CN117539568A

CN117539568A - Page processing method and related device

Info

Publication number: CN117539568A
Application number: CN202311487451.8A
Authority: CN
Inventors: 郑强
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2023-11-08
Filing date: 2023-11-08
Publication date: 2024-02-09

Abstract

The embodiment of the application discloses a page processing method and a related device, at least relating to artificial intelligence and other technologies, and being used for realizing customizable automation requirements and saving sustainable maintenance cost. The method comprises the following steps: acquiring an operation page to be processed; extracting element feature vectors and text feature vectors of the operation page to be processed, determining element information of each page element in the operation page to be processed based on the element feature vectors and the text feature vectors, wherein the element feature vectors are used for representing each page element, and the text feature vectors are used for representing text content of each page element; determining page identification of an operation page to be processed based on element information of all page elements; updating the element weight of each page element in the operation page to be processed based on the matching result between the page identifier of the operation page to be processed and the pre-stored page identifier, wherein the element weight is used for indicating the triggering degree when the corresponding page element is executed with triggering operation.

Description

Page processing method and related device

Technical Field

The embodiment of the application relates to the technical field of artificial intelligence, in particular to a page processing method and a related device.

Background

In an application program, a process of automatically executing a series of tasks by writing a program is called an automation task, which can improve work efficiency and the like. For automation tasks of pages, such as game pages, in an application, it is often necessary to configure content, such as page elements, required in an automation script, which is conventionally implemented based on template matching or intrusion into the application.

However, in the mode relying on template matching, a great deal of labor is required to carry out maintenance due to the fact that page elements are iterated quickly and business logic changes quickly; in the manner of intrusion, the application code of the intrusion tool needs to be modified, so that the intrusion tool is inconsistent with the application used by an actual user, and is continuously compatible with different versions of different engines, which causes continuous maintenance cost of the intrusion tool.

Disclosure of Invention

The embodiment of the application provides a page processing method and a related device, which are used for realizing customizable automation requirements and saving sustainable maintenance cost.

In a first aspect, an embodiment of the present application provides a method for processing a page. The method comprises the following steps: acquiring an operation page to be processed; extracting element feature vectors and text feature vectors of the operation page to be processed, and determining element information of each page element in the operation page to be processed based on the element feature vectors and the text feature vectors, wherein the element feature vectors are used for representing each page element, and the text feature vectors are used for representing text content of each page element; determining page identification of the operation page to be processed based on element information of all the page elements; updating the element weight of each page element in the operation page to be processed based on a matching result between the page identifier of the operation page to be processed and the pre-stored page identifier, wherein the element weight is used for indicating the triggering degree when the triggering operation is executed on the corresponding page element.

In a second aspect, an embodiment of the present application provides a page processing apparatus. The page processing apparatus includes, but is not limited to, a terminal device, a server, and the like. The page processing device comprises an acquisition unit, an extraction unit and a processing unit. The acquisition unit is used for acquiring the operation page to be processed. The extraction unit is used for extracting element feature vectors and text feature vectors of the operation pages to be processed, determining element information of each page element in the operation pages to be processed based on the element feature vectors and the text feature vectors, wherein the element feature vectors are used for representing each page element, and the text feature vectors are used for representing text content of each page element. And the processing unit is used for determining the page identification of the operation page to be processed based on the element information of all the page elements. The processing unit is used for updating the element weight of each page element in the operation page to be processed based on the matching result between the page identifier of the operation page to be processed and the prestored page identifier, and the element weight is used for indicating the triggering degree when the corresponding page element is executed to trigger operation.

In some alternative embodiments, the processing unit is configured to: calculating a page hash value of the operation page to be processed based on the element information of each page element, wherein the page hash value is used for indicating the page identification of the operation page to be processed; updating the element weight of each page element in the operation page to be processed based on the comparison result between the page hash value and each hash threshold, wherein each hash threshold is used for indicating the corresponding prestored page identifier.

In some alternative embodiments, the processing unit is configured to: calculating a similar distance between the page hash value and each hash threshold; and updating the element weight of each page element in the operation page to be processed based on a comparison result between the similarity distance and a preset similarity threshold.

