CN113378040A - User behavior analysis method and device for popularization - Google Patents
User behavior analysis method and device for popularization Download PDFInfo
- Publication number
- CN113378040A CN113378040A CN202110567129.0A CN202110567129A CN113378040A CN 113378040 A CN113378040 A CN 113378040A CN 202110567129 A CN202110567129 A CN 202110567129A CN 113378040 A CN113378040 A CN 113378040A
- Authority
- CN
- China
- Prior art keywords
- user
- behavior information
- information
- behavior
- promotion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 32
- 230000001960 triggered effect Effects 0.000 claims abstract description 10
- 230000006399 behavior Effects 0.000 claims description 211
- 230000000007 visual effect Effects 0.000 claims description 17
- 230000014759 maintenance of location Effects 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000007405 data analysis Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the specification discloses a user behavior analysis method and device for popularization. The method and the device are used for solving the problem that the user behavior information contains invalid behavior information, so that the user intention cannot be accurately analyzed and accurate recommendation can be performed. The scheme comprises the following steps: acquiring behavior information of a plurality of users in a promotion website, and unifying formats of the behavior information; based on a friend adding event triggered in a chat tool by a first user in the plurality of users, obtaining relevant information of the first user and/or the chat tool and time for customer service to add the first user; in the behavior information, retrieving according to the time and the related information, and determining the behavior information of the first user; and analyzing the behavior information of the first user to obtain an effective behavior analysis chart corresponding to the first user, so that the customer service performs commodity recommendation service to the first user based on the effective behavior analysis chart.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a user behavior analysis method and device for popularization.
Background
Currently, there are various promotion ways, such as search engine bidding, information flow, and short video promotion. Taking search engine bidding as an example, a contact way for contacting with an enterprise is reserved in a search engine bidding page, wherein the contact way comprises a telephone number, a chat tool and the like, and a user can add a customer service through the chat tool and perform related consultation to the customer service through the chat tool. Before adding a customer service chat tool friend, a user generally retains user behavior information on a related website, but the retained user behavior information often comprises invalid behavior information, so that the user intention cannot be accurately analyzed to perform accurate recommendation.
Disclosure of Invention
One or more embodiments of the present specification provide a user behavior analysis method and apparatus for promotion. The method is used for solving the following technical problems: the user behavior information contains invalid behavior information, and the user intention cannot be accurately analyzed to carry out accurate recommendation.
To solve the above technical problem, one or more embodiments of the present specification are implemented as follows:
in one aspect, one or more embodiments of the present specification provide a user behavior analysis method for promotion, including:
acquiring behavior information of a plurality of users in a promotion website, and unifying formats of the behavior information;
based on a friend adding event triggered in a chat tool by a first user in the plurality of users, obtaining relevant information of the first user and/or the chat tool and time for customer service to add the first user;
in the behavior information, retrieving according to the time and the related information, and determining the behavior information of the first user;
and analyzing the behavior information of the first user to obtain an effective behavior analysis chart corresponding to the first user, so that the customer service performs commodity recommendation service to the first user based on the effective behavior analysis chart.
Optionally, the analyzing the behavior information of the first user to obtain an effective behavior analysis graph corresponding to the first user specifically includes:
confirming invalid behavior information in the behavior information of the first user;
removing the invalid behavior information from the behavior information of the first user to obtain valid behavior information;
generating a user portrait for the first user according to the effective behavior information, and obtaining the intention level of the first user according to the user portrait;
and generating an effective behavior analysis graph corresponding to the first user according to the effective behavior information and the intention level.
Optionally, the confirming invalid behavior information in the behavior information of the first user specifically includes:
determining a link clicked by the first user on the promotion website according to the behavior information of the first user;
determining the operation of the first user in the page corresponding to the link and the time length of staying in the corresponding page;
and if the operation times of the first user and the stay time are both smaller than corresponding preset thresholds, the behavior information generated by clicking the link by the first user is invalid behavior information.
Optionally, after determining that the first user performs an operation in the page corresponding to the link, the method further includes:
determining, by a pre-trained neural network model and according to the behavior information of the first user, that the operation performed by the first user in the page is the probability of being performed by the same person as the operation performed by the first user before clicking the link;
and if the probability is smaller than a preset threshold value, determining the operation of the first user before clicking the link as invalid behavior information.
