A navigation back key recognition processing method, device and equipment

Abstract

This application discloses a method, apparatus, and device for identifying and processing navigation back keys. It includes: acquiring a first set of user click interaction data on the navigation back keys, collected by embedding tracking points on navigation back keys in different pages; calculating click distribution characteristics of the navigation back keys based on the first set of click interaction data; acquiring a second set of user click interaction data on a target page, collected by embedding tracking points on the target page; and determining whether the target page has a navigation back key by matching the click distribution characteristics against the second set of click interaction data.

Description

Technical Field

[0001] This specification relates to the field of front-end technology, and in particular to a navigation back button recognition processing method, apparatus, and device. Background Technology

[0002] In some pages of various applications, there is a navigation back button in the upper left corner, which greatly facilitates the user's operation and allows the user to switch more freely between different levels of pages.

[0003] In the actual development of applications, some pages do not have a navigation back button. This may be because it is not needed, but it may also be due to design or development issues. In addition, some pages do have a navigation back button, but its location may not be in the top left corner, which is not standardized and inconsistent with other pages. The latter two situations may affect the user experience and the reliability of the application, and therefore have room for optimization.

[0004] For application service providers, their work may involve a large number of pages or even a massive number of pages. Based on this, in response to the above situation, there is a need for a solution that can help efficiently identify whether a page has a navigation back button. Summary of the Invention

[0005] This specification provides one or more embodiments of a navigation back key recognition processing method, apparatus, device, and storage medium to solve the following technical problem: For application service providers, their work may involve a large number of pages or even a massive number of pages. Based on this, in view of the above situation, there is a need for a solution that helps to efficiently identify whether there is a navigation back key on the page.

[0006] To solve the above-mentioned technical problems, one or more embodiments of this specification are implemented as follows: This specification provides a navigation return key recognition processing method according to one or more embodiments, including: Obtain the set of user first click interaction data on the navigation back button by embedding points on the navigation back button in different pages; Based on the first set of click interaction data, calculate the click distribution characteristics of the navigation back button; Obtain the set of user second click interaction data on the target page by embedding data points on the target page; By matching the click distribution characteristics with the second click interaction data set, it is determined whether the target page has a navigation back button.

[0007] This specification provides a navigation return key recognition processing device according to one or more embodiments, comprising: The first click interaction data set acquisition module acquires the user's first click interaction data set on the navigation back button by embedding points on the navigation back button in different pages; The click distribution feature calculation module calculates the click distribution features of the navigation back key based on the first click interaction data set. The second click interaction data set acquisition module acquires the second click interaction data set of the user on the target page, which is collected by embedding points on the target page. The feature matching navigation back button recognition module determines whether the target page has a navigation back button by matching the click distribution features against the second click interaction data set.

[0008] This specification provides one or more embodiments of a navigation return key recognition processing device, comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform: Obtain the set of user first click interaction data on the navigation back button by embedding points on the navigation back button in different pages; Based on the first set of click interaction data, calculate the click distribution characteristics of the navigation back button; Obtain the set of user second click interaction data on the target page by embedding data points on the target page; By matching the click distribution characteristics with the second click interaction data set, it is determined whether the target page has a navigation back button.

[0009] This specification provides one or more embodiments of a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows: Obtain the set of user first click interaction data on the navigation back button by embedding points on the navigation back button in different pages; Based on the first set of click interaction data, calculate the click distribution characteristics of the navigation back button; Obtain the set of user second click interaction data on the target page by embedding data points on the target page; By matching the click distribution characteristics with the second click interaction data set, it is determined whether the target page has a navigation back button.

[0010] The above-described at least one technical solution adopted in one or more embodiments of this specification can achieve the following beneficial effects: Based on pre-embedded data points for different objects on a large number of pages, a large amount of click interaction data between users and these objects can be automatically collected. Click interaction data corresponding to known navigation back keys can be filtered out, and their click distribution characteristics can be calculated to obtain the click distribution characteristics of the navigation back keys, serving as the basis for identifying the navigation back keys, much like extracting the fingerprint of the navigation back keys. Next, pages that are not yet certain whether they have navigation back keys can be selected from these large numbers of pages as target pages. The number of target pages may also be large, or even refer to... By analyzing all pages of a given application, and since click interaction data has already been automatically collected, the target page's click interaction data set can be directly obtained. Matching the click distribution characteristics of this target page's click interaction data set is similar to fingerprinting a navigation back button. It checks if there are any click interaction data sets that match the specified click distribution characteristics. The object corresponding to these click interaction data sets is very likely the navigation back button. Based on this, it's possible to efficiently identify whether a large number of target pages have a navigation back button, thereby guiding design or development improvements. This allows for the optimization and improvement of pages lacking a navigation back button, contributing to improved user experience and application reliability. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A flowchart illustrating a navigation return key recognition processing method provided in one or more embodiments of this specification; Figure 2 A flowchart illustrating an auxiliary judgment scheme in the navigation return key recognition process provided in one or more embodiments of this specification; Figure 3 Provided for one or more embodiments of this specification Figure 1 A flowchart illustrating a specific implementation of the method; Figure 4 A schematic diagram of a navigation return key recognition processing device provided in one or more embodiments of this specification; Figure 5 This is a schematic diagram of the structure of a navigation return key recognition processing device provided for one or more embodiments of this specification. Detailed Implementation

[0013] This specification provides a navigation return key recognition processing method, apparatus, device, storage medium, and computer program product.