In some alternative embodiments, the processing unit is configured to: when the similarity distance is smaller than a preset similarity threshold value, calculating a second weight value based on a first weight value, a target value and a preset weight change speed threshold value, wherein the first weight value is used for indicating the weight of a first page element when the trigger operation is executed on the first page element in the previous execution stage, the target value is the sum of the weights of all page elements in the previous execution stage, the second weight value is used for indicating the weight of the first page element after the trigger operation is executed on the first page element in the current execution stage, and the first page element is any one of the page elements in the operation page to be processed; and adjusting the element weight of the first page element from the first weight value to the second weight value, wherein the first weight value is larger than the second weight value.

In some alternative embodiments, the processing unit is configured to: and when the similarity distance is greater than or equal to the preset similarity threshold, performing assignment processing on the element weight of each page element in the operation page to be processed so as to update and obtain the element weight of each page element in the operation page to be processed.

In some alternative embodiments, the processing unit is further configured to: when the similarity distance is greater than or equal to the preset similarity threshold value, generating page effective information of the operation page to be processed based on the element information of each page element and the page hash value, wherein the page effective information is used for indicating the page condition of the operation page to be processed; and caching page effective information of the operation page to be processed.

In some alternative embodiments, the processing unit is configured to: extracting element names corresponding to the page elements from the element information of each page element respectively; constructing a target character string based on the element names of all the page elements; and carrying out hash processing on the target character string to obtain a page hash value of the page to be operated.

In some alternative embodiments, the extraction unit is configured to: performing feature extraction processing on the operation page to be processed to obtain a page feature vector of the operation page to be processed, wherein the page feature vector is used for representing the page elements and the text contents in the operation page to be processed; performing feature extraction processing on the page feature vector through a preset icon recognition model to obtain an element feature vector of the operation page to be processed; and carrying out feature extraction processing on the page feature vector through a preset text recognition model to obtain the text feature vector of the operation page to be processed.

In some alternative embodiments, the extraction unit is configured to: performing element identification detection processing on the element feature vector to obtain the icon type of the page element and the coordinate position of the page element, and performing text identification detection processing on the text feature vector to obtain the semantic information and the text type of the page element; element information of each page element in the operation page to be processed is determined based on the icon type and the coordinate position of the page element, and the semantic information and the text type of the page element.

In some alternative embodiments, the processing unit is further configured to: before extracting element feature vectors and text feature vectors of the operation page to be processed and determining element information of each page element in the operation page to be processed based on the element feature vectors and the text feature vectors, determining a first page area in the operation page to be processed based on a preset device resolution, wherein the first page area indicates a changed page area. The extraction unit is used for extracting element feature vectors and text feature vectors of a second page area and determining element information of each page element in the second page area based on the element feature vectors and the text feature vectors of the second page area, wherein the second page area is other page areas except the first page area in the operation page to be processed.

In some alternative embodiments, the processing unit is configured to: extracting region width information and region length information from the preset device resolution; and determining a first page area in the operation page to be processed based on the area width information and the area length information.

In some alternative embodiments, the pending operations page comprises a game operations page.

A third aspect of the embodiments of the present application provides a page processing apparatus, including: memory, input/output (I/O) interfaces, and memory. The memory is used for storing program instructions. The processor is configured to execute program instructions in the memory to perform a method for processing a page according to an embodiment of the first aspect.

A fourth aspect of the embodiments of the present application provides a computer-readable storage medium having instructions stored therein, which when run on a computer, cause the computer to perform to execute a method corresponding to an embodiment of the first aspect described above.

A fifth aspect of the embodiments of the present application provides a computer program product comprising instructions which, when run on a computer or processor, cause the computer or processor to perform the above-described method for performing the embodiment of the above-described first aspect.