Optionally, the determining an operation performed by the first user in the page corresponding to the link specifically includes:
determining content in the page copied by the first user; or
Determining a button in the page clicked by the first user; or
And determining the sliding-down speed of the first user when the first user slides the page.
Optionally, after acquiring behavior information of a plurality of users in a promoted website and unifying formats of the behavior information, the method further includes:
counting and processing the behavior information of the users, and determining common operation habits and intention commodity ranking of the users on the promotion website;
and optimizing the promotion website according to the common operation habits and the rank of the intention commodities.
Optionally, after analyzing the behavior information of the first user to obtain an effective behavior analysis graph corresponding to the first user, the method further includes:
performing statistical analysis on different behavior information of the first user generated by the first user browsing the promotion website for multiple times;
determining the same behavior information in the behavior information of the different first users;
and confirming the behavior information similar to the same behavior information in the behavior information of the first user as the effective behavior information.
Optionally, after obtaining the relevant information of the first user and/or the chat tool and the time for customer service to add the first user based on the friend adding event triggered by the first user in the chat tool, the method further includes:
storing the behavior information in the unified format in a temporary database;
storing the time and the related information in the temporary database;
comparing the storage time of the behavior information stored in the temporary database with the current system time at regular time;
and deleting the behavior information when the difference value between the storage time and the current system time is larger than a preset range.
Optionally, the behavior information includes: static information and dynamic information;
the static information comprises the user browser information, the operating system information and the information carried in the url;
the dynamic information comprises the touch event, a copied content event and a clicked preset buried point event, and the user stays in a visual staying area of the current promotion page;
the preset buried point clicking event comprises a clicking event, an exposure event and a retention time event of the current promotion page.
In another aspect, one or more embodiments of the present specification provide a user behavior analysis device for promotion, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to cause the at least one processor to perform instructions for:
acquiring behavior information of a plurality of users in a promotion website, and unifying formats of the behavior information;
based on a friend adding event triggered in a chat tool by a first user in the plurality of users, obtaining relevant information of the first user and/or the chat tool and time for customer service to add the first user;
in the behavior information, retrieving according to the time and the related information, and determining the behavior information of a first user of the first user;
and analyzing the behavior information of the first user to obtain an effective behavior analysis chart corresponding to the first user, so that the customer service performs commodity recommendation service to the first user based on the effective behavior analysis chart.
The user behavior analysis method and the user behavior analysis equipment for popularization provided by the application can bring the following beneficial effects: the effective behavior information can be determined according to the user behavior information, the user effective behavior analysis chart can be determined, the level of the degree of intent of customer conversion can be accurately judged, the customer service can reasonably distribute energy to accurately popularize the user, and order completion is promoted. In addition, various browsers are adapted, user behavior information is unified, and data analysis is facilitated.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.
Fig. 1 is a schematic flowchart of a user behavior analysis method for promotion according to one or more embodiments of the present disclosure;
FIG. 2 is a diagram illustrating behavior information obtained by a browser layer according to one or more embodiments of the present disclosure;
FIG. 3 illustrates information collected by a data collection layer according to one or more embodiments of the present disclosure;
FIG. 4 is a data service provided by an analysis layer according to one or more embodiments of the present disclosure;
FIG. 5 is a schematic illustration of a technical chain provided in one or more embodiments of the present disclosure;
fig. 6 is a schematic structural diagram of a user behavior analysis device for popularization according to one or more embodiments of the present specification.
Detailed Description
The embodiment of the application provides a user behavior analysis method and device for popularization.
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 a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments of the present disclosure, shall fall within the scope of protection of the present application.
At present, there are various promotion ways, such as search engine bidding, information flow and short video promotion, taking search engine bidding as an example, a contact way for contacting with an enterprise is reserved in a search engine bidding page, including a telephone number, a chat tool and the like, and a user can add a customer service through the chat tool and make a relevant consultation to the customer service through the chat tool. Before adding a customer service chat tool friend, a user generally retains user behavior information on a related website, but the retained user behavior information often comprises invalid behavior information, so that the user intention cannot be accurately analyzed to perform accurate recommendation.
