JP2019079474A - Site improvement device, site improvement method and site improvement program - Google Patents

Abstract

To provide a site improvement device, a site improvement method and a site improvement program that simply and accurately improve a website.SOLUTION: A site improvement device 10 searches a content, in which a tracking tag collecting information associated with access to a website can be embedded, from the content within the website, inserts the tracking tag into the content in which the tracking tag can be embedded, and collects the information associated with the access to the website. And, the site improvement device 10 collects the information associated with the access to the collected websites, analyzes a tendency of the access to the website from collected data, and presents an action required for improvement of the website as recommendation information according to an analyzed result.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a site improvement apparatus, a site improvement method, and a site improvement program.

  In recent years, with the spread of digital marketing utilizing IT technology, in corporate activities, it has become important to grasp trends in company websites and improve content. As techniques for establishing a website, and grasping and analyzing an access state, there are log aggregation software (for example, Webalizer and the like) of a web server and an access analysis service for the web (for example, Google (registered trademark) Analytics and the like).

  Web access analysis and improvement efforts aimed at increasing the number of accesses to websites require prerequisite knowledge, technical know-how, and human resources to handle these tools. Specifically, it is necessary to set access analysis (install software, embed tracking tag information in content), view tabulated results, and study improvement measures from the results and implement improvements. In addition, after improvement is implemented, in order to evaluate the effect of the measure, review the results of the tabulation and consider the measure that will be the next action, etc. and go through the cycle of PDCA (Plan-Do-Check-Action). We have to go.

JP, 2014-119838, A Unexamined-Japanese-Patent No. 2014-115952 JP, 2013-182602, A

  However, in the conventional method, a person with specialized knowledge collects information on the website and understands the access situation and improvement points of the website, so that the website can not be improved simply and accurately. There was a problem.

  In order to solve the problems described above and achieve the purpose, the site improvement device of the present invention searches the content in the website for embeddable content of a tracking tag that collects information on access to the website. Collecting means for inserting the tracking tag into the embeddable content of the tracking tag and collecting information on access to the website, and information on access to the website collected by the collection means The analysis means for analyzing the tendency of access to the website from the aggregated and aggregated data, and the action required for the improvement of the website is presented as recommendation information according to the result analyzed by the analysis means And means.

  Further, the site improvement method of the present invention is a site improvement method executed by the site improvement apparatus, and from the content in the website, embeddable content of a tracking tag for collecting information related to access to the website. A collecting step of searching, inserting the tracking tag into the embeddable content of the tracking tag, collecting information on access to the website, and access to the website collected by the collecting step The analysis step of aggregating information and analyzing the tendency of access to the website from the aggregated data and presenting the action necessary for the improvement of the website as recommendation information according to the result analyzed by the analysis step And including a presenting step That.

  Also, the site improvement program of the present invention searches the embeddable content of the tracking tag for collecting information related to access to the website from the content in the website, and for the embeddable content of the tracking tag. The collecting step of inserting the tracking tag, collecting information on the access to the website, and aggregating the information on the access to the website collected by the collecting step, from the aggregated data to the website It is characterized by making a computer execute an analysis step of analyzing a tendency of access and a presentation step of presenting an action necessary for improvement of the website as recommendation information according to the result analyzed by the analysis step. .

  According to the present invention, it is possible to improve the website simply and accurately.

FIG. 1 is a block diagram showing a configuration example of the site improvement apparatus according to the first embodiment. FIG. 2 is a diagram showing an example of data stored in the access log storage unit. FIG. 3 is a diagram showing an example of data stored in the total data storage unit. FIG. 4 is a diagram showing an example of data stored in the analysis data storage unit. FIG. 5 is a diagram for explaining tag insertion processing in the site improvement apparatus according to the first embodiment. FIG. 6 is a diagram for explaining analysis processing in the site improvement apparatus according to the first embodiment. FIG. 7 is a diagram for explaining an outline of processing of an analysis AI engine in the site improvement apparatus according to the first embodiment. FIG. 8 is a diagram showing an example of recommendation information presented in the site improvement apparatus according to the first embodiment. FIG. 9 is a view showing a screen example of an analysis result output in the site improvement apparatus according to the first embodiment. FIG. 10 is a diagram showing an example of analysis results visualized in the site improvement apparatus according to the first embodiment. FIG. 11 is a diagram for explaining the flow of a series of processes of web analysis in the site improvement apparatus according to the first embodiment. FIG. 12 is a diagram for explaining an example of analysis results visualized by web analysis in the site improvement apparatus according to the first embodiment. FIG. 13 is a diagram for explaining the flow of a series of processes of mail analysis in the site improvement apparatus according to the first embodiment. FIG. 14 is a diagram for explaining an example of an analysis result visualized by mail analysis in the site improvement apparatus according to the first embodiment. FIG. 15 is a diagram for explaining cooperation of analysis engines in the site improvement apparatus according to the first embodiment. FIG. 16 is a flowchart showing an example of the overall processing flow in the site improvement apparatus according to the first embodiment. FIG. 17 is a diagram illustrating a computer that executes a site improvement program.