From the above technical solutions, the embodiments of the present application have the following advantages:

in the embodiment of the application, after the operation page to be processed is acquired, the element feature vector and the text feature vector of the operation page to be processed are extracted, and then the element information of each page element in the operation page to be processed is determined based on the element feature vector and the text feature vector. The element feature vectors mentioned are used to characterize each page element, and the text feature vectors are used to represent the text content of each page element. In this way, the page identification of the operation page to be processed is determined based on the element information of all the page elements, and the element weight of each page element in the operation page to be processed is updated based on the matching result between the page identification of the operation page to be processed and the pre-stored page identification, so as to realize the triggering degree when the corresponding page element is triggered by the element weight indication. According to the method, the feature vector in the operation page to be processed is firstly extracted through the neural network and other models, and then the page identification of the operation page to be processed and the pre-stored page identification are matched on the basis of determining the element information of each page element through the extracted element feature vector and the text feature vector, so that the element weight of each page element in the operation page to be processed is dynamically controlled and updated based on the matching result, the customizable automatic requirement is met, and the sustainable maintenance cost is greatly saved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 shows an application scenario schematic diagram of a method for processing a page according to an embodiment of the present application;

FIG. 2 shows a schematic diagram of a page processing flow provided in an embodiment of the present application;

FIG. 3 illustrates a flowchart of a method of page processing provided by embodiments of the present application;

FIG. 4 illustrates a weighted logic block diagram provided by an embodiment of the present application;

fig. 5 shows a schematic functional block diagram of a page processing apparatus provided in an embodiment of the present application;

fig. 6 shows a schematic hardware structure of the page processing apparatus provided in the embodiment of the present application.

Detailed Description

It will be appreciated that in the specific embodiments of the present application, related data such as user information is referred to, and when the above embodiments of the present application are applied to specific products or technologies, user permissions or consents need to be obtained, and the collection, use and processing of related data need to comply with related laws and regulations and standards of related countries and regions.

The following description of the technical solutions in the embodiments of the present application will be made clearly and completely with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

The terms "first," "second," "third," "fourth" and the like in the description and in the claims of this application and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be capable of being practiced otherwise than as specifically illustrated and described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

As artificial intelligence (artificial intelligence, AI) technology research and advances, artificial intelligence technology expands research and applications in a variety of fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, unmanned, autopilot, unmanned, digital twinning, virtual humans, robotics, artificial intelligence generation content (artificial intelligence generated content, AIGC), conversational interactions, smart medicine, smart customer service, game AI, and the like. It is believed that with the development of technology, artificial intelligence technology will find application in more fields and will be of increasing value.

However, in an automation task for a page, such as a game page, in an application, the conventional approach is typically to configure the content, such as page elements, required in an automation script based on template matching or intrusion into the application. But usually, because of fast page element iteration and fast business logic change, or because of the need of modifying own application program codes, the page elements are inconsistent with the application program used by the actual user, and are continuously compatible with different versions of different engines, which brings about large continuous maintenance cost and is not beneficial to realizing different customization demands of the user.

Therefore, in order to solve the above-mentioned technical problems, the embodiments of the present application provide a method for processing a page. The page processing method provided by the embodiment of the application is realized based on artificial intelligence. Artificial intelligence is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and expand human intelligence, sense the environment, acquire knowledge and use the knowledge to obtain optimal results. In other words, artificial intelligence is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, enables the machines to have functions of sensing, reasoning and decision.

The artificial intelligence technology is a comprehensive subject, and relates to the technology with wide fields, namely the technology with a hardware level and the technology with a software level. Artificial intelligence infrastructure technologies generally include, for example, sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, pre-training model technologies, operation/interaction systems, mechatronics, and the like. The pre-training model is also called a large model and a basic model, and can be widely applied to all large-direction downstream tasks of artificial intelligence after fine adjustment. The artificial intelligence software technology mainly comprises a computer vision technology, a voice technology, a natural language processing technology, machine learning/deep learning and other directions.

In the embodiments of the present application, the artificial intelligence techniques mainly include the above-mentioned directions of Computer Vision (CV), machine Learning (ML), and the like. For example, image processing, image semantic understanding (image semantic understanding, ISU) and the like in computer vision technology may be involved; deep learning (deep learning) in machine learning, including artificial neural networks (artificial neural network), and the like, may also be involved. And more particularly to recurrent neural networks (recurrent neural network, RNN), convolutional neural networks (convolutional neural network, CNN), and the like in artificial neural networks.