[0014] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0015] As mentioned in the background section, the navigation back button (primarily referring to the back button in the upper left corner of an application's page, such as a button resembling a left-pointing arrow) is crucial in practical applications, providing convenience for users. Especially for medium to large-sized applications, there is a need to standardize and unify the back navigation buttons across their pages to ensure consistency across these pages. Therefore, efficient technical methods are needed to identify whether a large number, or even massive number, of pages within an application lack missing navigation back buttons, allowing designers, developers, and merchants to optimize accordingly.

[0016] The applicant tried two solutions but found problems persisting. The first solution, manual sampling, had low page coverage in actual testing, high labor costs, and was difficult to monitor continuously. The second solution, image recognition, simulated accessing page addresses and taking screenshots, then used image recognition algorithms to identify whether there was a navigation back button in the top left corner of the page. However, many pages may have access level controls, in which case ordinary inspection accounts might be redirected to incorrect pages, leading to inaccurate detection. Furthermore, for large and medium-sized applications, a large number of pages need to be inspected and screenshotted, and new pages are also generated, resulting in high resource consumption.

[0017] To address the aforementioned issues and requirements, this application proposes a solution based on click interaction tracking and interaction hotspot fingerprint matching. This solution can identify, through pure data technology, whether a large number of pages within an application contain navigation back buttons that meet platform requirements. The details are explained below.

[0018] Figure 1 This is a flowchart illustrating a navigation back key recognition processing method provided in one or more embodiments of this specification. The method can be executed by a corresponding server or front-end management device. If the application has spare capacity, it can also be distributed and executed by the application itself on the front end, and then the data can be aggregated and analyzed as needed.

[0019] Figure 1 The process includes the following steps: S102: Obtain the set of user first click interaction data on the navigation back button by embedding points for the navigation back button on different pages.

[0020] The navigation back button is typically located in the upper left corner of an application's (typically including apps on smartphones) page, and this application focuses primarily on the navigation back button in this location. It is usually presented as an arrow such as "<" or "←", or it can be indicated directly with text. Its main function is to return to the previous page.

[0021] It should be noted that in practical applications, depending on the platform or implementation logic, the "return" mentioned here may be based on time sequence, following the user's operation history to go back to the page the user last interacted with, or it may be based on hierarchical relationships, returning to the logical previous level within the application according to the page hierarchy, such as returning from the details page to the list page.

[0022] In one or more embodiments of this specification, users may interact with some operable objects on the page, such as buttons, sliders, hyperlinks, and images. In touchscreen operation, any partial location on the page displayed on the screen can be considered an object that the user may interact with.

[0023] To better understand user interactions with pages, you can pre-select different objects on different pages as the objects for which tracking points are needed, and then track these objects. Specifically, tracking points can be tracked on the object itself or at the exact location of the object.

[0024] The objects to be tracked should at least include a navigation back button, and can also include other optional objects that require it, such as any area on the page (which can be defined based on location rather than function), product links, confirmation buttons, tabs, sub-function entry points, etc. It's even possible to consider tracking as many objects on the page as possible.

[0025] Data tracking, specifically targeting the object to be tracked, involves inserting corresponding data collection code into the front end. When the object is clicked or interacted with, this code is triggered, automatically collecting data related to the click interaction; this is called click interaction data. Click interaction data can indicate that a click event has occurred and can include the object's identifier to indicate which object the user is interacting with. If needed, it can also include more precise click coordinates to indicate the specific location on the object that the user clicked. Similarly, it can include more data if required, such as click time, user identifier, contextual behavior data, and other environmental data.

[0026] In one or more embodiments of this specification, the collected click interaction data can be reported to a designated device, such as a server. Then, from the automatically collected click interaction data, click interaction data whose corresponding object is a navigation back button can be filtered to form a first click interaction data set. In the automatically collected click interaction data, there may be some data whose object is actually a navigation back button, but it was not explicitly stated during the data entry process that the object is a navigation back button; it was merely a local area treated as the object. Such click interaction data, which introduces uncertainty, can be temporarily disregarded. Instead, click interaction data whose corresponding object is explicitly identified as a navigation back button (preferably, for example, a navigation back button belonging to a sufficiently standardized standard back component; the standard and specification here can be defined by the industry, operating system, or the platform itself as needed) should be prioritized.

[0027] The aforementioned event tracking and the collection of click interaction data based on event tracking may not be specifically performed for the purpose of identifying whether a page has a navigation back button, as described in this application. Rather, it's used to more generally analyze application usage (e.g., calculating click-through rates, analyzing user paths, assisting in fault location, analyzing channel traffic, etc.) to better serve users. In this case, this application essentially uses this click interaction data incidentally to achieve a new purpose, thus keeping costs low and allowing for more full utilization of the click interaction data, uncovering and leveraging its greater value.

