CN111310044A - Method, device, device and storage medium for extracting page element information - Google Patents

Abstract

The present application discloses a method, device, device and storage medium for extracting page element information, and relates to the technical field of data mining. The specific implementation scheme is: collecting the element information set triggered by the user interaction event on the target page; extracting the target element information from the element information set according to the attribute of the element associated with the page business and the index of the number of times the element is triggered. The embodiment of the present application extracts service-oriented element information that can clearly reflect the semantics of user behavior, so as to improve the application value of the element information for product and operation optimization.

Description

Method, device, device and storage medium for extracting page element information

technical field

The present application relates to computer technology, in particular to the technical field of data mining.

Background technique

Embedding is a common data analysis method for website analysis. By adding some program codes to a website or application, it is used to collect users' browsing, access data and application usage in the website or application, and to analyze user interaction. behaviors, which help in the subsequent optimization of products and operations.

In the prior art, the user interaction behavior is generally analyzed by collecting element information triggered by the user interaction behavior. With the gradual enrichment of the business of a website or application, more and more element information needs to be collected, and the user behavior reflected by the element information is messy, and the application value for product and operation optimization is getting lower and lower.

SUMMARY OF THE INVENTION

Embodiments of the present application provide a method, apparatus, device, and storage medium for extracting page element information, so as to extract element information that is valuable for product and operation optimization.

In a first aspect, an embodiment of the present application provides a method for extracting page element information, including:

Collect the set of element information triggered by user interaction events on the target page;

The target element information is extracted from the element information set according to the attribute of the element associated with the page service and the index of the number of times the element is triggered.

In this embodiment of the present application, all user behavior data is obtained by collecting the set of element information on the target page that is triggered by user interaction events. The target element information is extracted from the element information set, so as to extract the business-oriented element information that can clearly reflect the semantics of user behavior, so as to improve the application value of the element information for product and operation optimization.

Optionally, the attributes of the element associated with the page business include: click event bound to the element, button type of the element, link function of the element, content length of the element less than the set value, the element is located on the landing page and the element at least one of the promotion pages;

The indicator of the number of times the element is triggered, including: the conversion rate and/or the click rate of the element.

In an optional implementation manner in the above application, the click event bound to the element, the button type of the element, the link function of the element, the content length of the element less than the set value, the element located on the landing page and the element located on the promotion page can be clearly reflected. The business attribute of the element, so the target element information extracted based on the above attributes is the element information for the page business; the conversion rate and/or click rate of the element reflects the user's focusing behavior on the element, reflecting the clear behavior semantics, which is conducive to accuracy Extract target element information.

Optionally, extract target element information from the element information set according to the attribute of the element associated with the page business and the index of the number of times the element is triggered, including:

Extracting a candidate element information set from the element information set according to the attribute of the element associated with the page business;

The target element information is extracted from the candidate element information set according to the index of the number of times the element is triggered.

In an optional implementation manner in the above application, the attribute can be obtained directly from the element information set, and the number of times index needs to be obtained by calculation, and the element information is first extracted according to the attribute, and then the secondary extraction is carried out according to the number of times index, which can be quickly extracted. target element information and reduce the amount of computation.

Optionally, extracting a candidate element information set from the element information set according to the attribute of the element associated with the page business, including:

From the element information set, extract the element information triggered by the click event;

From the element information triggered by the click event, extract the element information of the button type, the element information of the link type, the element information of the content length less than the set value, the element information on the landing page and the element information on the promotion page. At least one of them constitutes a candidate element information set.

In an optional implementation manner in the above application, click events can better reflect the user's focus on elements compared with other interaction events; the element information is preferentially selected according to the click event type, and compared with other attributes, it can maximize the The available element information is selected in a range; then candidate elements are extracted according to the button, link, content length and page of the element, which is beneficial to improve the extraction efficiency of element information.