The page processing method provided by the application can be applied to page processing equipment with data processing capability, such as terminal equipment, a server, a question-answering robot and the like. The terminal device may include, but is not limited to, a smart phone, a desktop computer, a notebook computer, a tablet computer, a smart speaker, a vehicle-mounted device, a smart watch, a wearable smart device, a smart voice interaction device, a smart home appliance, an aircraft, and the like. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server or the like for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (context delivery network, CDN), basic cloud computing services such as big data and artificial intelligent platforms, and the application is not limited specifically. In addition, the terminal device and the server may be directly connected or indirectly connected by wired communication or wireless communication, and the present application is not particularly limited.

The above-mentioned page processing apparatus may be provided with the capability to implement the above-mentioned computer vision techniques. The mentioned computer vision technology is a science for researching how to make the machine "look at", and further means that the camera and the computer are used to replace human eyes to perform machine vision such as recognition, following, tracing and measuring on the target, and further perform graphic processing, so that the computer is processed into an image more suitable for human eyes to observe or transmit to the instrument to detect. As a scientific discipline, computer vision research-related theory and technology has attempted to build artificial intelligence systems that can acquire information from images or multidimensional data. The large model technology brings important innovation for the development of computer vision technology, and a pre-trained model in the vision fields of swin-transformer, viT, V-MOE, MAE and the like can be rapidly and widely applied to downstream specific tasks through fine tuning. Computer vision techniques typically include image processing, image recognition, image semantic understanding, image retrieval, optical character recognition (optical character recognition, OCR), video processing, video semantic understanding, video content/behavior recognition, three-dimensional object reconstruction, 3D techniques, virtual reality, augmented reality, mixed reality, synchronous localization and map construction, and other techniques, as well as common biometric recognition techniques such as face recognition, fingerprint recognition, and the like. In the embodiment of the application, the recognition processing of elements, text contents and the like in the operation page to be processed is realized mainly by means of technologies such as image processing, image recognition, image semantic understanding and the like in the computer vision technology.

In addition, the page processing device may also have machine learning capabilities. Machine learning is a multi-domain interdisciplinary, involving multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, and the like. It is specially studied how a computer simulates or implements learning behavior of a human to acquire new knowledge or skills, and reorganizes existing knowledge structures to continuously improve own performance. Machine learning is the core of artificial intelligence, a fundamental approach to letting computers have intelligence, which is applied throughout various areas of artificial intelligence. Machine learning and deep learning typically involve neural networks and the like. The pre-training model is the latest development result of deep learning, and integrates the technology. The artificial intelligent model is adopted in the page processing method provided by the embodiment of the application, which mainly relates to application to a neural network, and the recognition processing of element feature vectors, text feature vectors and the like of an operation page to be processed is realized through the neural network.

In order to facilitate understanding of the technical solution of the present application, the method for processing a page provided in the embodiment of the present application is described below in connection with an actual application scenario. Fig. 1 shows an application scenario schematic diagram of a method for processing a page according to an embodiment of the present application.

The application scenario shown in fig. 1 includes a terminal device and a server corresponding to a target object. The server stores various models including, but not limited to, a preset icon recognition model, a preset text recognition model, and the like. In the process that the target object triggers page elements such as icons in the operation page in a clicking mode, the terminal equipment can extract the current operation page to be processed, and then the operation page to be processed is sent to the server. Therefore, after receiving the operation page to be processed, the server further extracts page elements, text contents and the like by using a preset icon recognition model, a preset text recognition model and the like, so that updating processing of element weights of the page elements is dynamically realized based on the extracted information such as the page elements and the text contents, template matching or application program code modification is not needed, and the customizable automatic requirement is met, and the maintenance cost is saved.