[0028] S104: Calculate the click distribution characteristics of the navigation back button based on the first click interaction data set.

[0029] The first set of click interaction data can show the click behavior of different users on the navigation back button on different pages. Based on one or more specified dimensions, statistical calculations and / or more complex transformation analysis calculations are performed on this large amount of data to obtain the features corresponding to each dimension, which serve as the click behavior features of the navigation back button. The click behavior features can preferably include click distribution features, which can be calculated relatively efficiently through statistical calculations and other methods.

[0030] In one or more embodiments of this specification, the effective range of the navigation back button on different pages may not be the same. This effective range can be statistically analyzed based on the first click interaction data set to serve as at least a partial click distribution feature. For example, statistically obtaining the X-axis click interval and the Y-axis click interval can represent this effective range, which roughly reflects the effective click area size of the navigation back button (possibly corresponding to the actual pixel range of the navigation back button), or the boundary of the user click distribution. The X-axis click interval and the Y-axis click interval can form a corresponding rectangle; it can be assumed that if the user clicks within this rectangular area, it is likely that they are clicking the navigation back button.

[0031] In one or more embodiments of this specification, the user's click behavior preferences for the navigation back button can also be statistically analyzed based on the first click interaction data set, as at least some click distribution characteristics. For example, this could include the median click coordinates, the specific location on the navigation back button that users tend to click, and the preceding behavior chains under which users are more likely to click the navigation back button, etc. The median click coordinates refers to the coordinates of half of the clicks in the statistically analyzed dataset that are greater than the median, while the coordinates of the other half are not greater than the median. This reflects the user's central tendency in clicking; for example, they might prefer the upper left part of the navigation back button, or other parts, depending on the specific value of the statistically obtained median click coordinates.

[0032] Thus, the overall composition of one or more (preferably multiple but not too many, so as to facilitate precise comparison and avoid overfitting, thus resulting in better reliability) click distribution features of the navigation back key is like the fingerprint of the navigation back key from the perspective of user click interaction. This application uses it as the basis for the next attempt to identify the navigation back key.

[0033] S106: Obtain the set of second click interaction data of the user on the target page, which is collected by embedding points on the target page.

[0034] In one or more embodiments of this specification, a target page refers to a page on which it is necessary to determine whether a navigation back button is present. The number of target pages can be large, as specified according to needs. For example, all pages of a specified application or all pages of a specified functional module included in a specified application can be used as target pages to determine whether a navigation back button is present. Alternatively, all pages whose navigation back button has not yet been determined can be selected and used as target pages. And so on.

[0035] Since the target page can also be one of the pages mentioned earlier that has had its click interaction data collected via pre-embedded tracking, the second set of click interaction data can also be obtained relatively easily. Based on this, it's even possible to consider using all pages with collected tracking data as target pages and identifying them uniformly once, so that subsequent newly generated pages only need to be identified supplementarily.

[0036] S108: By matching the click distribution characteristics with the second click interaction data set, determine whether the target page has a navigation back button.

[0037] In one or more embodiments of this specification, the click distribution characteristics of the tracking objects corresponding to the second click interaction data set can be calculated using the same or similar calculation method. Then, the click distribution characteristics of these objects are matched with the click distribution characteristics of the navigation back button. For objects with a sufficiently high degree of matching, the object is very likely to be the navigation back button. Conversely, if the degree of matching is not high enough, it can be considered not to be the navigation back button.

[0038] Therefore, if the matching degree of all the tracking objects on a target page is insufficient, the target page likely does not have a navigation back button. Conversely, if at least one tracking object on a target page has a sufficiently high matching degree, the target page likely does not have a navigation back button, i.e., that object. This method allows us to determine whether a target page has a navigation back button. Optionally, we can combine this with other identification methods for a more comprehensive judgment.

[0039] pass Figure 1This method automatically collects a large amount of user click interaction data between different objects on a large number of pages, based on pre-embedded tracking points. It then filters out click interaction data corresponding to known navigation back buttons and calculates their click distribution characteristics to obtain the navigation back button's click distribution features. This serves as the basis for identifying the navigation back button, much like extracting its fingerprint. Next, pages whose presence of a navigation back button is uncertain can be selected as target pages. These target pages can be numerous, possibly even representing all pages of the application. Since click interaction data has already been automatically collected, the target page click interaction data set can be directly obtained. Matching the target page's click interaction data set with the click distribution characteristics is like performing fingerprint matching for the navigation back button. If any click interaction data matches the specified distribution characteristics, the object corresponding to that click interaction data is very likely the navigation back button. This allows for efficient identification of whether a large number of target pages have a navigation back button, guiding design or development improvements and optimizing abnormal pages that unreasonably lack a navigation back button, thus improving user experience and application reliability.

[0040] based on Figure 1 In addition to the method described herein, this specification also provides some specific implementation schemes and extension schemes of this method, which will be further explained below.