Optionally, extract target element information from the candidate element information set according to the index of the number of times the element is triggered, including:

Calculate the conversion rate and/or click-through rate for each candidate element;

From the candidate element information set, the candidate element information with the conversion rate within the first preset range and/or the candidate element information with the click-through rate within the second preset range is determined as the target element information.

In an optional implementation of the above application, the conversion rate and the click rate can significantly reflect the user's focusing behavior on the element, and have clear behavioral semantics; and the conversion rate and the click rate can reflect the user's focus on the element. Reflects the strength of behavioral semantics. Based on this, the conversion rate and/or click rate within a preset range can be selected according to business needs, and target element information with different semantic strengths can be extracted.

Optionally, calculate the conversion rate, and/or click-through rate for each candidate element, including:

Obtain multiple sessions generated during the interaction between the user and the target page, and each session includes element information triggered by click events within a preset period;

Calculate the conversion rate of each candidate element according to the number of sessions containing information about each candidate element, and the total number of sessions; and/or, according to the number of sessions containing information about each candidate element, and each candidate element The number of times the element information is displayed on the target page, and the click-through rate of each candidate element is calculated.

In an optional implementation manner of the above application, the session is used as the granularity, and the conversion rate and click rate are calculated by whether the user clicks on the candidate element within a preset period of time, so as to avoid the user's repeated click on the candidate element in a short period of time. error, improve the accuracy of conversion rate and click-through rate.

Optionally, from the candidate element information set, the element information with the conversion rate within the first preset range, and/or the element information with the click-through rate within the second preset range, is determined. Before being the target element information, the method further includes: deleting the element information whose conversion rate exceeds the first preset threshold and/or the element information whose click rate exceeds the second preset threshold in the candidate element information set.

In an optional implementation manner in the above application, the elements with higher frequency indicators are generally the elements that are routinely reached, and the basic services facing the page, such as the login button, the save button, etc.; the information of these elements is difficult to reflect the user's personalized behavior semantics; By deleting the candidate element information with a high frequency index, the element information reflecting the user's personalized behavior semantics can be centrally extracted.

Optionally, after the target element information is extracted from the element information set according to the attribute of the element associated with the page business and the index of the number of times the element is triggered, the method further includes:

According to the target element information, the page to be embedded is embedded.

In an optional implementation manner of the above application, according to the target element information, the page to be buried is buried, so as to accurately extract the business-oriented element information on the page to be buried that can clearly reflect the semantics of user behavior, and this The tracking method is suitable for novice users or users who are not professional analysts. The technical threshold is low. Starting from the element information collection, it fills the gap between the element information collection and the user setting tracking, and produces business-meaning tracking recommendation results. .

In a second aspect, an embodiment of the present application further provides a device for extracting page element information, including:

The collection module is used to collect the element information set triggered by the user interaction event on the target page;

The extraction module is configured to extract target element information from the element information set according to the attribute of the element associated with the page service and the index of the number of times the element is triggered.

In a third aspect, an embodiment of the present application also provides an electronic device, including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a method as provided by an embodiment of the first aspect The method for extracting page element information.

In a fourth aspect, embodiments of the present application further provide a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to cause the computer to execute a page element provided by the embodiments of the first aspect Information extraction method.

Other effects of the above-mentioned optional manners will be described below with reference to specific embodiments.

Description of drawings

The accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present application. in:

1 is a flowchart of a method for extracting page element information in Embodiment 1 of the present application;

2 is a flowchart of a method for extracting page element information in Embodiment 2 of the present application;

3 is a structural diagram of a device for extracting page element information in Embodiment 3 of the present application;

FIG. 4 is a block diagram of an electronic device used to implement the method for extracting page element information according to an embodiment of the present application.

Detailed ways

Exemplary embodiments of the present application are described below with reference to the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

Example 1

FIG. 1 is a flowchart of a method for extracting page element information in Embodiment 1 of the present application. The embodiment of the present application is suitable for extracting the application value of product and operation optimization from page element information triggered by user interaction behavior. In the case of element information, the method is performed by a device for extracting page element information, which is implemented by software and/or hardware, and is specifically configured in an electronic device with a certain data computing capability.