Illustratively, with respect to how the server in fig. 1 implements the update processing of the element weights of the page elements, it can be understood with reference to the page processing flow shown in fig. 2. As shown in fig. 2, after obtaining the operation page to be processed, the server first extracts the page feature vector of the operation page to be processed based on a multi-layer convolutional neural network or the like. Alternatively, a feature map may also be generated based on the page feature vector, where the feature map has a size (H ', W', C '), where H' is the height of the feature map, W 'is the height of the feature map, and C' is the number of channels of the feature map. Further, the page feature vectors are processed by the preset icon recognition model shown in fig. 1 to extract corresponding element feature vectors, for example, the element feature vectors are 1×1×64'. Similarly, after extracting the page feature vector, the server may process the page feature vector based on the preset text recognition model shown in fig. 1 to extract a corresponding text feature vector, so as to separate the page element and the text content from the page feature, for example, a vector with a text feature vector of 1×1×64'. After the element feature vector and the text feature vector are obtained through separation, the server determines element information of each page element in the operation page to be processed based on the element feature vector and the text feature vector, and further determines page identification of the operation page to be processed based on the element information of all page elements. After determining the page identifier of the operation page to be processed, the server performs matching processing on the page identifier of the operation page to be processed and the pre-stored page identifier, so that the element weight of each page element in the operation page to be processed is updated based on a matching result, and the triggering degree of the corresponding page element when the triggering operation is performed is indicated through the element weight. Optionally, the effective clicking position in the operation page to be processed can be obtained through the updated element weight, for example, the coordinate area where the page element with the weight meeting some threshold value is located can be used as the effective clicking position.

It should be noted that the above-mentioned preset icon recognition model may include, but is not limited to, CNN, etc., and the embodiment of the present application is not limited thereto. The described pre-set text recognition model may include, but is not limited to RNN, etc., and is not limited in this application.

In addition, the above-mentioned preset icon recognition model, preset text recognition model, and the like may also be deployed in the terminal device, which is not limited in this application. The server may be an independent physical server, a server cluster formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud storage, CDNs, and the like. The terminal device may also be understood by referring to the foregoing, and will not be described herein.

The following describes a page processing method provided in the embodiments of the present application with reference to the accompanying drawings. Fig. 3 shows a flowchart of a method for processing a page according to an embodiment of the present application. As shown in fig. 3, the method for processing a page may include the steps of:

301. and acquiring an operation page to be processed.

In this example, the operation page to be processed may be understood as an operation interface capable of providing various function modules for an object such as a user. For example, in a game scenario, the pending action page may include, but is not limited to, a game action page of a different hierarchy. For example, after a user logs in to a virtual game client through a game account, a game interface A currently displayed to the user can be understood as an operation page to be processed; or after triggering a page element such as one of icons (e.g. "knapsack") in the game interface a by clicking or the like, the user jumps from the game interface a to the game interface B, where the game interface B may be understood as the operation page to be processed, which is not limited in the embodiment of the present application.

It should be noted that the above-mentioned operation page to be processed may be applied to other application scenarios besides the page in the game scenario in practical application, and the embodiment of the present application is not limited.

302. And extracting element feature vectors and text feature vectors of the operation page to be processed, determining element information of each page element in the operation page to be processed based on the element feature vectors and the text feature vectors, wherein the element feature vectors are used for representing each page element, and the text feature vectors are used for representing text content of each page element.

In this example, since in an automation task, it is generally necessary to configure page elements, such as icons, etc., in an operation page, after obtaining an operation page to be processed, it is also necessary to extract relevant feature vectors about the operation page to be processed through the convolutional neural network mentioned in fig. 1 and the like.

For example, after the operation page to be processed is obtained, the operation page to be processed may be used as an input of the multi-layer convolutional neural network, so as to perform feature extraction processing on the operation page to be processed through the multi-layer convolutional neural network, thereby extracting a page feature vector of the operation page to be processed. It is to be appreciated that the page feature vector can indicate page elements and text content in the operational page to be processed. That is, in the page feature vector, the relevant feature of the page element and the relevant feature of the text content are fused.

After the page feature vector is extracted, the related features of the page elements and the related features of the text content are required to be separated. As a schematic description, the page feature vector can be used as the input of a preset icon identification model, and then the feature extraction is carried out on the page feature vector through the preset icon identification model, so that the element feature vector is extracted from the page feature vector. For example, elemental feature vectors include, but are not limited to, features such as edges, shapes, corner points, textures, icon sizes, and the like of icons. And similarly, taking the text feature vector as input of a preset text recognition model, and further carrying out feature extraction on the page feature vector through the preset text recognition model, so as to extract the text feature vector from the page feature vector. For example, text feature vectors may include, but are not limited to, related features such as semantics of an icon, strokes, lines, curves, and the like. It should be noted that each page element can be represented by an element feature vector, such as a "knapsack" icon, a "mall" icon, etc. in a game scene. The text feature vectors described can characterize the text content of each page element, such as the associated description of the "knapsack" icon, and the like, and are not limited in the embodiments of the present application.