In order to solve the above problem, embodiments of the present specification provide a user behavior analysis method and device for popularization. The effective behavior information can be determined according to the user behavior information, the user effective behavior analysis chart can be determined, the level of the degree of intent of customer conversion can be accurately judged, the customer service can reasonably distribute energy to accurately popularize the user, and order completion is promoted. In addition, various browsers are adapted, user behavior information is unified, and data analysis is facilitated.
The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.
Fig. 1 is a schematic flowchart of a user behavior analysis method for promotion according to one or more embodiments of the present disclosure. As shown in fig. 1, the user behavior method for promotion includes the following steps:
s101: the method comprises the steps of obtaining behavior information of a plurality of users in a promotion website, and unifying formats of the behavior information.
Fig. 2 is a diagram of behavior information obtained by a browser layer according to one or more embodiments of the present disclosure.
In one or more embodiments of the present description, the behavior information includes static information and dynamic information. The static information comprises user browser information, operating system information and information carried in url, and the dynamic information comprises a touch event, a content copying event, a preset buried point clicking event and a visual staying area of a user on the current popularization page; the preset buried point clicking event comprises a clicking event, an exposure event and a current promotion page stay time event.
Specifically, the browser information includes a browser name, browser version information, a display height, a display width, a browser installation plug-in number, a browser installation plug-in information list, and the like, and the operating system refers to a window series operating system, an android system, an IOS system, a Linux operating system, and the like. The information carried in the url refers to information that can be accessed and obtained by the url to the current promotion page. The information carried in the url includes search keyword information and other bidding information of the user when entering the promotion page, etc.
Further, a touch event provides the ability to interpret finger (or stylus) activity on a touch screen or touch pad, a touch event refers to the entire process of a touch object staying on the screen, and the interaction ends when the touch object leaves the touch screen. The touch object refers to a finger (or elbow, ear, nose) or a stylus. The content copying event refers to an operation of copying the page content on a current promotion page by a user, and the current promotion page refers to a page displayed in the screen at the current moment. If the browser has the right of calling the camera, capturing the eyes of the user through the camera, determining the visual staying area of the user and counting the visual staying time, or determining the visual staying area of the user and counting the visual staying time by monitoring the staying position and the staying time of a mouse cursor of the user. For example, the time that the user visually stays at the upper left of the browser is longer, the time that the user visually stays at the lower right of the browser is shorter, a visual thermodynamic diagram is formed according to the visual staying area and the staying time of the visual staying area, and the area with the long visual staying time of the user is displayed in a special highlight mode in the visual thermodynamic diagram.
Further, when the user's behavior satisfies a certain condition, such as every click, every jump, every login, etc., of the user's behavior, the recording and storing are automatically triggered. The click event refers to the user clicking a button of the current page. And successfully opening the page once to record the exposure event once, refreshing the page once to record the exposure event once, loading a new page of the next page, and loading the exposure event once to record once. The current promotion page stay time event represents that the stay time of a user on the current page is recorded as the stay time. For example, customer A9:00 visited the home page of the promotional website, at which point the analysis tool begins recording 1 session for this visitor to customer A. Then, 9:01, customer a browses another list page and leaves the promotion website (the process of leaving the promotion website can be realized by closing the browser, typing a different website in the address bar, or clicking a link linked to other websites on the promotion website), and the process is regarded as a session, and finally, the residence time of customer a on the first page of the promotion website is 1 minute.
In one or more embodiments of the present specification, behavior information of a plurality of users is counted and processed, and an operation habit and an intention commodity rank shared by the plurality of users on a promotion website are determined; and optimizing the promotion website according to the common operation habits and the ranking of the intention commodities.
Specifically, the user may have a common operation habit when browsing the promotion website, such as a time period when the user intensively browses the promotion webpage, a visual retention area when the user browses the promotion webpage, and the like. For example, the time periods for browsing the promotion web pages by the user are concentrated on 12:00-14:00 and 20:00-22:00, which indicate that the free time is sufficient at the two time points, and the customer service can promote the promotion to the user in the time periods.
Furthermore, the visual retention area of the user when browsing the promotion webpage shows that the area above the left of the browser is the area with the longest visual retention time of the user, the area below the right of the browser is the area with the shortest visual retention time of the user, and a worker can place the promotion of a new product or a main printing product at the upper left of the promotion webpage and place an unimportant promotion at the lower right of the promotion webpage, so that the transformation of the promotion of the new product or the main printing product is facilitated.