As shown in Figure 1, a method for extracting page element information includes:

S101. Collect a set of element information on a target page that is triggered by a user interaction event.

The target page may be a page of a website or a page of an application, and the number of target pages is at least one. This embodiment pre-embeds points on the target page, such as full point embedding or code embedding. By burying the point, the user interaction event set by the element binding on the target page, when the user interaction event is monitored, the bound element information is triggered. Element information includes, but is not limited to, element content (or element name), element type, element location, and the page where the element is located.

Optionally, during the interaction between the user and the target page, the element information triggered by the user interaction event is collected in real time by burying points to form an element information set; or, in the element information collected by burying points, some or all of the elements are selected. information, which constitutes a set of element information.

S102. Extract target element information from the element information set according to the attribute of the element associated with the page service and the index of the number of times the element is triggered.

Elements on a page have properties such as element content, element type, and the page the element is on. Page business refers to the functions, portals and services provided by the target page. Some element attributes are associated with page services, and some element attributes are not associated with page services. Whether the element attribute is associated with the page business can be determined by whether the page business is called after the element is triggered, that is, whether the function, entry or service provided by the page is called.

Optionally, the attributes of the element associated with the page business include: the click event bound to the element, the button type of the element, the link function of the element, the content length of the element less than the set value, the element on the landing page and the element on the promotion page. at least one of them. The click events include but are not limited to touch, single click, and double click. The page calls the page business in response to the user's click-type operation; moreover, the click-type event can better reflect the user's focusing behavior on the element than the sliding-type event. Similarly, the page invokes the corresponding page service in response to the user's trigger operation on the button-type element, and jumps to the corresponding page in response to the user's trigger operation on the link function element. For the element content length less than the set value, if the element content length is less than the set value, that is, the element content is short text, and the element with short text can identify the service or function of the page, such as page title, music, video, game and other tags. A landing page is a webpage that is displayed to a user after a potential user clicks on an ad or searches with a search engine. Generally, this page will display expanded content related to the clicked ad or search result link, and this page should be search engine optimized for a certain keyword (or phrase). Therefore, the landing page comprehensively displays the provided functions, portals and services, etc., and is closely related to the page business; moreover, the landing page can directly face the user's interaction compared with the subsequent pages, and can better reflect the user's focus on elements. At present, the registration in the promotion process and the order in the promotion are often reached through the promotion channel. The elements on the promotion page are triggered by interactive events, and the promotion content will be displayed or jumped to the merchant page.

Elements fired metrics include element conversion rate and/or element click-through rate.

The times indicator reflects the user's degree of focus on the element. The higher the user's degree of focus on the element, the clearer the reflected user behavior semantics. The user behavior semantics in this embodiment is different from the semantics in images or texts, but is service-oriented user behavior semantics. For example, the user clicks the read button on the page and uses the reading service provided by the page, which can reflect to a certain extent The semantics of the user's behavior is not clear enough to rule out the possibility of misoperation or random operation; in combination, the indicator of the number of times the read button is triggered is within the preset range, reflecting the user's clear reading behavior semantics.

The target element information extracted in this embodiment includes, but is not limited to: element content, element type, and the page where the element is located (which may span multiple uniform resource locators).

In this embodiment of the present application, all user behavior data is obtained by collecting the set of element information on the target page that is triggered by user interaction events; through the attribute of the element associated with the page business and the index of the number of times the element is triggered, the The target element information is extracted from the collection, so as to extract the business-oriented element information that can clearly reflect the semantics of user behavior, so as to improve the application value of the element information for product and operation optimization.