  Hereinafter, embodiments of a site improvement apparatus, a site improvement method, and a site improvement program according to the present application will be described in detail based on the drawings. In addition, the site improvement apparatus, the site improvement method, and the site improvement program which concern on this application are not limited by this embodiment.

First Embodiment
In the following embodiments, the configuration of the site improvement apparatus 10 according to the first embodiment and the flow of processing of the site improvement apparatus 10 will be described in order, and finally the effects of the first embodiment will be described.

[Configuration of site improvement device]
First, the configuration of the site improvement apparatus 10 will be described using FIG. FIG. 1 is a block diagram showing a configuration example of the site improvement apparatus according to the first embodiment. The site improvement apparatus 10 is a server apparatus that supports work required for access analysis of a website and site improvement. Specifically, the site improvement apparatus 10 has a function for automatically executing a series of processes such as collection, aggregation, visualization, analysis of content necessary for access analysis, and improvement of content.

  As shown in FIG. 1, the site improvement apparatus 10 includes a communication processing unit 11, a control unit 12, and a storage unit 13. The processing of each part of the site improvement apparatus 10 will be described below.

  The communication processing unit 11 controls communication regarding various information. For example, the communication processing unit 11 transmits and receives data to and from a site visitor or a terminal of a server administrator who manages a website.

  The storage unit 13 stores data and programs necessary for various processes performed by the control unit 12. Especially as closely related to the present invention, the access log storage unit 13a, the total data storage unit 13b, and the analysis data storage unit It has 13c. For example, the storage unit 13 is a semiconductor memory device such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk.

  The access log storage unit 13a stores information related to access to a website and social information. For example, as illustrated in FIG. 2, the access log storage unit 13a, as information related to access to a website, “time” when the website is accessed, “IP address” of the accessed terminal, and where access is made The "access source" indicating the presence, the "access location" indicating the prefecture of the accessed terminal, and the "browser information" including the OS, language, browser-related information and resolution of the accessed terminal are stored in association with each other. The information stored in the access log storage unit 13a is updated each time access to a web site occurs.

  The access log storage unit 13a will be described specifically with reference to the example shown in FIG. 2. The access log storage unit 13a stores the time "12:00:01", the IP address "A", the access source "search engine", and the access location "Tokyo". And browser information “OS: B...” Are stored in association with each other. This means that the terminal in Tokyo whose IP address is "A" has access to the website at time "12:00:01" via the search engine using the browser "OS: B ..." I mean.

  In addition, the access log storage unit 13a stores, as social data, transition of the number of searches of analysis words in social media, related search words searched along with analysis words in social media, and related news. Here, the social data is not limited to data on SNS (Social Networking Service) but means various data such as search tendency and news on the Internet. Also, the analysis word is a word related to a website, and is a word to be analyzed which is set by the server administrator or automatically extracted from the content by the system.

  The aggregated data storage unit 13 b stores aggregated data which is a result of aggregating information on access to a website and social data. For example, as illustrated in FIG. 3, the aggregated data storage unit 13 b associates the “date and time” for which the access count is to be calculated with the “access count” that indicates the total access count for the website at the target date and time. Remember. In the example of FIG. 3, although the case where the total data storage part 13b stores the total result which totaled the access number of a unit of 1 day is illustrated, it is not limited to this, For example, in the access to a website The number of accesses for each IP address of the visitor, which is the IP address of the transmission source, may be stored, or the access for each area (for example, prefectures etc.) estimated using GeoIP corresponding to the IP address of the visitor The number may be stored. Further, the number of accesses may be stored for each piece of access destination information (for example, URL, IP address, FQDN, etc.). Although not shown in the figure, the total data storage unit 13 b also stores statistical data of social data. For example, the number of searches of analysis words in units of one day, the ratio of related search words, and the like are stored.

  The analysis data storage unit 13c stores recommendation data generated by the analysis unit 12b described later. For example, as illustrated in FIG. 4, the analysis data storage unit 13 c is provided after the improvement based on the recommendation based on the “date and time of generation of the recommendation”, the “recommend statement” indicating the content of the recommendation presented to the user It matches and memorizes a "score". Although the score is manually assigned according to the improved access tendency based on the recommendation, it may be automatically assigned according to the number of accesses.