S102: and obtaining the relevant information of the first user and/or the chat tool and the time for customer service to add the first user based on the friend adding event triggered by the first user in the chat tool.
Fig. 3 is information collected by a data collection layer according to one or more embodiments of the present disclosure. In the invention, the chat tools comprise an enclosed chat tool and a non-enclosed chat tool. The open type chat tool is a chat tool which can legally acquire the relevant information of the user by a third party. For the closed type chatting tool, if an agreement is reached with a manager of the closed type chatting tool, the user is informed in advance, and the related information of the user can be obtained on the basis of the agreement of the user. The method comprises the steps of obtaining an HTML node change condition triggering a friend adding event based on a browser development tool, and obtaining relevant information of a first user and/or a chat tool, wherein the relevant information of the first user comprises operating system information of the first user, search keyword information and the like.
Further, the obtained related information of the first user and/or the chat tool is processed, the format of the related information of the first user and/or the chat tool is changed into the same format as the user behavior information, and the related information of the first user is convenient to compare with the plurality of user behavior information.
In one or more embodiments of the present description, the behavior information in a unified format is stored in a temporary database; storing the time and the related information in a temporary database; comparing the storage time of the behavior information stored in the temporary database with the current system time at regular time; and deleting the behavior information when the difference value between the storage time and the current system time is larger than a preset range.
Specifically, the storage space of the temporary database is small, and the user behavior information stored in the temporary database for a long time is deleted, so that the memory space of the temporary database can be saved. It is worth noting that if a user adds a friend of a customer service chat tool, after an effective behavior analysis graph is generated, behavior information of the user is deleted from the temporary database, the user behavior information stored in the temporary database for a long time is the user behavior information of the friend of the customer service chat tool which is not added for a long time, the user does not add the friend of the customer service chat tool for a long time after browsing the promotion webpage, the intention is low, and the behavior information of the user with low intention is deleted, so that the storage space of the temporary database is saved.
S103: and in the behavior information, retrieving according to the time and the related information, and determining the behavior information of the first user.
In general, before adding a friend of a customer service chat tool, a user browses a promotion webpage of a promotion website, at this time, behavior information of the user is left, and then, the first user adds the friend of the customer service chat tool through a chat tool contact way reserved in the promotion webpage to acquire time for adding the friend. The behavior information of the first user is generated before the time, the obtained related information of the first user is compared with the behavior information stored in the temporary database in a first time range before the time, for example, the operating system information and the search keyword information of the first user are compared with the operating system information and the search keyword information stored in the temporary database in the first time range, and if the operating system information and the search keyword information exist, the behavior information of the first user is determined. It should be noted that not only the operating system information and the search key information are compared. Wherein the first time range may be within 5 minutes to 30 minutes before the time node.
S104: and analyzing the behavior information of the first user to obtain an effective behavior analysis chart corresponding to the first user, so that the customer service performs commodity recommendation service to the first user based on the effective behavior analysis chart.
In one or more embodiments of the present description, invalid behavior information is confirmed among behavior information of a first user; removing invalid behavior information from the behavior information of the first user to obtain valid behavior information; generating a user portrait for the first user according to the effective behavior information, and obtaining the intention level of the first user according to the user portrait; and generating an effective behavior analysis graph corresponding to the first user according to the effective behavior information and the intention level.
Fig. 4 is a data service provided by an analysis layer according to one or more embodiments of the present disclosure. Specifically, the user portrait is drawn for the first user, for example, the first user clicks some promotion links on a promotion page, and then it is analyzed that the promotion links clicked by the first user have bid intentions, and under an effective behavior, the more the number of clicks, the higher the intention level of the first user to the promotion is, and the higher the intention level is, the darker the color in the effective behavior analysis graph is.
Furthermore, the effective behavior analysis graph also comprises promotion similar to the promotion link according to the intention level of the first user for clicking the promotion link, so that the potential requirements of the first user can be known in the first time conveniently.
Further, the effective behavior analysis graph comprises a series of charts made according to browsing emphasis of the first user, copying actions when browsing the promotion page, touch events, preset point clicking events and visual stay areas of the current promotion page. It should be noted that, the above-mentioned series of events are not only collected behavior information left by the first user in a web page, but also behavior information left by the first user in browsing the whole popularization web page.