Further, the click event bound to the element, the button type of the element, the link function of the element, the content length of the element less than the set value, the element located on the landing page and the element located on the promotion page can clearly reflect the business attributes of the element, so based on the above The target element information of attribute extraction is the element information oriented to the page business; the conversion rate and/or click rate of the element reflects the user's focusing behavior on the element, reflects the clear behavior semantics, and is conducive to accurately extracting the target element information.

Embodiment 2

FIG. 2 is a flowchart of a method for extracting page element information in Embodiment 2 of the present application. The embodiments of the present application are optimized and improved on the basis of the technical solutions of the foregoing embodiments.

Further, the operation "extract target element information from the element information set according to the attributes of the element associated with the page business and the index of the number of times the element is triggered" is refined into "according to the attributes of the element associated with the page business, from the element Extract the candidate element information set from the information set; extract the target element information from the candidate element information set according to the index of the number of times the element is triggered, so as to quickly extract the target element information and reduce the amount of calculation.

A method for extracting page element information as shown in Figure 2, including:

S201. Collect a set of element information on a target page that is triggered by a user interaction event.

S202. Extract the candidate element information set from the element information set according to the attribute of the element associated with the page service.

The element information set stores various attributes of the element. Based on this, attributes can be directly compared in the element information set, and then the candidate element information set with attributes associated with the page business can be extracted.

Optionally, first extract the element information triggered by the click event from the element information set; then, from the element information triggered by the click event, extract the element information of the button type, the element information of the link type, and the content length less than At least one of the element information of the set value, the element information located on the landing page, and the element information located on the promotion page constitutes a set of candidate element information.

Specifically, after extracting the element information triggered by the click event, extract the element attributes triggered by the click event, including the element type (class), whether it is a link (href), the length of the element content (content), and the page where the element is located. After that, extract the element information of the button (button) type, the element information of the element content length less than the set value, the element information of the link type, the element information of the landing page (Landing Page) and the element information of the promotion page to form candidate elements collection of information. For convenience of description and distinction, the element information in the candidate element information set is referred to as candidate element information.

In this embodiment, the click event can better reflect the user's focus on the element compared with other interaction events; the element information is preferentially selected according to the click event type, and compared to other attributes, the available Element information; and then extract candidate elements according to the button, link, content length and page of the element, which is beneficial to improve the extraction efficiency of element information.

S203 , extracting target element information from the candidate element information set according to the index of the number of times the element is triggered.

This operation includes the following three optional implementations.

A first optional implementation manner: Calculate the conversion rate of each candidate element, and determine, from the candidate element information set, candidate element information whose conversion rate is within a first preset range as target element information.

The second optional implementation manner: Calculate the click-through rate of each candidate element, and determine candidate element information whose click-through rate is within a second preset range from the candidate element information set as the target element information.

The third optional implementation manner: Calculate the conversion rate and click rate of each candidate element, from the candidate element information set, the candidate element information with the conversion rate within the first preset range, and the click rate within the second preset range. The candidate element information within the range is determined as the target element information.

In this embodiment, the conversion rate and the click rate can significantly reflect the user's focusing behavior on elements, and have clear behavioral semantics; while the values of the conversion rate and click rate can reflect the user's degree of focus on the element, and also reflect the intensity of behavioral semantics . Based on this, the first preset range and/or the second preset range can be determined according to business needs, and the conversion rate within the first preset range and/or the click rate within the second preset range can be selected to extract Target element information with different semantic strengths.

This embodiment uses the session as the granularity to calculate the click-through rate and the conversion rate of the candidate element.

Taking the session as the granularity as an example, obtain multiple sessions generated during the interaction between the user and the target page. Each session includes the element information triggered by click events within a preset time period; the preset time period can be 30 minutes, 40 minutes, etc. . When calculating the conversion rate, for each candidate element, the element is scored by calculating the element conversion rate or click-through rate. For each session (session), if there is a click on an element in the session, no matter how many clicks are made, then the element in the session is considered to be converted to 1, otherwise it is 0. Count the number of sessions with a conversion rate of 1 for each candidate element information, and divide by the total number of sessions to obtain the conversion rate of each candidate element information.