In this way, after the element feature vector and the text feature vector are extracted, the element information of each page element in the operation page to be processed is determined based on the element feature vector and the text feature vector. As a schematic description how to determine the element information of each page element, after extracting the element feature vector and the text feature vector, the element feature vector may be subjected to element recognition detection processing by means of softmax, so as to quantitatively determine the icon type of the corresponding page element and the coordinate position of the page element; similarly, text recognition detection processing can be performed on the text feature vector through softmax and the like so as to quantitatively determine the text type and semantic information of the corresponding page element. Then, after the icon type and the coordinate position of the page element and the text type and the semantic information of the page element are obtained, element information of each page element corresponding to the operation page to be processed is generated based on the icon type and the coordinate position of the page element and the text type and the semantic information of the page element. In other words, in the element information of each page element, related information such as the icon type, the coordinate position, the semantic information, and the like of the corresponding page element is included. Illustratively, the content such as the element name of the corresponding page element can be known through the semantic information of the page element.

In some alternative examples, since page elements in some areas of the operation page to be processed are easy to change, and thus, additional large resource consumption and other costs are easy to be brought to the subsequent page matching process, before executing the step 302, the changed page area in the operation page to be processed may be determined, so that the changed page area may be filtered. For example, the first page region in the operation page to be processed may be determined based on a preset device resolution. For example, the region width information and the region length information may be extracted from a preset device resolution, and then a first page region of a region size corresponding to the region width information and the region length information may be determined from the operation page to be processed based on the region width information and the region length information. That is, with respect to the first page area, it can be understood that the page area where the change occurs in the operation page to be processed.

In this way, in the specific execution of step 302, only the feature vectors of the other page areas except the first page area in the operation page to be processed, that is, the element feature vector and the text feature vector of the second page area may be extracted. It should be noted that the second page area is described as the other page areas except the first page area in the operation page to be processed. For example, assume that the original page size of the operation page to be processed is w×h, where w represents the page length and h represents the page width. If the region length information extracted from the preset device resolution is b and the region width information is b, the determined size of the first page region is bxb, and the determined length L1 w-b and width L2 h-b of the second page region are less than or equal to w-b, so that corresponding element feature vectors and text feature vectors can be extracted from the region of L1×L2.

Thus, after the element feature vector and the text feature vector of the second page area are extracted, the element information of each page element in the second page area is determined based on the element feature vector and the text feature vector of the second page area. Further, after determining the element information of each page element in the second page area, determining the page identifier of the operation page to be processed based on the element information of each page element in the second page area, which is specifically understood with reference to the content of the subsequent step 303, which is not described herein in detail.

303. And determining the page identification of the operation page to be processed based on the element information of all the page elements.

In this example, the page identification described is used to reflect the identity of the operational page. Through the page identification, the corresponding operation page can be identified, and then conditions are provided for judging whether the same or similar operation pages exist in the pre-stored page list.

Therefore, after the element information of each page element is determined, the page identifier of the operation page to be processed can be determined based on the element information of all the page elements. For example, in determining the page identifier of the operation page to be processed, the page hash value of the operation page to be processed may be calculated based on the element information of all the page elements, so as to indicate the page identifier of the operation page to be processed through the page hash value.

As an exemplary description, in the process of calculating the page hash value of the operation page to be processed, the element name of the corresponding page element may be extracted from the element information of each page element. Then, a target character string is constructed by the element names of all the extracted page elements, for example, s=s1 & S2& S3& S4& & gt. In this way, after the target character string is obtained, the target character string is subjected to hash processing, so that a page hash value of the operation page to be processed is obtained, for example, hash (S) =hash (S1 & S2& S3& S4& gt.