In one or more embodiments of the present description, a link clicked by a first user on a promotion website is determined according to behavior information of the first user; determining the operation of the first user in the page corresponding to the link and the time length of staying in the corresponding page; and if the operation times of the first user and the stay time are both smaller than the corresponding preset threshold, the behavior information generated by clicking the link by the first user is invalid behavior information.
In one or more embodiments of the present description, content in a page copied by a first user is determined; or determining a button in a page clicked by the first user; or determining the sliding-down speed when the first user performs the sliding operation on the page.
Specifically, when browsing the promotion page, the user may click the promotion link without clicking the promotion link, and in this case, the user generally exits immediately after entering the page corresponding to the link, and does not perform any operation on the page, or performs a small amount of operation, so that the behavior information generated in this case is invalid. For example, after the first user clicks the promotion link to enter the corresponding page, no operation is performed, or only one cancel button is clicked, and the page is closed within a preset threshold for the stay time. The preset threshold of the stay time can be 1 second, 2 seconds and the like, and the preset threshold of the operation times can be 1 time, 2 times and the like.
Further, the behavior information generated by the first user's misoperation is also invalid behavior information, for example, the mouse of the first user is pressed to refresh the promotion page for several times, and at this time, a plurality of pieces of identical behavior information are generated in a short time, and the behavior information is considered to be invalid behavior information.
In one or more embodiments of the present specification, a pre-trained neural network model is used to determine, according to behavior information of a first user, a probability that an operation performed by the first user in a page is performed by the same person as an operation performed by the first user before a link is clicked; and if the probability is smaller than a preset threshold value, determining the operation of the first user before clicking the link as invalid behavior information.
Specifically, in daily life, different users may use the same terminal, for example, between couples and couples, and between couples may continue browsing after one person browses another person, and usually, the intentions of different users are different. In one case, before clicking the link, the husband browses the information such as football and basketball by using the wife's terminal, then the wife clicks the promotion links such as bags, shoes and clothes by using the self terminal, enters the corresponding page and then carries out a series of operations, and then the wife is the client who really has the intention by adding the chat tool of customer service. The action taken between wife clicking on a link is to invalidate the behavioural information.
In one or more embodiments of the present specification, statistical analysis is performed on behavior information of different first users generated by a first user browsing a promotion website for multiple times; determining the same behavior information in the behavior information of different first users; and confirming the behavior information similar to the same behavior information in the behavior information of the first user as effective behavior information. Specifically, a first user can browse a promotion website for multiple times, behavior information of the first user is left once when browsing the promotion website every time, in a general situation, situations that different users use the same terminal rarely occur, situations that behavior information of the first user left for multiple times is obviously classified are relatively few, operation habits of the same user are the same, the same behavior information is more, for example, a gliding speed, a clicking frequency, browser information, a stay time of each promotion page and the like of the user when browsing the promotion webpage, and based on the same behavior information, it can be judged which behavior information of the first user is generated when the first user browses the promotion website, and which effective behavior information of the first user is determined.
Further, the chat tool account of the customer service is obtained, the chat tool account of the first user is bound with the chat tool account of the customer service, and the newly generated effective behavior analysis chart of the first user is sent to the customer service at regular time.
Specifically, after a first user adds a friend of a chat tool of customer service, the account of the chat tool of the customer service is obtained, the first user is bound with the customer service, the first user is received in a special form, and the customer service can accurately master the intention of the first user. Under normal circumstances, the first user can browse the promotion website more than once, and the newly generated effective behavior analysis chart of the first user is sent to the customer service at regular time, so that the subsequent maintenance and promotion of the customer service on the first user are facilitated.
Further, the customer service can share the intention promotion or the promotion similar to the intention promotion to the first user through the chat window of the chat tool and the first user or indirectly share the intention promotion or the promotion similar to the intention promotion to the first user through the functions of sharing dynamics and the like carried by the chat tool according to the effective behavior analysis diagram of the first user.
It should be noted that, in this specification, only the promotion website web page is taken as an example, but the present invention is not limited to the promotion website web page, and may also be an information flow promotion, an e-commerce website, and the like.