When calculating the click-through rate, the number of times each candidate element information is displayed on the target page may be determined according to the number of jumps or refresh times of the target page. Divide the number of sessions containing each candidate element information by the number of times the corresponding candidate element information is displayed on the target page to obtain the click-through rate of each candidate element information.

Optionally, before determining the target element information, the element information whose conversion rate exceeds the first preset threshold and/or the element information whose click rate exceeds the second preset threshold in the candidate element information set is deleted. Specifically, the first preset threshold and the second preset threshold can be set independently. After the conversion rate and/or click rate are calculated for each candidate element information, elements with a high conversion rate and/or click rate need to be eliminated. information. For example, a conversion rate of more than 5% is usually on the high side. These elements are often elements that are routinely reached, and are oriented to the basic business of the page, such as the login button, save button, etc. The information of these elements is difficult to reflect the user's personalized behavior semantics; By deleting the candidate element information with a high frequency index, the element information reflecting the user's personalized behavior semantics can be centrally extracted.

In this embodiment, the attributes can be obtained directly from the element information set, and the times index needs to be obtained by calculation. The element information is first extracted according to the attribute, and then the secondary extraction is carried out according to the times index, which can quickly extract the target element information and reduce the calculation. quantity. Further, with the session as the granularity, the conversion rate and click rate are calculated by whether the user clicks on the candidate element within a preset time period, so as to avoid errors caused by the user repeatedly clicking the candidate element in a short period of time, and improve the conversion rate and click rate. accuracy.

In each of the above embodiments, after extracting the target element information from the element information set according to the attribute of the element associated with the page business and the index of the number of times the element is triggered, the method further includes: according to the target element information, perform an operation on the page to be buried. Bury. Specifically, if code embedding or visual embedding is used to bury the target element information on the page to be embedded, business-oriented element information that can clearly reflect the semantics of user behavior can be collected through embedding.

In this embodiment, according to the target element information, the page to be embedded is embedded, so as to accurately extract the business-oriented element information on the page to be embedded that can clearly reflect the semantics of user behavior, and this embedding method is suitable for primary users. Or users of non-professional analysts, with low technical thresholds, start from the element information collection, fill the gap between the element information collection and user-set embedding points, and produce business-meaningful embedding point recommendation results.

Embodiment 3

FIG. 3 is a structural diagram of a device for extracting page element information in Embodiment 3 of the present application. The embodiment of the present application is suitable for extracting the application value of product and operation optimization from page element information triggered by user interaction behavior. In the case of element information, the device is implemented by software and/or hardware, and is specifically configured in an electronic device with a certain data computing capability.

As shown in FIG. 3, an apparatus 300 for extracting page element information includes: a collection module 301 and an extraction module 302; wherein,

The collection module 301 is configured to collect the element information set triggered by the user interaction event on the target page.

The extraction module 302 is configured to extract target element information from the element information set according to the attribute of the element associated with the page service and the index of the number of times the element is triggered.

In this embodiment of the present application, all user behavior data is obtained by collecting the set of element information on the target page that is triggered by user interaction events; through the attribute of the element associated with the page business and the index of the number of times the element is triggered, the The target element information is extracted from the collection, so as to extract the business-oriented element information that can clearly reflect the semantics of user behavior, so as to improve the application value of the element information for product and operation optimization.

Further, the attributes of the element associated with the page business include: the click event bound to the element, the button type of the element, the link function of the element, the content length of the element less than the set value, the element on the landing page and the element on the promotion page. at least one of;

Metrics for the number of times the element was triggered, including: the element's conversion rate and/or click-through rate.

Further, the extraction module 302 includes a candidate element information set extraction unit and a target element information extraction unit. The candidate element information set extraction unit is used for extracting the candidate element information set from the element information set according to the attribute of the element associated with the page business; the target element information extraction unit is used for extracting the candidate element information set from the candidate element information set according to the index of the number of times the element is triggered , extract the target element information.