[0041] In one or more embodiments of this specification, objects such as operation controls on a page may have their own identifiers that distinguish them from other objects. These identifiers can be directly used for tracking and reporting click interaction data. However, in practical applications, some objects may not be standard controls, and some objects may not even be controls at all; for example, they may just be a page area. Therefore, to more reliably distinguish objects, an additional set of encoding rules can be designed to assign new identifiers to different objects and more accurately represent the location of the objects. Such identifiers are called tracking and reporting codes.

[0042] Based on this, click interaction data can be automatically collected using event tracking. This can include, for example, obtaining the click coordinates of a user clicking on an object that has been tracked on the page (which can be used to calculate the median of click coordinates or for other purposes); obtaining the event tracking code generated for the object, which is used to locate the object; associating the click coordinates with the event tracking code to generate the click interaction data for this instance; and collecting more data as needed. Afterward, the collected click interaction data can be automatically reported to the server.

[0043] Tracking codes can indicate (directly contain or indirectly map) multi-level information, such as the application or website to which the object belongs, the page (e.g., product tile page, product detail page), the block within the page (e.g., top function area, main product image display area, bottom recommendation area), the position within the block (e.g., the leftmost function key, the first product in the third row of the recommendation area), and the object type (e.g., function key, image, text, background), to accurately distinguish and locate the object. Based on the selected multi-level information, each object (e.g., each button or each block area) within a specified range (e.g., a specified application) that needs tracking can be encoded. For example, the information at each level can be segmented and encoded to obtain the corresponding tracking code, enabling it to uniquely identify each object within the specified range.

[0044] In one or more embodiments of this specification, the click distribution characteristics may include the median of click coordinates, the X-axis click interval, and the Y-axis click interval. In this case, based on the first click interaction data set, the corresponding median of click coordinates, the X-axis click interval, and the Y-axis click interval are calculated as the click distribution characteristics of the navigation back button; in the second click interaction data set, the second click interaction data subsets corresponding to each tracking object on the target page are obtained; based on the second click interaction data subsets, the corresponding median of click coordinates, the X-axis click interval, and the Y-axis click interval are calculated as the click distribution characteristics of the tracking objects; the click distribution characteristics of each tracking object are matched with the click distribution characteristics of the navigation back button to determine whether the click distribution characteristics of the two are sufficiently similar, and thus determine whether the tracking object is the navigation back button.

[0045] Furthermore, during matching, specifically, the overlap rate of the first rectangle and the second rectangle is calculated. The first rectangle is enclosed by the X-axis and Y-axis click intervals corresponding to the tracked object, and the second rectangle is enclosed by the X-axis and Y-axis click intervals corresponding to the navigation back button. The deviation between the median click coordinates of the tracked object and the median click coordinates of the navigation back button is calculated. Based on the calculated overlap rate and deviation, it is determined that the target page contains a navigation back button. The overlap rate can be the ratio between the area of ​​the overlapping portion of the first and second rectangles and the area of ​​either the first or second rectangle (especially using the second rectangle as a reference).

[0046] For example, determine if the overlap rate is greater than a set threshold and the deviation is less than a set threshold. If so, it can be determined that the target page containing the event tracker has a navigation back button. Otherwise, continue to check other event trackers on the target page. If the results for all event trackers on the target page are negative, it can be determined that the target page does not have a navigation back button. Similarly, you can consider whether the non-overlapping portion is too large. If it is too large, it may not be a navigation back button.

[0047] In the example above, both the X-axis and Y-axis click intervals are combined to determine the click distribution based on the rectangle overlap rate. This improves reliability and aligns with user intuition. Alternatively, one could separately match the X-axis and Y-axis click intervals, specifically the navigation back button and the embedded objects on the target page.

[0048] If more or fewer click distribution features are used, the above approach can also be used for feature matching.

[0049] Furthermore, to improve reliability and fault tolerance, an auxiliary judgment scheme for the navigation return key recognition process is provided for one or more embodiments of this specification, see [link to relevant documentation]. Figure 2 , Figure 2 This is a flowchart illustrating the auxiliary judgment scheme.

[0050] Figure 2 The process includes the following steps: S202: After determining whether the overlap rate is greater than the corresponding set threshold and the deviation is less than the corresponding set threshold, determine whether the overlap rate is greater than the corresponding set threshold and the deviation is greater than the corresponding set threshold.

[0051] To address the various possible scenarios of the aforementioned deviations, a more granular analysis should be conducted to further reduce the potential impact of user subjectivity.

[0052] S204: If so, obtain the click-related operation chain interaction data corresponding to the embedded point object.

[0053] In this scenario, the median click coordinate feature is insufficient for a good match. Furthermore, since the median click coordinate is more closely related to user preferences, it may introduce more errors if the sample data is incomplete. To improve fault tolerance, we can temporarily refrain from determining that the target page lacks a navigation back button and instead proceed with an optional auxiliary judgment process.

[0054] Click-related action chain interaction data refers to the chain of actions users tend to perform before and / or after clicking on a tracked object. This includes things like clicking other buttons, triggering certain business processes, and engaging in browsing or dwelling activities. More representative click-related action chain interaction data can be extracted through statistical analysis or clustering to more accurately and indirectly reflect the relevant information about the tracked object, providing a basis for subsequent judgments.

