first evaluation content identical to the real-time evaluation content exists in the plurality of first evaluation contents, determining that the real-time evaluation content is positive evaluation.

After the real-time evaluation content including the positive and negative evaluations is found in step S110, the positive evaluation needs to be selected from the real-time evaluation content. And comparing each real-time evaluation content with the first evaluation content in the preset database, and judging whether the first evaluation content identical to a certain real-time evaluation content exists in the first evaluation contents. If the first evaluation content which is the same as the real-time evaluation content exists, the real-time evaluation content is determined to be positive evaluation.

S130, acquiring a first change trend of positive evaluation.

The data of the positive rating obtained from the web page typically contains time stamp information, i.e. the date and time point at which the user released the rating. And sorting all the positive evaluations according to the release time stamps of the respective evaluations to form a time-ordered sequence. And forming a time sequence of the sorted aggressive evaluation data, wherein each time point corresponds to at least one aggressive evaluation. This can be achieved by rounding the time stamps to the nearest time unit (e.g. minutes, hours, days), forming a discrete time sequence. Finally, capturing the trend of the evaluation quantity change by using a time sequence analysis method such as moving average, exponential smoothing, trend line fitting and the like, and generating a first change trend, wherein the first change trend is the quantity change trend which is actively evaluated before implementing a new media operation activity aiming at a preset automobile brand, and the first change trend is one of the evaluation quantity increasing trend, the evaluation quantity stabilizing trend and the evaluation quantity reducing trend. Wherein, the number increasing trend is that the number of the evaluation is increased, the number stabilizing trend is that the number of the evaluation is stable and unchanged, and the number decreasing trend is that the number of the evaluation is decreased.

Firstly, by acquiring the release time stamps and sorting the release time stamps according to time, a time sequence of the positive evaluation is constructed, and the change of the positive evaluation along with time is clearly presented. This enables the time distribution of user ratings to be captured intuitively, thereby tracking the trend of ratings. Next, by analyzing the time series, a first trend of change in positive evaluation is generated. The change trend reflects the evolution of the positive evaluation quantity along with time, and can help enterprises to more comprehensively know the evaluation trend of users on the automobile brands. For example, if the number of ratings is in a gradual trend, this may indicate that the new media operation activity has a positive effect, causing the user to participate actively and feedback.

S140, determining a second trend of change in aggressively-oriented evaluation during implementation of a new media operation activity for a preset car brand.

During the execution of the new media operation activity for the preset brand of automobile by the enterprise, the second variation trend is calculated according to the first variation trend calculation method of the positive evaluation in step S130. The second trend, that is, the trend of the number of positive evaluations during the implementation of a new media operation activity for a preset brand of automobile, is one of an evaluation number increasing trend, an evaluation number stabilizing trend, and an evaluation number decreasing trend.

And S150, if the first change trend is determined to be the stable evaluation number trend or the reduced evaluation number trend, and the second change trend is determined to be the increasing evaluation number trend, recording the operation effect of the new media operation activity to achieve the first operation effect.

Before the new media operation activity is implemented, if the evaluation amount decreasing trend is actively presented to the first change trend of the evaluation, and during the new media operation activity is implemented, the evaluation amount increasing trend is actively presented to the second change trend of the evaluation. Or if the first trend of the rating is positively presented with a stable trend of the number of ratings, and the second trend of the rating is positively presented with an increasing trend of the number of ratings during the implementation of a new media operation activity. The novel media operation activity is shown to play a certain role, so that friendly evaluation on the Internet aiming at preset automobile brands is increased. The server further records the operation effect of the new media operation activity to achieve a first operation effect, i.e. an effect of increasing the number of positive evaluation.