Fig. 5 is a schematic view of a technical chain according to one or more embodiments of the present disclosure. As shown in fig. 5, the browser provides user behavior information and data information such as friend adding events, data acquisition and analysis analyze the data information provided by the browser, and an analysis result is displayed to a customer service, a data analyst or enterprise related personnel, and the like.
Fig. 6 is a schematic structural diagram of a user behavior analysis device for popularization according to one or more embodiments of the present specification.
As shown in fig. 6, the user behavior analysis device for promotion includes:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to cause the at least one processor to perform instructions for:
acquiring behavior information of a plurality of users in a promotion website, and unifying formats of the behavior information;
based on a friend adding event triggered in a chat tool by a first user in the plurality of users, obtaining relevant information of the first user and/or the chat tool and time for customer service to add the first user;
in the behavior information, retrieving according to the time and the related information, and determining the behavior information of the first user;
and analyzing the behavior information of the first user to obtain an effective behavior analysis chart corresponding to the first user, so that the customer service performs commodity recommendation service to the first user based on the effective behavior analysis chart.
The user behavior analysis method and the user behavior analysis equipment for popularization provided by the application can bring the following beneficial effects: the effective behavior information can be determined according to the user behavior information, the user effective behavior analysis chart can be determined, the level of the degree of intent of customer conversion can be accurately judged, the customer service can reasonably distribute energy to accurately popularize the user, and order completion is promoted. In addition, various browsers are adapted, user behavior information is unified, and data analysis is facilitated.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The above description is merely one or more embodiments of the present disclosure and is not intended to limit the present disclosure. Various modifications and alterations to one or more embodiments of the present description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of the claims of the present specification.
Claims (10)
1. A user behavior analysis method for promotion is characterized by comprising the following steps:
acquiring behavior information of a plurality of users in a promotion website, and unifying formats of the behavior information;
based on a friend adding event triggered in a chat tool by a first user in the plurality of users, obtaining relevant information of the first user and/or the chat tool and time for adding the first user by a customer service terminal;
in the behavior information, retrieving according to the time and the related information, and determining the behavior information of the first user;
and analyzing the behavior information of the first user to obtain an effective behavior analysis chart corresponding to the first user, so that the customer service terminal performs commodity recommendation service to the first user based on the effective behavior analysis chart.
2. The user behavior analysis method for popularization according to claim 1, wherein the analyzing the behavior information of the first user to obtain an effective behavior analysis graph corresponding to the first user specifically includes:
confirming invalid behavior information in the behavior information of the first user;
removing the invalid behavior information from the behavior information of the first user to obtain valid behavior information;
generating a user portrait for the first user according to the effective behavior information, and obtaining the intention level of the first user according to the user portrait;
and generating an effective behavior analysis graph corresponding to the first user according to the effective behavior information and the intention level.
3. The method according to claim 2, wherein the confirming of invalid behavior information in the behavior information of the first user specifically includes:
determining a link clicked by the first user on the promotion website according to the behavior information of the first user;
determining the operation of the first user in the page corresponding to the link and the time length of staying in the corresponding page;
and if the operation times of the first user and the stay time are both smaller than corresponding preset thresholds, the behavior information generated by clicking the link by the first user is invalid behavior information.
4. The method according to claim 3, wherein after determining that the first user performs an operation in the page corresponding to the link, the method further comprises:
determining, by a pre-trained neural network model and according to the behavior information of the first user, that the operation performed by the first user in the page is the probability of being performed by the same person as the operation performed by the first user before clicking the link;
and if the probability is smaller than a preset threshold value, determining the operation of the first user before clicking the link as invalid behavior information.
5. The method according to claim 3, wherein the determining of the operation performed by the first user in the page corresponding to the link specifically includes:
determining content in the page copied by the first user; or
Determining a button in the page clicked by the first user; or
And determining the sliding-down speed of the first user when the first user slides the page.
6. The method of claim 1, wherein after obtaining behavior information of a plurality of users at a promotion website and unifying formats of the behavior information, the method further comprises:
counting and processing the behavior information of the users, and determining common operation habits and intention commodity ranking of the users on the promotion website;
and optimizing the promotion website according to the common operation habits and the rank of the intention commodities.