Further, the candidate element information set extraction unit is specifically used to extract the element information triggered by the click event from the element information set; from the element information triggered by the click event, extract the element information of the button type and the element of the link type. At least one of the information, the element information whose content length is less than the set value, the element information located on the landing page, and the element information located on the promotion page, constitutes a candidate element information set.

Further, the target element information extraction unit is specifically used to calculate the conversion rate and/or click rate of each candidate element; from the candidate element information set, the candidate element information whose conversion rate is within the first preset range, and/or , and the candidate element information whose click-through rate is within the second preset range is determined as the target element information.

Further, when calculating the conversion rate and/or click rate of each candidate element, the target element information extraction unit is specifically used for: acquiring multiple sessions generated during the interaction between the user and the target page, and each session includes a preset time period. Element information triggered by a click event; calculate the conversion rate of each candidate element according to the number of sessions containing information about each candidate element and the total number of sessions; and/or, according to the session containing information about each candidate element The number of items, and the number of times each candidate element information is displayed on the target page, calculate the click-through rate of each candidate element.

Further, the device also includes a deletion unit, which is used for, from the candidate element information set, element information whose conversion rate is within a first preset range, and/or element information whose click rate is within a second preset range , before determining the target element information, delete the element information whose conversion rate exceeds the first preset threshold and/or the element information whose click rate exceeds the second preset threshold in the candidate element information set.

Further, the device further includes a burying module, wherein the burying module is used for burying the page to be embedded according to the target element information.

The above apparatus for extracting page element information can execute the method for extracting page element information provided by any embodiment of the present application, and has functional modules and beneficial effects corresponding to executing the method for extracting page element information.

Embodiment 4

According to the embodiments of the present application, the present application further provides an electronic device and a readable storage medium.

As shown in FIG. 4 , it is a block diagram of an electronic device implementing the method for extracting page element information according to the embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the application described and/or claimed herein.

As shown in FIG. 4, the electronic device includes: one or more processors 401, a memory 402, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or otherwise as desired. The processor may process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used with multiple memories and multiple memories, if desired. Likewise, multiple electronic devices may be connected, each providing some of the necessary operations (eg, as a server array, a group of blade servers, or a multiprocessor system). In FIG. 4, a processor 401 is taken as an example.

The memory 402 is the non-transitory computer-readable storage medium provided by the present application. Wherein, the memory stores instructions executable by at least one processor, so that the at least one processor executes the method for extracting page element information provided by the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions, and the computer instructions are used to cause the computer to execute the method for extracting page element information provided by the present application.

As a non-transitory computer-readable storage medium, the memory 402 can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions/modules corresponding to the method for extracting page element information in the embodiments of the present application. (For example, the acquisition module 301 and the extraction module 302 shown in FIG. 3 are included). The processor 401 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions and modules stored in the memory 402, that is, the method for extracting page element information in the above method embodiments.

The memory 402 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store a data created by the use of an electronic device that implements a method for extracting page element information data etc. Additionally, memory 402 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 402 may optionally include memory located remotely relative to the processor 401, and these remote memories may be connected to the electronic device performing the method of extracting page element information through a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The electronic device performing the method for extracting page element information may further include: an input device 403 and an output device 404 . The processor 401 , the memory 402 , the input device 403 and the output device 404 may be connected by a bus or in other ways, and the connection by a bus is taken as an example in FIG. 4 .

The input device 403 can receive input numerical or character information, and generate key signal input related to user settings and function control of the electronic device performing the extraction method of page element information, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad , pointing stick, one or more mouse buttons, trackball, joystick and other input devices. Output devices 404 may include display devices, auxiliary lighting devices (eg, LEDs), haptic feedback devices (eg, vibration motors), and the like. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.

Various implementations of the systems and techniques described herein can be implemented in digital electronic circuitry, integrated circuit systems, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.