For example, in the case where n=3, that is, the operation page to be processed includes 3 page elements, for example, icon 1 to icon 3, corresponding icon names, for example, "backpack", "mall", "battle score", may be extracted from the respective element information of icon 1, icon 2 and icon 3. Then, the target character string S is "knapsack & mall & battle", and hash processing is further performed on the target character string S "knapsack & mall & battle" to obtain a page hash value of the operation page to be processed, for example, hash (S) =hash (knapsack & mall & battle). Thus, by the hash (knapsack & mall & battle), the page identification of the operation page to be processed can be identified.

304. Updating the element weight of each page element in the operation page to be processed based on the matching result between the page identifier of the operation page to be processed and the pre-stored page identifier, wherein the element weight is used for indicating the triggering degree when the corresponding page element is executed with triggering operation.

In this example, since other operation pages have been previously stored in the cache, and identified using corresponding page identifications. Then, after determining the page identifier of the operation page to be processed, the page identifier of the operation page to be processed and the pre-stored page identifier can be matched, and then after obtaining a corresponding matching result, the element weight of each page element in the operation page to be processed is updated based on the matching result.

As can be seen from the foregoing content of step 303, the hash value may be used to reflect the page identifier of the corresponding operation page, and then, in the process of matching the page identifier of the operation page to be processed with the pre-stored page identifier, the hash value of the page to be processed may be compared with each hash threshold, and further, based on the comparison result between the hash value of the page to be processed and each hash threshold, the update processing of the element weight of each page element in the operation page to be processed may be completed. It should be noted that, for each hash threshold, a corresponding pre-stored page identifier may be indicated.

As a schematic description, fig. 4 shows a weighted logic structure diagram provided in an embodiment of the present application. As shown in fig. 4, after calculating the page hash value of the operation page to be processed in step 303, the page hash value may be calculated with a similar distance from each hash threshold in the cache hash list. For example, at similar distancesTaking Hamming distance as an example, the calculated Hamming distance isWherein H1 is the operation page to be processed, H2 is the page corresponding to the hash threshold, H1[ i ]]H2[ i ] is the page hash value of the operation page to be processed]For the hash threshold, m represents the number of pages. In this way, after the similarity distance is calculated, the magnitude relation between the similarity distance and the preset similarity threshold is compared, and then the element weight of each page element is updated based on the comparison result between the similarity distance and the preset similarity threshold. It should be noted that the above-mentioned similar distances may include, but are not limited to, cosine similar distances, hamming distances, and the like, which are not limited in the embodiments of the present application.

In addition, the above-mentioned comparison result between the similarity distance and the preset similarity threshold may include a case where the similarity distance is smaller than the preset similarity threshold, or a case where the similarity distance is greater than or equal to the preset similarity threshold. And under the condition that the similarity distance is smaller than a preset similarity threshold value, describing that the operation page similar to the operation page to be processed is prestored, and updating the weight of the page element of the operation page to be processed based on the similar operation page. Otherwise, when the similarity distance is greater than or equal to the preset similarity threshold, the current operation page to be processed is described as a newly generated page, and the weight of the page element in the operation page to be processed is initialized at this time, so that the corresponding weight updating process can be completed. This can be understood in particular with reference to the two cases described below, namely:

Case 1: the similarity distance is smaller than a preset similarity threshold

Illustratively, since the updating process is substantially similar for each page element in the operation to be processed page, the embodiment of the present application will be described by taking only any one page element (i.e., the first page element) as an example.

In addition, in order to perform complete flow coverage for an application program such as a virtual game, it is necessary to perform a trigger operation on a page element on which a trigger operation has been performedAnd shielding, and simultaneously improving the selection rate of page elements which do not execute triggering operation. Therefore, in order to improve the effective rate of flow coverage, the weight of the first page element, that is, the first weight, when the trigger operation is executed on the first page element in the previous execution stage can be obtained first under the condition that the similar distance is smaller than the preset similar threshold value. And then, counting the weights of all page elements in the previous execution stage, and summing the weights of all page elements in the previous execution stage to obtain a target value. Thus, based on the first weight, the target value and the preset weight change speed threshold, a second weight is calculatedWherein W1i is represented as a first weight, λ is a preset weight change speed threshold, λ is a constant for controlling the change speed of the weight, sum (W) is a target value, and i represents an i-th page element. It should be noted that the second weight is smaller than the first weight. In addition, the second weight value can indicate the weight of the first page element after the trigger operation is executed on the first page element in the current execution stage. Thus, after the second weight is obtained, the element weight of the first page element is adjusted from the first weight to the second weight, so that the weight update of the first page element is completed.