  The control unit 12 has a program that defines various processing procedures and the like, and an internal memory for storing required data, and executes various processing by these, and particularly as closely related to the present invention, It has a collection unit 12a, an analysis unit 12b, a recommendation presentation unit 12c, and an analysis result output unit 12d. Here, the control unit 12 is an electronic circuit such as a central processing unit (CPU) or a micro processing unit (MPU) or an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). The processing of each unit of the control unit 12 will be described below.

  The collecting unit 12a searches the embeddable content of the tracking tag for collecting information on access to the website from the content in the website, inserts the tracking tag into the embeddable content of the tracking tag, and In addition to aggregating information about site access, social data is collected from the outside.

Here, tag insertion processing for inserting a tracking tag into embeddable content of a tracking tag will be described with reference to FIG. FIG. 5 is a diagram for explaining tag insertion processing in the site improvement apparatus according to the first embodiment. For example, the collection unit 12a searches the web content area for an html file that is an embeddable file of a tracking tag, and adds the following tracking tag (html code) to the html file searched. In addition, although the html file is mentioned as an example of processing object, it is not limited to this, for example, it is good also considering dynamic files, such as CGI (Common Gateway Interface), as processing object.
<script src = "/ ControlPanel / static / js / wa.js"></script><noscript><img src = "/ wa / analysis.php? id = 1" style = "border: 0;">< / noscript>

  Here, as a method for determining the html file which is an embeddable file of the tracking tag, for example, the collection unit 12a may use a rule (with <html> tag, presence of </ head> tag, etc.) or machine learning (file The html likeness is judged by the classifier from the feature quantity of. In addition, the collection unit 12a periodically checks the target directory or file to detect addition or change of the file, and self-repairs the tracking tag. The collection unit 12a may associate not only the access data but also the data necessary for digital marketing with the access data.

  Then, the collection unit 12a stores the access data collected by the tracking tag in the access log storage unit 13a. For example, the collection unit 12a calls a log acquisition API, acquires PV (Page View), Referrer, User Agent, and page transition information, and stores the page transition information in the access log storage unit 13a. In addition, the collection unit 12a, as social data, for example, changes in the number of searches of analysis words in social media, the number of searches of related search words searched along with analysis words in social media, and related news related to analysis words Are collected and stored in the access log storage unit 13a. For example, the collection unit 12a acquires the search trend, the related search word, and the related news based on the analysis keyword, and stores the search trend, the related news, and the like in the access log storage unit 13a.

  Further, for example, when a site visitor makes an inquiry by using a form mail, the collecting unit 12a may analyze a mail sentence based on a keyword to grasp an inquiry trend. The collection unit 12a can grasp trends in topic units by acquiring related words related to keywords by natural language processing as analysis of mail text. The mail analysis process will be described later with reference to FIGS. 13 and 14.

  Returning to the explanation of FIG. 1, the analysis unit 12b counts information on access to the website and social data by the collection unit 12a, and the tendency of access to the website from the summarized data and related information on the social media Comparative analysis of the trend of Specifically, the analysis unit 12b analyzes the tendency of access to the website using the learned model generated as a result of machine learning. For example, the analysis unit 12b extracts a predetermined pattern using the analysis AI engine, which is a learned model for extracting a predetermined pattern, using the data collected by the collection unit 12a as an input, and extracts the predetermined pattern. Generate recommendation information to Although there is no limitation on the analysis method of AI, it is preferable to use machine learning, use past access tendency data as learning data, and use a learning model to make the learner learn and predict the future number of accesses Create Also, as the learning device, for example, known supervised learning (for example, linear regression or SVM) may be used. The recommendation information may be generated by a unique logic or the like using a threshold for the number of accesses without using a learned model. The original logic is, for example, based on the knowledge of the analysis method, to recommend the change rate if the collected data time-series change rate changes beyond a preset threshold (for example, 150% or more).

  Here, analysis processing in the site improvement apparatus 10 will be described using FIG. FIG. 6 is a diagram for explaining analysis processing in the site improvement apparatus according to the first embodiment. As illustrated in FIG. 6, for example, as a web analysis, the analysis unit 12b designates a processing target period and a processing granularity as a query, acquires data from the total data storage unit 13b, and is necessary for output and analysis of analysis results Convert to a format that will be passed to the analysis AI engine. Here, in the analysis AI engine, search trend analysis rules, visitor analysis rules, page transition analysis rules and access trend analysis rules are set for web analysis, and related word extraction rules and relations for mail analysis. Word analysis rules are set.