[0055] S206: By predicting or verifying the previous click object and / or the next click object of the click-related operation chain interaction data, calculate the correlation between the click-related operation chain interaction data and the navigation return key.

[0056] The prediction in step S206 can be achieved through large models or direct statistics. If the clicked object in the previous step and / or the clicked object in the next step, or even a small number of clicked objects within a few nearby steps, is more likely to be the navigation back button, then the correlation between the click-related operation chain interaction data and the navigation back button can be considered to be higher.

[0057] S208: If the correlation is greater than the set threshold, then it is determined that the target page has a navigation back button.

[0058] If the correlation is high enough, it is considered that the object being tracked is very likely the navigation back button.

[0059] An additional advantage of this auxiliary judgment is that the interaction data of the click-related operation chain is also affected by the user's subjectivity. Therefore, the error that may be introduced by the median of the click coordinates is offset to a certain extent. Moreover, since the interaction data of the click-related operation chain may involve specific business, the adaptability to different pages and objects will be improved, avoiding being too general and affecting the accuracy of recognition of certain special pages.

[0060] Furthermore, it can be determined whether the click-related operation chain interaction data is typical enough. For example, is the cluster size large enough? If not, it may not reflect users' preferences well. In this case, the analysis scale can be actively reduced, and one or more clickable objects (objects other than the aforementioned embedded objects) can be selected from the click-related operation chain interaction data. Then, in the same way, the deviation between the median click coordinates of the clickable object and the median click coordinates of the corresponding standard object can be calculated. If the deviation is consistent with the deviation mentioned in step S202 (for example, the difference between the two is less than the set threshold), it can be considered that there may be an imbalance problem in the sample selection, which may cause the deviation to not meet the conditions. Therefore, the deviation result can be ignored, and it can be determined that the target page has a navigation back button, or it can be reported to trigger manual verification.

[0061] Based on the foregoing description, and more intuitively, one or more embodiments of this specification also provide Figure 1 One specific implementation scheme of the method is shown in [reference]. Figure 3 , Figure 3 This is a flowchart illustrating the specific implementation plan.

[0062] exist Figure 3In scenarios where multiple segmented codes are used to represent the reported codes for tracking points, enabling layer-by-layer location, letters can be used to identify each segment, such as "a192.b5743..." shown in the diagram. Taking four segments as an example, segment a indicates which application or website it is in, segment b indicates which page it is on, segment c indicates which section of the page it is in, and segment d indicates the specific location or button within that section.

[0063] Figure 3 The main processes include: Select a back button in a specific application (which can be tracked based on the corresponding application identifier, such as app_id) that can serve as a standard navigation back button. In particular, select a button with a high click volume. For some large and medium-sized applications, the daily click volume of such a back button may reach millions, tens of millions, or even hundreds of millions.

[0064] Based on the pre-implemented general tracking points and the automatic collection and reporting of click interaction data based on tracking points, a large amount or even the entire amount of click interaction data corresponding to the back button is directly obtained (as the first click interaction data set mentioned above). Based on this, the click distribution characteristics of the back button are calculated. Taking a coordinate system with the origin at the upper left corner of the screen, the X-axis to the right, and the Y-axis downward as an example, it is shown below: The median of the click coordinates (11, 22) means that half of all clicks occurred in the region where the X-axis coordinates are less than 11 and the X-axis coordinates are less than 22, while the other half occurred in the region where the X-axis coordinates are greater than this value. The X-axis click interval (1, 103) represents the X-axis coordinate range of all click positions from 1 to 103. The Y-axis click interval (1, 113) represents the Y-axis coordinate range of all click positions from 1 to 113. From the example interval range, it can also be seen that the back button is located in the upper left corner of the screen, approximately 1 pixel away from both the top and left edges. The button length is approximately 103-1=102 pixels, and the height is approximately 113-1=112 pixels. From the example click coordinate median, it can also be seen that since the values ​​are relatively small, users are more likely to click the upper left part of the back button.

[0065] Based on these click distribution characteristics, feature modeling is performed to generate a feature rectangle model, which facilitates efficient feature matching in the subsequent process. The feature rectangle model can represent the rectangular area where the navigation back button should be located, based on the click intervals along the X-axis and Y-axis. In addition, other features such as the median of click coordinates can also be incorporated into the feature rectangle model, so that subsequent intelligent and adaptive multi-dimensional feature comparison can be performed uniformly through the feature rectangle model.

[0066] Assuming all pages in the specified application are considered as target pages, and based on the pre-prepared work mentioned above, the click interaction data corresponding to each target page is directly obtained, forming the second click interaction data set. For the second click interaction data set of a single target page, since this target page may have multiple tracking objects, the second click interaction data set can be further divided into click interaction data subsets corresponding to each tracking object. Feature extraction and comparison can then be performed on each click interaction data subset.

[0067] Figure 3 The example illustrates coordinate extraction and other processing methods, which enable the extraction of click distribution features such as the corresponding X-axis click interval, Y-axis click interval, and median click coordinates for each object.