7. The method according to claim 1, wherein after analyzing the behavior information of the first user to obtain an effective behavior analysis graph corresponding to the first user, the method further comprises:
performing statistical analysis on different behavior information of the first user generated by the first user browsing the promotion website for multiple times;
determining the same behavior information in the behavior information of the different first users;
and confirming the behavior information similar to the same behavior information in the behavior information of the first user as the effective behavior information.
8. The method of claim 1, wherein after obtaining the information related to the first user and/or the chat tool and the time for customer service to add the first user based on the friend adding event triggered by the first user in the chat tool, the method further comprises:
storing the behavior information in the unified format in a temporary database;
storing the time and the related information in the temporary database;
comparing the storage time of the behavior information stored in the temporary database with the current system time at regular time;
and deleting the behavior information when the difference value between the storage time and the current system time is larger than a preset range.
9. The method of claim 1, wherein the behavior information comprises: static information and dynamic information;
the static information comprises the user browser information, the operating system information and the information carried in the url;
the dynamic information comprises the touch event, a copied content event and a clicked preset buried point event, and the user stays in a visual staying area of the current promotion page;
the preset buried point clicking event comprises a clicking event, an exposure event and a retention time event of the current promotion page.
10. A user behavior analysis device for promotion, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to cause the at least one processor to perform instructions for:
acquiring behavior information of a plurality of users in a promotion website, and unifying formats of the behavior information;
based on a friend adding event triggered in a chat tool by a first user in the plurality of users, obtaining relevant information of the first user and/or the chat tool and time for customer service to add the first user;
in the behavior information, retrieving according to the time and the related information, and determining the behavior information of the first user;
and analyzing the behavior information of the first user to obtain an effective behavior analysis chart corresponding to the first user, so that the customer service performs commodity recommendation service to the first user based on the effective behavior analysis chart.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567129.0A CN113378040A (en) | 2021-05-24 | 2021-05-24 | User behavior analysis method and device for popularization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567129.0A CN113378040A (en) | 2021-05-24 | 2021-05-24 | User behavior analysis method and device for popularization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113378040A true CN113378040A (en) | 2021-09-10 |
Family
ID=77571727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110567129.0A Pending CN113378040A (en) | 2021-05-24 | 2021-05-24 | User behavior analysis method and device for popularization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113378040A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114580435A (en) * | 2022-02-18 | 2022-06-03 | 深圳数鉴科技有限公司 | Session analysis method and system based on user behavior data |
| CN114926222A (en) * | 2022-06-06 | 2022-08-19 | 山东浪潮爱购云链信息科技有限公司 | Core enterprise popularization method, device and medium |
| CN117037279A (en) * | 2023-08-25 | 2023-11-10 | 北京智芯微电子科技有限公司 | Action detection and counting method and device, heterogeneous chip, equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886090A (en) * | 2014-03-31 | 2014-06-25 | 北京搜狗科技发展有限公司 | Content recommendation method and device based on user favorites |
| CN107437189A (en) * | 2016-05-25 | 2017-12-05 | 腾讯科技（深圳）有限公司 | A kind of put-on method of promotion message, apparatus and system |
| CN107507041A (en) * | 2017-09-08 | 2017-12-22 | 北京京东尚科信息技术有限公司 | The construction method and construction device of user model |
| CN109145194A (en) * | 2017-06-27 | 2019-01-04 | 北京国双科技有限公司 | The acquisition method and device of user behavior data |
| CN109992717A (en) * | 2019-03-29 | 2019-07-09 | 珠海豹好玩科技有限公司 | Information recommendation method, device, terminal and computer readable storage medium |
| CN110415022A (en) * | 2019-07-05 | 2019-11-05 | 阿里巴巴集团控股有限公司 | Handle the method and device of user behavior sequence |