  Then, the analysis unit 12b calculates a change rate, an abnormal value, and a difference from input data, performs extraction processing of predetermined patterns, determination of similarity, classification processing, and stores analysis results in the analysis data storage unit 13c. Thereafter, the data stored in the analysis data storage unit 13c is acquired by a query specifying a target period, and visualized using a visualization library. Here, the predetermined pattern includes various patterns such as an access pattern, a trend pattern, and a visitor attribute pattern, and it is possible to appropriately set and change what pattern to extract.

  Here, the outline of the process of the analysis AI engine in the site improvement apparatus will be described with reference to FIG. FIG. 7 is a diagram for explaining an outline of processing of an analysis AI engine in the site improvement apparatus according to the first embodiment. As illustrated in FIG. 7, in the analysis AI engine, a data wrapper, which is a common interface for acquiring data from a plurality of data sources, acquires data from inside and outside the site improvement apparatus 10. For example, the data wrapper obtains PV, UU (Unique Users), search transition, visitor environment, feedback, access page ranking, related keyword and visitor area.

  Then, the analysis AI engine combines data from a plurality of data sources and calculates data necessary for the purpose of utilization by the set calculation logic. The calculation method is estimated by technical analysis or machine learning. Subsequently, in the analysis AI engine, the determination logic evaluates the calculation result with a threshold, a category, etc. in line with the purpose. Then, in the analysis AI engine, the use logic performs actions such as output or notification of a recommended statement to the user, change of content, control of a device, and the like.

  Returning to the explanation of FIG. 1, the recommendation presentation unit 12c presents, as recommendation information, an action necessary for improvement of the website according to the result of analysis by the analysis unit 12b. Specifically, the recommendation presentation unit 12c presents the recommendation information generated by the analysis unit 12b. After the improvement based on the recommendation, whether the access tendency has changed may be used as feedback to adjust the accuracy of the recommendation to be higher. For example, after the improvement of the website based on the presented recommendation, as the number of accesses increases, the recommendation is automatically or manually given a high score, and the analysis logic with high score is processed from the next time onwards But let them be applied preferentially.

  Here, an example of the recommendation information will be described with reference to FIG. FIG. 8 is a diagram showing an example of recommendation information presented in the site improvement apparatus according to the first embodiment. As exemplified in FIG. 8, the recommendation statement (described as a recommendation statement in FIG. 8) differs depending on the analysis category and the analysis viewpoint. For example, the case where the analysis category is “analysis of the number of site accesses” and the analysis viewpoint is “trend analysis of the number of accesses to the entire site” will be described as an example.

  As a result of the analysis unit 12 b analyzing the number of site accesses from the viewpoint of trend analysis of the number of accesses to the entire site, if the number of recent accesses is increasing, the recommendation sentence “The number of recent accesses is By placing a link with the highest number of accesses per page and making improvements such as making the link more prominent, the number of accesses can be expected to further increase. Then, the recommendation presentation unit 12 c presents the generated recommendation sentence to the user. Thus, even if there is no expert knowledge or the like, the user can execute improvement of the website referring to the recommended sentence.

  Also, as a result of the analysis unit 12 b analyzing the number of site accesses from the viewpoint of trend analysis of the number of accesses to the entire site, if there is no change in the number of recent accesses, “Recented number of accesses as a recommendation statement” The number of accesses can be expected to increase if the number of pages is further increased or if the number of websites with the highest number of accesses is enhanced. Then, the recommendation presentation unit 12 c presents the generated recommendation sentence to the user.

  In addition, as a result of the analysis unit 12b analyzing the number of site accesses from the viewpoint of trend analysis of the number of accesses to the entire site, if the latest number of accesses is decreasing, it is recommended If the search trend and related search words have a low relative value, you can reset the site analysis word and increase the number of popular words in the website to increase the number of accesses. Generate Then, the recommendation presentation unit 12 c presents the generated recommendation sentence to the user.

  In addition to presenting the recommendation information, the site improvement apparatus 10 may automate the editing of the content and the measurement of the post-editing effects based on the action necessary for the improvement of the site. For example, the recommendation presentation unit 12c may automatically change the content based on the access analysis result as the automatic generation of the content, or to increase the arrival rate of the visitor to the targeted page, the link position in the content may be changed. The page transition may be guided by changing or popping up a banner.