By adopting the technical scheme, the real-time evaluation of the user on the preset automobile brand is obtained during the implementation of the new media operation activity, and the evaluation and monitoring of the new media operation effect are realized by combining the pre-stored evaluation content in the preset database. Firstly, by extracting real-time evaluation contents aiming at automobile brands on a webpage, judging whether the real-time evaluation contents are matched with prestored positive evaluation contents in a preset database. If there is a match, i.e., the real-time evaluation content is the same as the pre-stored aggressive evaluation content, the real-time evaluation content is determined to be an aggressive evaluation. Next, a first trend of change positively toward evaluation, that is, a trend of increase, stabilization, or decrease in the number of evaluation is analyzed. During the new media operation campaign, a second trend of change towards the rating, i.e. increasing, stabilizing or decreasing trend of the number of ratings, is further determined. If the first change trend is that the evaluation number is stable or reduced, and the second change trend is that the evaluation number is increased, the operation effect of the new media operation activity is recorded to reach the first operation effect, namely, the positive evaluation number is successfully increased. The technical scheme has the advantages that the evaluation of the automobile brands can be captured from the real-time feedback of the user, and the emotion tendencies of the feedback of the user can be judged by comparing the positive evaluation in the preset database. By analyzing the change trend of the evaluation quantity, the attitude change of the user to the preset automobile brand can be comprehensively considered, and then the effect of the new media operation activity can be evaluated. The method provides an operable effect evaluation mechanism for new media operation of the automobile brand by combining real-time user feedback and a preset positive evaluation standard, and is helpful for more comprehensively and real-time understanding the user satisfaction and brand image change, so that the operation strategy is timely adjusted and optimized.

Further, if the first variation trend is determined to be the stable evaluation number trend or the increasing evaluation number trend, and the second variation trend is determined to be the decreasing evaluation number trend, the recorded operation effect is a second operation effect, and the second operation effect is an effect of decreasing the positive evaluation number.

Before the new media operation activity is implemented, if the evaluation amount increasing trend is actively presented to the first change trend of the evaluation, and during the new media operation activity is implemented, the evaluation amount decreasing trend is actively presented to the second change trend of the evaluation. Or if the first trend of the rating is positively presented with a stable trend of the number of ratings, and the second trend of the rating is positively presented with a decreasing trend of the number of ratings during the implementation of a new media operation activity. Indicating that the new media operation activity may not play a positive role or otherwise affect the public praise of the preset car brand, so that the friendly evaluation on the internet for the preset car brand is reduced. The server further records the operation effect of the new media operation activity to achieve a second operation effect, and the second operation effect is an effect of reducing the number of positive evaluation.

Further, if the first change trend is determined to be the evaluation quantity stable trend, the second change trend is determined to be the evaluation quantity stable trend, or if the first change trend is determined to be the evaluation quantity reduction trend, the second change trend is determined to be the evaluation quantity reduction trend, the recorded operation effect is a third operation effect, and the third operation effect is an effect of stabilizing and actively evaluating the quantity.

Before the new media operation activity is implemented, if the first variation trend of the rating is actively presented with the rating quantity stabilizing trend, and during the new media operation activity is implemented, the second variation trend of the rating is actively presented with the rating quantity stabilizing trend. Or if the first trend of the rating is positively presented with a reduced number of ratings, while the second trend of the rating is still positively presented with a reduced number of ratings during the implementation of the new media operation campaign. The new media operation activity is shown to play a slight role or is shown to not play a role, so that friendly evaluation on the internet for a preset automobile brand is kept stable, namely, the number is increased or not reduced. And the server records the operation effect of the new media operation activity to achieve a third operation effect, and the third operation effect is the effect of stabilizing and actively evaluating the quantity.

Further, if the first trend of change of the aggressiveness towards the rating before the new media operation activity is implemented presents a trend of increasing the number of ratings, and the second trend of change of the aggressiveness towards the rating also presents a trend of increasing the number of ratings during the implementation of the new media operation activity, it is necessary to further compare the number increase rate of the aggressiveness towards before and after the implementation of the new media operation activity to determine the effect of the new media operation activity. First, a first rate of increase in the number of active evaluations before a new media operation is performed and a second rate of increase in the number of active evaluations during the new media operation are calculated.

The method comprises the steps of respectively intercepting preset time periods before and after implementing new media operation activities, calculating a first evaluation increasing speed and a second evaluation increasing speed, and calculating the second evaluation increasing speed through the following formula:

;

wherein N is the second rate of increase, β _i For the coefficient of the linear item corresponding to the ith time point in the preset time length, X _i For the number delta of positive evaluation corresponding to the ith time point in the preset time period _i And T is the preset duration, wherein the error term corresponds to the ith time point in the preset duration.