| CN110516151A (en) * | 2019-08-27 | 2019-11-29 | 咪咕文化科技有限公司 | Vaild act detection and personalized recommendation method |
| CN112100156A (en) * | 2020-09-15 | 2020-12-18 | 北京百度网讯科技有限公司 | Method, device, medium and system for constructing knowledge base based on user behaviors |
| CN112232933A (en) * | 2020-12-11 | 2021-01-15 | 深圳市房多多网络科技有限公司 | House source information recommendation method, device, equipment and readable storage medium |
-
2021
- 2021-05-24 CN CN202110567129.0A patent/CN113378040A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886090A (en) * | 2014-03-31 | 2014-06-25 | 北京搜狗科技发展有限公司 | Content recommendation method and device based on user favorites |
| CN107437189A (en) * | 2016-05-25 | 2017-12-05 | 腾讯科技（深圳）有限公司 | A kind of put-on method of promotion message, apparatus and system |
| CN109145194A (en) * | 2017-06-27 | 2019-01-04 | 北京国双科技有限公司 | The acquisition method and device of user behavior data |
| CN107507041A (en) * | 2017-09-08 | 2017-12-22 | 北京京东尚科信息技术有限公司 | The construction method and construction device of user model |
| CN109992717A (en) * | 2019-03-29 | 2019-07-09 | 珠海豹好玩科技有限公司 | Information recommendation method, device, terminal and computer readable storage medium |
| CN110415022A (en) * | 2019-07-05 | 2019-11-05 | 阿里巴巴集团控股有限公司 | Handle the method and device of user behavior sequence |
| CN110516151A (en) * | 2019-08-27 | 2019-11-29 | 咪咕文化科技有限公司 | Vaild act detection and personalized recommendation method |
| CN112100156A (en) * | 2020-09-15 | 2020-12-18 | 北京百度网讯科技有限公司 | Method, device, medium and system for constructing knowledge base based on user behaviors |
| CN112232933A (en) * | 2020-12-11 | 2021-01-15 | 深圳市房多多网络科技有限公司 | House source information recommendation method, device, equipment and readable storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114580435A (en) * | 2022-02-18 | 2022-06-03 | 深圳数鉴科技有限公司 | Session analysis method and system based on user behavior data |
| CN114580435B (en) * | 2022-02-18 | 2022-10-25 | 深圳数鉴科技有限公司 | Session analysis method and system based on user behavior data |
| CN114926222A (en) * | 2022-06-06 | 2022-08-19 | 山东浪潮爱购云链信息科技有限公司 | Core enterprise popularization method, device and medium |
| CN114926222B (en) * | 2022-06-06 | 2024-05-10 | 山东浪潮爱购云链信息科技有限公司 | Popularization method, equipment and medium for core enterprises |
| CN117037279A (en) * | 2023-08-25 | 2023-11-10 | 北京智芯微电子科技有限公司 | Action detection and counting method and device, heterogeneous chip, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113378040A (en) | User behavior analysis method and device for popularization | |
| US7610276B2 (en) | Internet site access monitoring | |
| US9300755B2 (en) | System and method for determining information reliability | |
| US8756224B2 (en) | Methods, systems, and media for content ranking using real-time data | |
| US20180315084A1 (en) | System and method of providing a platform for managing data content campaign on social networks | |
| Adar et al. | Resonance on the web: web dynamics and revisitation patterns | |
| Akuma et al. | Comparative analysis of relevance feedback methods based on two user studies | |
| CN101681488A (en) | The client application of Contextually aware | |
| CN105069087A (en) | Web log data mining based website optimization method | |
| EP2339526A1 (en) | System and method for monitoring visits to a target site | |
| US20120311140A1 (en) | Method of processing web access information and server implementing same | |
| Festic et al. | How long and what for? Tracking a nationally representative sample to quantify internet use | |
| Wani et al. | Design and implementation of iMacros-based data crawler for behavioral analysis of Facebook users | |
| CN113392358A (en) | Static resource preloading method and device | |
| JP4770445B2 (en) | Information recommendation device | |
| CN103605742A (en) | Method and device for recognizing network resource entity content page | |
| CN110751526A (en) | Advertisement pushing method and device, computer equipment and storage medium | |
| CN106126538B (en) | Page conversion processing method and device | |
| Mowla et al. | Analysis of web server logs to understand internet user behaviour and develop digital marketing strategies | |
| Vasconcelos et al. | Exploiting client logs to support the construction of adaptive e-commerce applications | |
| CN102662567B (en) | The method and apparatus of operation in trigger web pages | |
| CN112818217A (en) | Web service recommendation method and system based on block chain fragmentation | |
| CN112417301A (en) | Information pushing method, device, server and storage medium | |
| CN109074365B (en) | Parameterizing network communication paths | |
| Husin | Analysis of user behaviour on an online newspaper using Web server logs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210910 |
|
| RJ01 | Rejection of invention patent application after publication |