  In addition, the recommendation presentation unit 12 c classifies the content structure into patterns, identifies the structure, changes the content arrangement such as links, banners, pop-ups, etc., and divides the contents according to the profile of the site browser. It may be done (access source area, browser environment, inflow source (access from search site or bookmark, etc.)). Further, for example, the recommendation presentation unit 12c may display information according to the browser characteristics for the site browser and may guide the information, or analyze keywords in the content and add related keywords. The test may be performed with a plurality of patterns from the search site, the effect may be measured, and the content may be changed.

  Returning to the explanation of FIG. 1, the analysis result output unit 12d arranges the tendency of access to a website and the tendency of related information on social media in the same time series from the analysis result analyzed by the analysis unit 12b. Generate a screen and output the screen. For example, the analysis result output unit 12d visualizes in the form of graph or ranking so that the user can intuitively understand the site access state. The analysis result output unit 12d combines the scaling of the time axis and the scale to compare the tendency of access to the website and the tendency of access on the social media, so that comparison can be performed in the same time series on the same screen. Make it

  Here, a screen example of an analysis result will be described with reference to FIG. FIG. 9 is a view showing a screen example of an analysis result output in the site improvement apparatus according to the first embodiment. As illustrated in FIG. 9, the analysis result output unit 12 d cites social data taken from the outside such as news and search trends on the same screen as the information presentation on the site of its own, and presents it in the same time series. For example, in the analysis result output unit 12 d, “transition of the number of accesses” at the top of the screen and “transition of the number of searches” at the bottom of the screen are both data of the “08/24” to “09/21” period, The transition of the number of accesses (the number of searches) on a daily basis is displayed.

  Also, in the example of FIG. 9, as the “trend analysis” analyzing the access tendency of the website, “the transition of the number of accesses” displaying the number of accesses visiting the website and the number of unique users, from where on the user's website "Access source page" to display whether it has been accessed as a percentage (direct access, search engine, other sites), "transition of the number of searches" to display the transition of the number of searches of analysis words set by the user, analysis words set by the user The “relevant search word” for extracting and displaying the word used by the person who searched for the other search and the “related news” for extracting and displaying the news including the analysis word set by the user are displayed.

  Also, although the screen example in FIG. 9 displays "trend analysis", the page trend in which the user analyzes the access trend to the page in the website, or the trend of the visitor accessing the website It is possible to switch to a screen that displays "visitor analysis" to analyze. As illustrated in FIG. 10, the analysis result output unit 12d displays “page access count”, “access upper page”, and “transition status for each page” on the “page analysis” screen. In addition, the analysis result output unit 12 d displays “use device”, “use browser”, “access source area”, “visitor IP ranking” and “visitor Whois” on the “visitor analysis” screen. FIG. 10 is a diagram showing an example of analysis results visualized in the site improvement apparatus according to the first embodiment.

  Further, the analysis result output unit 12d may display not only the screen of the web analysis result but also the screen of the mail analysis result. As exemplified in FIG. 10, the analysis result output unit 12d is a screen of the mail analysis result, which is a “trend analysis” for analyzing a tendency that the analysis word includes the analysis word, and an outline of the mail including the analysis word. It is also possible to display "related mail" and a "participant map" showing a relationship between mail senders and recipients.

  Here, a flow of a series of processing of web analysis will be described with reference to FIG. FIG. 11 is a diagram for explaining the flow of a series of processes of web analysis in the site improvement apparatus according to the first embodiment. As shown in FIG. 11, the site improvement apparatus 10 inserts an analysis tag (tracking tag) required for access analysis into the content in the website (see (1) in FIG. 11) and collects and accesses the access log. It stores in the log storage unit 13a (see (2) in FIG. 11). Subsequently, the site improvement apparatus 10 collects social data such as search tendency and news to be compared with the access analysis data, and stores the social data in the access log storage unit 13a (see (3) in FIG. 11).

  Then, the site improvement apparatus 10 tabulates the data stored in the access log storage unit 13a, formats the data into a format that can be handled by analysis, and stores the data in the tabulated data storage unit 13b (see (4) in FIG. 11). Subsequently, the site improvement apparatus 10 extracts the access pattern (rate of change, abnormal value, difference) and time-series comparison using the data stored in the total data storage unit 13b, and analyzes the analysis result as an analysis data storage unit. A recommendation statement is generated based on the extracted pattern stored in 13c, and the recommendation statement is stored in the analysis data storage unit 13c (see (5) in FIG. 11). Thereafter, the site improvement apparatus 10 acquires the analysis result and the recommendation information stored in the analysis data storage unit 13c, and displays the analysis result and the recommendation information on a GUI (Graphical User Interface) (see (6) in FIG. 11).