[0068] Then, feature comparison is performed based on the feature rectangle model. For example, it is determined whether the current object is in the rectangle area where the navigation back button should be located, whether the median of the click coordinates are relatively consistent, and so on.

[0069] If the match is high enough, the current object is marked as a back button, for example, with the value "1". Otherwise, it is marked as a back button, for example, with the value "0".

[0070] By analogy, all objects on all target pages are marked. Then, for each target page, if it contains at least one object marked "1", it is considered that the target page has a back button (i.e., a navigation back key); otherwise, it is considered that the target page does not have a back button.

[0071] Based on this, each target page can be assessed for integrity and a corresponding governance list can be generated to notify designers or developers that abnormal pages need to be addressed and optimized, so that abnormal pages that should have a back button but are missing can be fixed in a timely manner.

[0072] pass Figure 3 The proposed solution establishes an automated comparison mechanism for embedded point coordinate feature fingerprints, proposes a multi-dimensional judgment scheme based on a pre-embedded point system, and realizes a reverse detection model that uses standard components (such as the navigation back button) to infer abnormal pages. This helps overcome the manual sampling and image recognition schemes previously attempted by the applicant. On the one hand, because it can reuse embedded point data and click interaction data that may be prepared for other purposes in advance, it reduces additional costs such as algorithm resources and manpower. Moreover, since it does not require simulated access, it avoids corresponding permission issues and can achieve application-level and overall business-level coverage more broadly and efficiently.

[0073] Based on the same idea, one or more embodiments of this specification also provide apparatus and devices corresponding to the above methods, such as... Figure 4 , Figure 5 As shown. The apparatus and equipment are capable of performing the above methods and related alternatives accordingly.

[0074] Figure 4 This is a schematic diagram of a navigation return key recognition processing device provided in one or more embodiments of this specification. The device includes: The first click interaction data set acquisition module 402 acquires the first click interaction data set of the user on the navigation back button by embedding points for the navigation back button on different pages. The click distribution feature calculation module 404 calculates the click distribution features of the navigation return key based on the first click interaction data set. The second click interaction data set acquisition module 406 acquires the second click interaction data set of the user on the target page, which is collected by embedding points on the target page. The feature matching navigation back key recognition module 408 determines whether the target page has a navigation back key by matching the click distribution features against the second click interaction data set.

[0075] Optionally, it also includes: Before acquiring the user's first click interaction data set on the navigation back key obtained by tracking the navigation back key on different pages, the interaction data acquisition module 410 determines the objects that need to be tracked on different pages. Data points are embedded for the object. Acquire click interaction data automatically collected based on the embedded points when the user clicks the object; The first click interaction data set acquisition module 402 filters the click interaction data whose corresponding object is the navigation back key from the automatically collected click interaction data that has been acquired, and forms the first click interaction data set.

[0076] Optionally, the click interaction tracking module 410 acquires the user's click coordinates on the object when the user clicks on the object, so as to calculate the median of the click coordinates; Obtain the tracking code generated for the object, the tracking code being used to locate the object; The click coordinates are associated with the embedded point reporting code to generate the click interaction data for this time.

[0077] Optionally, the embedded point reporting code indicates the application, page, block within the page, and location within the block to which the object belongs.

[0078] Optionally, the click distribution feature calculation module 404 calculates the median of the corresponding click coordinates, the X-axis click interval, and the Y-axis click interval based on the first click interaction data set, as the click distribution feature of the navigation return key.

[0079] Optionally, the feature matching navigation back key recognition module 408 obtains the second click interaction data subset corresponding to each embedded point object in the target page from the second click interaction data set; Based on the second subset of click interaction data, the median of the corresponding click coordinates, the X-axis click interval, and the Y-axis click interval are calculated as the click distribution characteristics of the embedded object; The click distribution characteristics of each of the aforementioned embedded objects are matched with the click distribution characteristics of the navigation back button.

[0080] Optionally, the feature matching navigation back key recognition module 408 calculates the overlap rate between the first rectangle and the second rectangle, wherein the first rectangle is enclosed by the X-axis click interval and the Y-axis click interval corresponding to the embedded point object, and the second rectangle is enclosed by the X-axis click interval and the Y-axis click interval corresponding to the navigation back key; Calculate the deviation between the median click coordinates of the embedded object and the median click coordinates of the navigation back button; Based on the overlap rate and the deviation, it is determined that the target page contains a navigation back button.

[0081] Optionally, the feature matching navigation return key recognition module 408 determines whether the overlap rate is greater than a corresponding set threshold and whether the deviation is less than a corresponding set threshold. If so, then the target page is determined to have a navigation back button.

[0082] Optionally, the feature matching navigation return key recognition module 408, after determining whether the overlap rate is greater than a corresponding set threshold and the deviation is less than a corresponding set threshold, further includes: Determine whether the overlap rate is greater than a corresponding set threshold, while the deviation is greater than a corresponding set threshold; If so, then obtain the click-related operation chain interaction data corresponding to the embedded point object; The correlation between the click-related operation chain interaction data and the navigation back button is calculated by predicting the previous click object and / or the next click object in the click-related operation chain interaction data. If the correlation is greater than the set threshold, then the target page is determined to have a navigation back button.