In a multiple linear regression model, the coefficients of the linear terms and the estimation of the error term are typically obtained by the least squares method. The least squares method is an optimization method for fitting model parameters, with the goal of minimizing the sum of squares of residuals between actual observations and model predictions. Wherein, in the multiple linear regression model, parameters of the coefficient model of the linear term represent the influence of the number of positive-going evaluations at each time point on the second evaluation increasing speed. The coefficients of these linear terms are estimated by minimizing the sum of squares of the residuals. Error terms are random parts of the model that cannot be interpreted, representing the differences between the model and the actual observations due to not taking into account all possible influencing factors. The error term is present in order to make the model more flexible, adapting to complex changes in the real world. By minimizing the sum of squares of the residuals, the parameters of the model are estimated, optimizing the fit of the model to the observations. Analysis of the residuals may help verify assumptions of the model, such as the normality, co-variance, etc. of the errors. The presence of the error term means that the model cannot fully predict the change in the second evaluation increase rate, so the uncertainty of the error term can be evaluated by analysis of the residual.

X _i And X is _i+1 As an interaction term between the number of positive evaluations per time point, or a higher order term of the number of positive evaluations per time point. The interaction term allows to consider in the model the interaction effect between the number of positive evaluations at two or more each time point. For example, if there are two positive evaluation numbers X at each time point ₁ And X ₂ Interaction item X ₁ ×X ₂ Can capture X ₁ And X ₂ The joint effect between them enables the model to better fit the data.

The first evaluation increasing speed calculation method is consistent with the second evaluation increasing speed principle. After the first evaluation increasing speed and the second evaluation increasing speed are obtained, the magnitude relation between the first evaluation increasing speed and the second evaluation increasing speed is compared. If the second evaluation increasing speed is larger than the first evaluation increasing speed, recording the operation effect of the new media operation activity as reaching the first operation effect. And if the second evaluation increasing speed is equal to the first evaluation increasing speed, recording the operation effect of the operation activity of the new media as reaching the second operation effect. If the second evaluation increasing speed is smaller than the first evaluation increasing speed, the operation effect of the new media operation activity is recorded to reach the third operation effect.

Considering the change speed of the evaluation quantity, the effect of the new media operation activity on promoting the positive evaluation is highlighted. When a new media operation activity is performed, if the rate of increase in the number of ratings is significantly higher than before the operation activity, this indicates that the operation activity successfully promotes the increasing potential for users to actively rate. This not only demonstrates the positive effect of the operational activity, but also emphasizes its contribution in accelerating the user's positive feedback.

In a second aspect of the present application, an apparatus for monitoring a new media operation effect of an automobile based on big data is provided, referring to fig. 2, including an acquisition module 201, a judgment module 202, a processing module 203, and a recording module 204, where:

the acquiring module 201 is configured to extract real-time evaluation content for a preset automobile brand on a web page according to a preset mode;

the judging module 202 is configured to judge whether a first evaluation content identical to a real-time evaluation content exists in a plurality of pre-stored first evaluation contents in a preset database, and if the first evaluation content identical to the real-time evaluation content exists in the plurality of first evaluation contents, determine that the real-time evaluation content is a positive evaluation, the first evaluation content is a pre-stored positive evaluation content;

An obtaining module 201, configured to obtain a first trend of positive evaluation, where the first trend of positive evaluation is one of an evaluation number increasing trend, an evaluation number stabilizing trend, and an evaluation number decreasing trend;

a processing module 203, configured to determine, during implementation of a new media operation activity for a preset car brand, a second trend of change towards evaluation, where the second trend of change is one of an evaluation number increasing trend, an evaluation number stabilizing trend, and an evaluation number decreasing trend;

the recording module 204 is configured to record an operation effect of the new media operation activity to achieve a first operation effect, where the first operation effect is an effect of increasing the number of active evaluations, if the first change trend is determined to be a stable number of evaluations or a decreasing number of evaluations, and the second change trend is determined to be an increasing number of evaluations.