  Thus, as shown in FIG. 12, in the site improvement apparatus 10, analysis tags are automatically embedded to count access logs, and external data (social data) is obtained to total external data. Then, the site improvement apparatus 10 analyzes the aggregated data, and on the same screen as the information presentation about the own site, cites social data imported from the outside such as news and search trend, and the user intuitively accesses the site Visualize in graph or ranking format so that you can grasp FIG. 12 is a diagram for explaining an example of analysis results visualized by web analysis in the site improvement apparatus according to the first embodiment.

  Also, the site improvement apparatus 10 presents recommendation information. In the example of FIG. 12, since recommendation information to the effect that an increase in the number of entrances to the site is predicted is presented by the posting of the "recruitment" information, the user is requested to enter content regarding the "recruitment information page" based on the recommendation information. By fulfilling, access to the website can be increased.

  Next, the flow of a series of processes of mail analysis will be described using FIG. FIG. 13 is a diagram for explaining the flow of a series of processes of mail analysis in the site improvement apparatus according to the first embodiment. As shown in FIG. 13, the site improvement apparatus 10 receives in advance the setting input of the keyword when analyzing the mail (see (1) in FIG. 13). Then, the site improvement apparatus 10 acquires the header and the text of the mail exchanged by the user, stores the meta information and the appearance keyword of the mail in the access log storage unit 13a (see (2) in FIG. 13), and the mail log Are stored in the access log storage unit 13a (see (3) in FIG. 13).

  Subsequently, the site improvement apparatus 10 tabulates the data stored in the access log storage unit 13a, shapes the data into a format that can be visualized or analyzed, and stores the converted data in the tabulated data storage unit 13b (see FIG. )reference). Subsequently, the site improvement apparatus 10 performs extraction of keyword appearance patterns (rate of change, abnormal value, difference) and keyword analysis (co-occurrence word extraction, classification) using data stored in the total data storage unit 13b. And store it in the analysis data storage unit 13c (see (5) in FIG. 13). Thereafter, the site improvement apparatus 10 acquires the analysis result stored in the analysis data storage unit 13c and displays it on the GUI.

  For example, as illustrated in FIG. 14, the site improvement apparatus 10 performs keyword extraction by natural language processing from the mail text and address aggregation by statistical processing. In addition, the site improvement apparatus 10 learns the analysis result to enhance the accuracy of the analysis. In addition, the site improvement apparatus 10 performs visualization of an analysis result and alert notification. In the example of FIG. 14, the site improvement apparatus 10 displays the “keyword appearance transition” indicating the transition of the number of occurrences of how many keywords are included in the mail, the “heat map” of the distribution of the number of occurrences of related words, and "Transceiver Correlation Diagram", which is a relationship diagram of a sender / receiver (mail address) of a mail including

  In the example of FIG. 6, the analysis AI engine in the site improvement apparatus 10 analyzes only, but as illustrated in FIG. 15, the server such as the internal processing engine and the cloud in the site improvement apparatus 10 The provided external processing engines may be linked. FIG. 15 is a diagram for explaining cooperation of analysis engines in the site improvement apparatus according to the first embodiment. For example, small-scale data and confidential data are collected and tabulated within a container, but depending on the type and amount of data handled, they may be offloaded to an external processing engine to collect and tabulate data. Good.

  Specifically, an application is added to the container of the internal processing engine (see (1) in FIG. 15), and small-scale data and confidential data are accumulated in the container (see (2) in FIG. 15). Also, an application is added to the external processing engine (see (3) in FIG. 15), and when the processing amount is large, data is stored in the external processing engine (see (4) in FIG. 15). In addition, the container refers to external data and machine learning through an API (see I in FIG. 15) or refers to the analysis result (see II in FIG. 15), and the internal processing engine and external processing engine. Work together. As described above, when the processing amount is large, the analysis engine can be used properly by offloading the process to the external processing engine and using the internal engine for analysis using highly confidential data such as mail data. It is.

[Process procedure of site improvement device]
Next, an example of processing procedure by the site improvement apparatus 10 according to the first embodiment will be described using FIG. FIG. 16 is a flowchart showing an example of the overall processing flow in the site improvement apparatus according to the first embodiment.

  As shown in FIG. 16, the collection unit 12a of the site improvement apparatus 10 searches the embeddable content of the tracking tag for collecting information related to access to the website from the content in the website, and can embed the tracking tag. The tracking tag is inserted into the content (step S101), and the access log is collected (step S102). Also, the collection unit 12a collects social data (step S103).

  Subsequently, the analysis unit 12b causes the collection unit 12a to count information on access to the website and social data (step S104). Then, the analysis unit 12b analyzes the tendency of access to the website and the tendency of access on social media from the aggregated data, and generates recommendation information according to the analysis result (step S105). The recommendation presentation unit 12 c presents the recommendation information generated by the analysis unit 12 b.