[0083] Optionally, it also includes: The target page determination module 412, before determining whether the target page has a navigation back button, filters out all pages in the specified application or all pages of the specified functional modules included in the specified application that have not yet been determined to have a navigation back button. Each of the filtered pages is taken as the target page to determine whether it contains a navigation back button.

[0084] Figure 5 This specification provides a schematic diagram of the structure of a navigation return key recognition processing device according to one or more embodiments. The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform: Obtain the set of user first click interaction data on the navigation back button by embedding points on the navigation back button in different pages; Based on the first set of click interaction data, calculate the click distribution characteristics of the navigation back button; Obtain the set of user second click interaction data on the target page by embedding data points on the target page; By matching the click distribution characteristics with the second click interaction data set, it is determined whether the target page has a navigation back button.

[0085] Based on the same idea, one or more embodiments of this specification also provide a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows: Obtain the set of user first click interaction data on the navigation back button by embedding points on the navigation back button in different pages; Based on the first set of click interaction data, calculate the click distribution characteristics of the navigation back button; Obtain the set of user second click interaction data on the target page by embedding data points on the target page; By matching the click distribution characteristics with the second click interaction data set, it is determined whether the target page has a navigation back button.

[0086] Following the same line of thought, one or more embodiments of this specification also provide a computer program product comprising at least one computer-readable storage medium having computer-readable program instructions stored therein, the computer-readable program instructions including: Obtain the set of user first click interaction data on the navigation back button by embedding points on the navigation back button in different pages; Based on the first set of click interaction data, calculate the click distribution characteristics of the navigation back button; Obtain the set of user second click interaction data on the target page by embedding data points on the target page; By matching the click distribution characteristics with the second click interaction data set, it is determined whether the target page has a navigation back button.

[0087] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the customer's programming of the device. Designers can program a digital system themselves to "integrate" it onto a PLD, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0088] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0089] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0090] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0091] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, produce a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0093] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0094] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0095] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0096] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0097] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0098] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0099] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0100] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0101] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0102] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for recognizing and processing navigation back keys, comprising: Obtain the set of user first click interaction data on the navigation back button by embedding points on the navigation back button in different pages; Based on the first set of click interaction data, calculate the click distribution characteristics of the navigation back button; Obtain the set of user second click interaction data on the target page by embedding data points on the target page; By matching the click distribution characteristics with the second click interaction data set, it is determined whether the target page has a navigation back button.

2. The method as described in claim 1, prior to acquiring the set of user first click interaction data on the navigation back button obtained by embedding tracking points on different pages, the method further includes: Identify the objects for which tracking points are needed on different pages; Data points are embedded for the object. Acquire click interaction data automatically collected based on the embedded points when the user clicks the object; The acquisition of the user's first click interaction data set on the navigation back button, obtained by embedding tracking points on the navigation back button in different pages, specifically includes: From the automatically collected click interaction data that has been acquired, click interaction data corresponding to the navigation back button are filtered out to form the first click interaction data set.

3. The method as described in claim 2, wherein when a user clicks the object, click interaction data is automatically collected based on the embedded points, specifically including: When a user clicks on the object, the user's click coordinates on the object are obtained in order to calculate the median of the click coordinates; Obtain the tracking code generated for the object, the tracking code being used to locate the object; The click coordinates are associated with the embedded point reporting code to generate the click interaction data for this time.

4. The method as described in claim 3, wherein the embedded reporting code indicates the application, page, block within the page, and location within the block to which the object belongs.

5. The method as described in claim 1, wherein calculating the click distribution characteristics of the navigation back button based on the first click interaction data set specifically includes: Based on the first set of click interaction data, the median of the corresponding click coordinates, the X-axis click interval, and the Y-axis click interval are calculated as the click distribution characteristics of the navigation back button.

6. The method as described in claim 5, wherein matching the click distribution features to the second click interaction data set specifically includes: In the second click interaction data set, obtain the second click interaction data subset corresponding to each tracking point object in the target page; Based on the second subset of click interaction data, the median of the corresponding click coordinates, the X-axis click interval, and the Y-axis click interval are calculated as the click distribution characteristics of the embedded object; The click distribution characteristics of each of the aforementioned embedded objects are matched with the click distribution characteristics of the navigation back button.

7. The method as described in claim 6, wherein matching the click distribution features to determine whether the target page has a navigation back button specifically includes: Calculate the overlap rate between the first rectangle and the second rectangle, wherein the first rectangle is enclosed by the X-axis click interval and the Y-axis click interval corresponding to the embedded point object, and the second rectangle is enclosed by the X-axis click interval and the Y-axis click interval corresponding to the navigation back button; Calculate the deviation between the median click coordinates of the embedded object and the median click coordinates of the navigation back button; Based on the overlap rate and the deviation, it is determined that the target page contains a navigation back button.

8. The method of claim 7, wherein determining whether the target page has a navigation back button based on the overlap rate and the deviation specifically includes: Determine whether the overlap rate is greater than a corresponding set threshold and whether the deviation is less than a corresponding set threshold; If so, then the target page is determined to have a navigation back button.