In a possible implementation manner, the obtaining module 201 is configured to directionally obtain a plurality of first web content, where the first web content is web content of an automobile related website;

the judging module 202 is configured to screen at least one second web page content from the plurality of first web page contents, where the second web page content is a web page content related to a preset automobile brand;

The processing module 203 is configured to extract text content from at least one second web page content, so as to obtain a plurality of preset evaluation contents, where the preset evaluation contents are text evaluation contents related to a preset automobile brand;

the judging module 202 is configured to judge whether a first evaluation content or a second evaluation content identical to a preset evaluation content exists in a plurality of first evaluation contents and a plurality of second evaluation contents pre-stored in a preset database, where the second evaluation content is a pre-stored negative evaluation content;

the recording module 204 is configured to determine that the preset evaluation content is a real-time evaluation content if the first evaluation content or the second evaluation content that is the same as the preset evaluation content exists in the plurality of first evaluation contents and the plurality of second evaluation contents.

In one possible implementation manner, the recording module 204 is configured to record the operation effect as a second operation effect if it is determined that the first variation trend is a stable evaluation number trend or an increasing evaluation number trend, and the second variation trend is a decreasing evaluation number trend, where the second operation effect is an effect of decreasing the positive evaluation number.

In one possible implementation manner, the recording module 204 is configured to record the operation effect as a third operation effect if it is determined that the first variation trend is the evaluation number stabilizing trend, the second variation trend is the evaluation number stabilizing trend, or if it is determined that the first variation trend is the evaluation number reducing trend, the second variation trend is the evaluation number reducing trend, and the third operation effect is an effect of stabilizing the positive evaluation number.

In a possible implementation manner, if the processing module 203 is configured to determine that the first variation trend is an evaluation number increasing trend, and the second variation trend is an evaluation number increasing trend, determine a first evaluation increasing speed based on the first variation trend, and determine a second evaluation increasing speed based on the second variation trend, where the first evaluation increasing speed is a positive increasing speed of the number of evaluations before implementing the new media operation activity, and the second evaluation increasing speed is a positive increasing speed of the number of evaluations during implementing the new media operation activity;

the judging module 202 is configured to judge whether the second evaluation increasing speed is greater than the first evaluation increasing speed, and if the second evaluation increasing speed is greater than the first evaluation increasing speed, record the operation effect of the new media operation activity as reaching the first operation effect.

In a possible implementation manner, the obtaining module 201 is configured to obtain a release timestamp of each positive evaluation;

the processing module 203 is configured to sort the active evaluations according to a time sequence according to the release timestamps, so as to form a time sequence, where each time point corresponds to at least one active evaluation;

The processing module 203 is configured to analyze the number of positive evaluations at each time point of the time sequence, and generate a first variation trend.

In one possible implementation, the recording module 204 is configured to determine a preset duration during which the new media operation activity is implemented;

the processing module 203 is configured to calculate a second evaluation increasing speed within a preset duration, specifically by the following formula:

;

It should be noted that: in the device provided in the above embodiment, when implementing the functions thereof, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be implemented by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the embodiments of the apparatus and the method provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the embodiments of the method are detailed in the method embodiments, which are not repeated herein.

The embodiment also discloses an electronic device, referring to fig. 3, the electronic device may include: at least one processor 301, at least one communication bus 302, a user interface 303, a network interface 304, at least one memory 305.

Wherein the communication bus 302 is used to enable connected communication between these components.

The user interface 303 may include a Display screen (Display), a Camera (Camera), and the optional user interface 303 may further include a standard wired interface, and a wireless interface.

The network interface 304 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.

Wherein the processor 301 may include one or more processing cores. The processor 301 utilizes various interfaces and lines to connect various portions of the overall server, perform various functions of the server and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and invoking data stored in the memory 305. Alternatively, the processor 301 may be implemented in hardware in at least one of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 301 may integrate one or a combination of several of a central processing unit 301 (Central Processing Unit, CPU), an image processing unit 301 (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 301 and may be implemented by a single chip.

The Memory 305 may include a random access Memory 305 (Random Access Memory, RAM) or a Read-Only Memory 305 (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). Memory 305 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 305 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-described respective method embodiments, etc.; the storage data area may store data or the like involved in the above respective method embodiments. Memory 305 may also optionally be at least one storage device located remotely from the aforementioned processor 301. As shown, an operating system, a network communication module, a user interface 303 module, and an application program of the new media operation effect monitoring method for an automobile based on big data may be included in the memory 305 as one type of computer storage medium.