  Further, the analysis result output unit 12d generates a screen in which the tendency of access to a website and the tendency of access on social media are arranged in time series from the analysis result analyzed by the analysis unit 12b, and the analysis It outputs as a screen of a result (step S106).

[Effect of First Embodiment]
In the site improvement apparatus 10 according to the first embodiment, the site improvement apparatus 10 searches the content in the website for embeddable content of the tracking tag that collects information on access to the website, and the tracking tag Insert tracking tags for embeddable content and collect information about website access. Then, the site improvement apparatus 10 aggregates information on access to the collected website, analyzes the tendency of access to the website from the aggregated data, and improves the website according to the analyzed result. Present necessary actions as recommended information. Therefore, it is possible to improve the website simply and accurately.

  In addition, the site improvement apparatus 10 searches the content in the website for embeddable content of the tracking tag for collecting information on access to the website, and inserts the tracking tag into the embeddable content of the tracking tag. And aggregate information on access to websites, and collect social data from outside. Then, the site improvement apparatus 10 tabulates the collected information on access to the web site and the social data, and analyzes the trend of access to the web site and the trend of access on the social media from the tabulated data. Then, from the analysis result analyzed, a screen is generated in which the tendency of access to a website and the tendency of access on social media are arranged in time series, and the screen is outputted. Thus, for example, in the past, it was necessary for the user himself to gather information as to the cause of increase or decrease in site access, but by automatically capturing external data and displaying them together, the website by the user It is possible to facilitate access analysis to

  That is, in the site improvement apparatus 10, the function of access analysis can be easily used even if the site administrator has no prerequisite knowledge, and the work can be automated. In addition, the site improvement apparatus 10 can analyze not only the access log to the own site but also trends in the world, such as social data, and information such as e-mail by multi-channel. Furthermore, in the site improvement apparatus 10, site improvement and effect measurement can be performed automatically by the analysis logic. Moreover, in the site improvement apparatus 10, even if the user does not have marketing knowledge, it is possible to perform an analysis in which the collected information is linked.

[System configuration etc.]
Further, each component of each device illustrated is functionally conceptual, and does not necessarily have to be physically configured as illustrated. That is, the specific form of the distribution and integration of each device is not limited to the illustrated one, and all or a part thereof may be functionally or physically dispersed in any unit depending on various loads, usage conditions, etc. It can be integrated and configured. Furthermore, all or any part of each processing function performed in each device may be realized by a CPU and a program analyzed and executed by the CPU, or may be realized as wired logic hardware.

  Further, among the processes described in the present embodiment, all or part of the process described as being automatically performed may be manually performed, or the process described as being manually performed. All or part of can be performed automatically by known methods. In addition to the above, the processing procedures, control procedures, specific names, and information including various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified.

[program]
In addition, it is also possible to create a program in which the processing to be executed by the site improvement apparatus described in the above embodiment is described in a computer executable language. For example, it is also possible to create a site improvement program in which the processing executed by the site improvement apparatus 10 according to the embodiment is described in a computer executable language. In this case, when the computer executes the site improvement program, the same effect as that of the above embodiment can be obtained. Furthermore, even if the site improvement program is recorded in a computer readable recording medium, and the site improvement program recorded in the recording medium is read and executed by a computer, the same process as the above embodiment can be realized. Good.

  FIG. 17 is a diagram illustrating a computer that executes a site improvement program. As illustrated in FIG. 17, the computer 1000 has, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These units are connected by a bus 1080.

  The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012 as illustrated in FIG. The ROM 1011 stores, for example, a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to the hard disk drive 1090 as illustrated in FIG. The disk drive interface 1040 is connected to the disk drive 1100 as illustrated in FIG. For example, a removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to, for example, a mouse 1110 and a keyboard 1120 as illustrated in FIG. The video adapter 1060 is connected to, for example, the display 1130 as illustrated in FIG.

  Here, as illustrated in FIG. 17, the hard disk drive 1090 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. That is, the above-described site improvement program is stored in, for example, the hard disk drive 1090 as a program module in which a command to be executed by the computer 1000 is described.

  In addition, various data described in the above embodiment are stored as program data in, for example, the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads the program module 1093 and program data 1094 stored in the memory 1010 and the hard disk drive 1090 into the RAM 1012 as necessary, and executes various processing procedures.