These computational programs (also referred to as programs, software, software applications, or codes) include machine instructions for programmable processors, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages calculation program. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or apparatus for providing machine instructions and/or data to a programmable processor ( For example, magnetic disks, optical disks, memories, programmable logic devices (PLDs), including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.

The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), the Internet, and blockchain networks.

A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.

According to the technical solutions of the embodiments of the present application, all user behavior data is obtained by collecting the set of element information on the target page that is triggered by user interaction events; The target element information is extracted from the element information set, so as to extract business-oriented element information that can clearly reflect the semantics of user behavior, so as to improve the application value of the element information for product and operation optimization.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present application can be performed in parallel, sequentially or in different orders, and as long as the desired results of the technical solutions disclosed in the present application can be achieved, no limitation is imposed herein.

The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims (11)

1. A method for extracting page element information is characterized by comprising the following steps:

acquiring an element information set triggered by a user interaction event on a target page;

and extracting target element information from the element information set according to the attribute of the element, which is associated with the page service, and the number index of triggered times of the element.

2. The method of claim 1,

the attributes of the elements associated with the page service include: at least one of a click type event bound by the element, a button type of the element, a link function of the element, an element content length smaller than a set value, a landing page of the element and a promotion page of the element;

the number of times the element is triggered index includes: conversion and/or click-through of the element.

3. The method according to claim 1 or 2, wherein the extracting target element information from the element information set according to the attribute of the element associated with the page service and the index of the number of times the element is triggered comprises:

extracting a candidate element information set from the element information set according to the attribute of the element associated with the page service;

and extracting target element information from the candidate element information set according to the number index of triggered elements.

4. The method of claim 3, wherein the extracting a candidate element information set from the element information set according to the attribute of the element associated with the page service comprises:

extracting element information triggered by a click event from the element information set;

and extracting at least one of the element information of the button type, the element information of the link type, the element information of which the content length is smaller than a set value, the element information positioned on the landing page and the element information positioned on the promotion page from the element information triggered by the clicked event to form a candidate element information set.

5. The method according to claim 3, wherein the extracting target element information from the candidate element information set according to the index of the number of times that the element is triggered comprises:

calculating the conversion rate and/or click rate of each candidate element;

and determining the candidate element information with the conversion rate within a first preset range and/or the candidate element information with the click rate within a second preset range from the candidate element information set as target element information.

6. The method of claim 5, wherein calculating the conversion rate and/or click-through rate for each candidate element comprises:

acquiring a plurality of sessions generated in the interaction process of the user and a target page, wherein each session comprises element information triggered by a click event in a preset time period;

calculating the conversion rate of each candidate element according to the number of sessions containing the information of each candidate element and the total number of the sessions; and/or calculating the click rate of each candidate element according to the number of the conversations containing the information of each candidate element and the display times of the information of each candidate element on the target page.

7. The method according to claim 5, before determining, from the candidate element information set, element information with the conversion rate within a first preset range and/or element information with the click rate within a second preset range as target element information, further comprising:

and deleting the element information of which the conversion rate exceeds a first preset threshold value and/or the element information of which the click rate exceeds a second preset threshold value in the candidate element information set.

8. The method according to any one of claims 1 to 7, further comprising, after extracting target element information from the element information set according to an attribute of an element associated with a page service and an index of a number of times the element is triggered:

and embedding points in the page to be embedded according to the target element information.

9. An apparatus for extracting information of a page element, comprising:

the acquisition module is used for acquiring an element information set triggered by a user interaction event on a target page;

and the extracting module is used for extracting target element information from the element information set according to the attribute of the element, which is associated with the page service, and the number index of triggered times of the element.

10. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of extracting page element information as claimed in any one of claims 1 to 8.

11. A non-transitory computer readable storage medium storing computer instructions for causing a computer to execute a method of extracting page element information according to any one of claims 1 to 8.

Images