In the electronic device shown in fig. 3, the user interface 303 is mainly used for providing an input interface for a user, and acquiring data input by the user; and the processor 301 may be configured to invoke an application in the memory 305 that stores big data based methods of monitoring the operation of new media of a car, which when executed by the one or more processors 301, causes the electronic device to perform the method as in one or more of the embodiments described above.

It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.

In the several embodiments provided herein, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as a division of units, merely a division of logic functions, and there may be additional divisions in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory 305. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory 305, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned memory 305 includes: various media capable of storing program codes, such as a U disk, a mobile hard disk, a magnetic disk or an optical disk.

The foregoing is merely exemplary embodiments of the present disclosure and is not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.

Claims

1. The method for monitoring the operation effect of the new media of the automobile based on the big data is characterized by comprising the following steps:

2. The method for monitoring the operation effect of the new media of the automobile based on big data as claimed in claim 1, wherein the extracting the real-time evaluation content of the webpage aiming at the preset automobile brand according to the preset mode specifically comprises:

3. The big data based method of monitoring new media operation effects of an automobile of claim 1, wherein after determining the second trend of positive rating during implementation of new media operation activities for the preset automobile brand, the method further comprises:

4. The big data based method of monitoring new media operation effects of an automobile of claim 1, wherein after determining the second trend of positive rating during implementation of new media operation activities for the preset automobile brand, the method further comprises:

5. The big data based method of monitoring new media operation effects of an automobile of claim 1, wherein after determining the second trend of positive rating during implementation of new media operation activities for the preset automobile brand, the method further comprises:

6. The method for monitoring new media operation effects of an automobile based on big data according to claim 1, wherein the obtaining the first trend of change of the positive evaluation specifically includes:

acquiring release time stamps of the positive evaluations;

7. The method for monitoring the operation effect of the new media of the automobile based on big data according to claim 5, wherein the determining the second evaluation increasing speed based on the second change trend specifically comprises:

;

wherein N is the second rate of increase, β _i X is the coefficient of the linear item corresponding to the ith time point in the preset time length _i Corresponding to the ith time point in the preset time lengthThe number of positive evaluations, δ _i And T is the preset duration, wherein the error term corresponds to the ith time point in the preset duration.

8. The device for monitoring the operation effect of the new media of the automobile based on big data is characterized by comprising an acquisition module (201), a judgment module (202), a processing module (203) and a recording module (204), wherein:

the acquisition module (201) is used for extracting real-time evaluation content aiming at a preset automobile brand on a webpage according to a preset mode;

The judging module (202) is configured to judge whether a plurality of pre-stored first evaluation contents in a preset database have first evaluation contents identical to the real-time evaluation contents, and if the plurality of first evaluation contents have first evaluation contents identical to the real-time evaluation contents, determine that the real-time evaluation contents are positive evaluation contents, where the first evaluation contents are pre-stored positive evaluation contents;

the acquisition module (201) is configured to acquire a first variation trend of the positive evaluation, where the first variation trend is one of an evaluation number increasing trend, an evaluation number stabilizing trend, and an evaluation number decreasing trend;

-the processing module (203) for determining, during implementation of a new media operation activity for the preset car brand, a second trend of change of the aggressive rating, the second trend of change being one of the rating number increasing trend, the rating number stabilizing trend and the rating number decreasing trend;

the recording module (204) is configured to record an operation effect of the new media operation activity as a first operation effect if it is determined that the first variation trend is the stable trend of the evaluation number or the decreasing trend of the evaluation number, and the second variation trend is the increasing trend of the evaluation number, where the first operation effect is an effect of increasing the number of active evaluations.

9. An electronic device comprising a processor (301), a memory (305), a user interface (303) and a network interface (304), the memory (305) being adapted to store instructions, the user interface (303) and the network interface (304) being adapted to communicate with other devices, the processor (301) being adapted to execute the instructions stored in the memory (305) to cause the electronic device to perform the method according to any of claims 1-7.

10. A computer readable storage medium storing instructions which, when executed, perform the method of any one of claims 1-7.