  The program module 1093 and the program data 1094 related to the site improvement program are not limited to being stored in the hard disk drive 1090, for example, stored in a removable storage medium and read by the CPU 1020 via a disk drive or the like. It is also good. Alternatively, the program module 1093 and program data 1094 related to the site improvement program are stored in another computer connected via a network (LAN (Local Area Network), WAN (Wide Area Network), etc.), and the network interface 1070 is It may be read by the CPU 1020 via the interface.

  The above embodiments and the modifications thereof are included in the invention described in the claims and the equivalents thereof as well as included in the technology disclosed in the present application.

10 site improvement apparatus 11 communication processing unit 12 control unit 12a collection unit 12b analysis unit 12c recommendation presentation unit 12d analysis result output unit 13 storage unit 13a access log storage unit 13b total data storage unit 13c analysis data storage unit

Claims (9)

The content in the website is searched for embeddable content of a tracking tag for collecting information on access to the website, the tracking tag is inserted into the embeddable content of the tracking tag, and the website Collection means for collecting information on access to the
Analysis means for aggregating information on access to the website collected by the collection means, and analyzing the tendency of access to the website from the aggregated data;
A site improvement apparatus comprising: presentation means for presenting an action necessary for improvement of the website as recommendation information according to a result analyzed by the analysis means.   The site improvement apparatus according to claim 1, wherein the analysis means analyzes the tendency of access to the website using a learned model generated as a result of machine learning. The collecting means acquires information on access to the website and collects social data from the outside,
The analysis means aggregates information on access to the website collected by the collection means and the social data, and based on the aggregated data, a tendency of access to the website and a tendency of relevant information on social media The site improvement apparatus according to claim 1, wherein the site analysis apparatus is compared and analyzed. The analysis unit extracts the predetermined pattern using a learned model for extracting a predetermined pattern, using the data collected by the collection unit as an input, and generates the recommendation information based on the predetermined pattern. And
The site improvement apparatus according to claim 1, wherein the presentation means presents the recommendation information generated by the analysis means. The content in the website is searched for embeddable content of a tracking tag for collecting information on access to the website, the tracking tag is inserted into the embeddable content of the tracking tag, and the website Means for collecting social data from the outside as well as tallying information related to access to the
Analysis which aggregates information on access to the website and the social data collected by the collection means, and compares and analyzes the tendency of access to the website and related information on social media from the aggregated data Means,
An output unit that generates a screen in which the tendency of access to the website and the tendency of related information on the social media are arranged in the same time series from the analysis result analyzed by the analysis unit, and the screen is output And a site improvement device characterized by having. A site improvement method performed by the site improvement device,
The content in the website is searched for embeddable content of a tracking tag for collecting information on access to the website, the tracking tag is inserted into the embeddable content of the tracking tag, and the website A collection process for collecting information on access to the
Analyzing the information related to the access to the website collected by the collecting step, and analyzing the tendency of the access to the website from the aggregated data;
And a presenting step of presenting, as recommendation information, an action necessary for the improvement of the website according to a result analyzed by the analyzing step. A site improvement method performed by the site improvement device,
The content in the website is searched for embeddable content of a tracking tag for collecting information on access to the website, the tracking tag is inserted into the embeddable content of the tracking tag, and the website As well as aggregating information about access to the Internet, and collecting social data from the outside,
An analysis that aggregates information on access to the website and the social data collected by the collection process, and compares and analyzes trends of access to the website and related information on social media from the aggregated data Process,
An output step of generating a screen in which the tendency of access to the website and the tendency of related information on the social media are arranged in the same time series from the analysis result analyzed by the analysis step, and outputting the screen A site improvement method characterized by including and. The content in the website is searched for embeddable content of a tracking tag for collecting information on access to the website, the tracking tag is inserted into the embeddable content of the tracking tag, and the website Collection steps to collect information on access to the
Analyzing the information on the access to the website collected by the collecting step and analyzing the tendency of the access to the website from the aggregated data;
A site improvement program which causes a computer to execute a presentation step of presenting an action necessary for improvement of the website as recommendation information according to a result analyzed in the analysis step. The content in the website is searched for embeddable content of a tracking tag for collecting information on access to the website, the tracking tag is inserted into the embeddable content of the tracking tag, and the website As well as aggregating information about access to the Internet, and collecting social data from the outside,
The information on the access to the website collected by the collection step and the social data are aggregated, and the tendency of the access to the website and the tendency of the related information on the social media are compared and analyzed from the aggregated data. Analysis steps to analyze,
An output step of generating a screen in which the tendency of access to the website and the tendency of related information on the social media are arranged in the same time series from the analysis result analyzed by the analysis step, and the screen is output A site improvement program characterized by causing a computer to execute and.

Images