9. The method of claim 8, wherein after determining whether the overlap rate is greater than a corresponding set threshold and the deviation is less than a corresponding set threshold, the method further comprises: Determine whether the overlap rate is greater than a corresponding set threshold, while the deviation is greater than a corresponding set threshold; If so, then obtain the click-related operation chain interaction data corresponding to the embedded point object; The correlation between the click-related operation chain interaction data and the navigation back button is calculated by predicting the previous click object and / or the next click object of the click-related operation chain interaction data. If the correlation is greater than the set threshold, then the target page is determined to have a navigation back button.

10. The method according to any one of claims 1 to 9, wherein before determining whether the target page has a navigation back button, the method further comprises: In the entire page of the specified application or the entire page of the specified functional module contained in the specified application, filter out all pages whose navigation back button has not yet been determined. Each of the filtered pages is taken as the target page to determine whether it contains a navigation back button.

11. A navigation return key recognition processing device, comprising: The first click interaction data set acquisition module acquires the user's first click interaction data set on the navigation back button by embedding points on the navigation back button in different pages; The click distribution feature calculation module calculates the click distribution features of the navigation back key based on the first click interaction data set. The second click interaction data set acquisition module acquires the second click interaction data set of the user on the target page, which is collected by embedding points on the target page. The feature matching navigation back button recognition module determines whether the target page has a navigation back button by matching the click distribution features against the second click interaction data set.

12. The apparatus of claim 11, further comprising: Before acquiring the user's first click interaction data set on the navigation back key obtained by tracking the navigation back key on different pages, the interaction data module of the interaction data module determines the objects that need to be tracked on different pages. Data points are embedded for the object. Acquire click interaction data automatically collected based on the embedded points when the user clicks the object; The first click interaction data set acquisition module filters the click interaction data whose corresponding object is the navigation back button from the automatically collected click interaction data, thus forming the first click interaction data set.

13. The apparatus of claim 12, wherein the click interaction data acquisition module acquires the user's click coordinates on the object when the user clicks on the object, so as to calculate the median of the click coordinates; Obtain the tracking code generated for the object, the tracking code being used to locate the object; The click coordinates are associated with the embedded point reporting code to generate the click interaction data for this time.

14. The apparatus of claim 13, wherein the embedded reporting code indicates the application, page, block within the page, and location within the block to which the object belongs.

15. The apparatus of claim 11, wherein the click distribution feature calculation module calculates the median of the corresponding click coordinates, the X-axis click interval, and the Y-axis click interval based on the first click interaction data set, as the click distribution feature of the navigation return key.

16. The apparatus of claim 15, wherein the feature matching navigation return key recognition module obtains, from the second click interaction data set, a second click interaction data subset corresponding to each embedded point object in the target page; Based on the second subset of click interaction data, the median of the corresponding click coordinates, the X-axis click interval, and the Y-axis click interval are calculated as the click distribution characteristics of the embedded object; The click distribution characteristics of each of the aforementioned embedded objects are matched with the click distribution characteristics of the navigation back button.

17. The apparatus of claim 16, wherein the feature matching navigation return key recognition module calculates the overlap rate between the first rectangle and the second rectangle, wherein, The first rectangle is formed by the X-axis click range and the Y-axis click range corresponding to the embedded point object, and the second rectangle is formed by the X-axis click range and the Y-axis click range corresponding to the navigation back button; Calculate the deviation between the median click coordinates of the embedded object and the median click coordinates of the navigation back button; Based on the overlap rate and the deviation, it is determined that the target page contains a navigation back button.

18. The apparatus of claim 17, wherein the feature matching navigation return key recognition module determines whether the overlap rate is greater than a corresponding set threshold and the deviation is less than a corresponding set threshold; If so, then the target page is determined to have a navigation back button.

19. The apparatus of claim 17, wherein the feature matching navigation return key recognition module, after determining whether the overlap rate is greater than a corresponding set threshold and the deviation is less than a corresponding set threshold, further comprises: Determine whether the overlap rate is greater than a corresponding set threshold, while the deviation is greater than a corresponding set threshold; If so, then obtain the click-related operation chain interaction data corresponding to the embedded point object; The correlation between the click-related operation chain interaction data and the navigation back button is calculated by predicting the previous click object and / or the next click object of the click-related operation chain interaction data. If the correlation is greater than the set threshold, then the target page is determined to have a navigation back button.

20. The apparatus according to any one of claims 11 to 19, further comprising: The target page determination module, before determining whether the target page has a navigation back button, filters out all pages in the specified application or all pages of the specified functional modules included in the specified application that have not yet been determined to have a navigation back button. Each of the filtered pages is taken as the target page to determine whether it contains a navigation back button.

21. A navigation return key recognition processing device, comprising: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform: Obtain the set of user first click interaction data on the navigation back button by embedding points on the navigation back button in different pages; Based on the first set of click interaction data, calculate the click distribution characteristics of the navigation back button; Obtain the set of user second click interaction data on the target page by embedding data points on the target page; By matching the click distribution characteristics with the second click interaction data set, it is determined whether the target page has a navigation back button.

Images