For example, taking page element 1 to page element 3, λ=0.5 as an example, if weights of page element 1 to page element 3 in the previous execution stage are 0.2, 0.4, and 0.6, respectively, i.e. w11=0.2, w12=0.4, and w13=0.6. Through calculation, the target value sum (W) =w11+w12+w13=1. Assume that, in the current execution stage, the user triggers clicking on the page element 2, and the calculated second weight w22=w12/(1+λ×sum (W))=0.4/(1+0.5×1) ≡0.27 for that page element. Thus, the element weight of the first page element is again adjusted from 0.4 to 0.27.

It should be noted that, for the element weights of the other page elements except the first page element, the update process may be understood by referring to the update process of the first page element, which is not described herein.

In this way, after all the page elements are completed by performing the trigger operation, the element weight of each page element thereof may be reset to wi=0 for one task. In this way, the page weight of the corresponding page element in the current execution stage is dynamically adjusted through the change of the page element with the trigger operation, so that the element weight of the page element with the trigger operation is reduced, and the element weight of the page element without the trigger operation is increased, thereby improving the accuracy of the trigger of the page element without the trigger operation in the next execution stage.

Case 2: the similarity distance is greater than or equal to a preset similarity threshold

For example, when the similarity distance is greater than or equal to the preset similarity threshold, it is indicated that the page to be processed acquired at this time is a newly generated page, and the related page information is not stored. Therefore, in the updating of the weight of the page element of the newly generated operation page to be processed, the assignment processing can be performed on the element weight of each page element in the operation page to be processed based on the service requirement and the like, so as to initialize the updating to obtain the element weight of each page element in the operation page to be processed. For example, for page element 1 to page element 4, the corresponding element weights are initialized to be 0.2, 0.4, 0.1, 0.3, etc., which is not limited in the embodiment of the present application.

In some optional examples, since the page that is newly generated by the operation page to be processed and acquired at this time is described in the case where the similarity distance is greater than or equal to the preset similarity threshold, the relevant page information is not stored. Therefore, the page valid information of the operation page to be processed can also be generated based on the element information of each page element and the page hash value under the condition that the similarity distance is greater than or equal to the preset similarity threshold value, and the page valid information is used for indicating the page condition of the operation page to be processed. And then caching the page effective information of the operation page to be processed.

For example, taking a game scenario as an example, assume that an operation page to be processed is an operation page (e.g., page B) after triggering a page element "knapsack" in a top page a, and page effective information for the page B is:

as can be seen from the page valid information of the page B, the page valid information of the page B includes at least the page hash value of the own page B, the page hash value of the parent page (i.e., the first page a), and content. Also, as can be seen from the content, the corndinate can indicate the coordinate position of the page element in the page B (e.g., [124,4,176,4,176,24,124,24 ]), and whether the page element "knapsack" can be triggered, and the corresponding element weight, etc.

Therefore, after the element weight of each page element is updated, the page elements in the operation page to be processed can be traversed based on the updated element weights in the subsequent process of constructing the automation task, so that the traversing coverage rate is greatly improved, the customizable automation requirement is met, and the sustainable maintenance cost is greatly saved.

The foregoing description of the solution provided in the embodiments of the present application has been mainly presented in terms of a method. It should be understood that, in order to implement the above-described functions, hardware structures and/or software modules corresponding to the respective functions are included. Those of skill in the art will readily appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The embodiment of the application may divide the functional modules of the apparatus according to the above method example, for example, each functional module may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The integrated modules may be implemented in hardware or in software functional modules. It should be noted that, in the embodiment of the present application, the division of the modules is schematic, which is merely a logic function division, and other division manners may be implemented in actual implementation.

The following describes the page processing apparatus in the embodiment of the present application in detail, and fig. 5 is a schematic diagram of one embodiment of the page processing apparatus provided in the embodiment of the present application. As shown in fig. 5, the page processing apparatus may include an acquisition unit 501, a extraction unit 502, and a processing unit 503.

The acquiring unit 501 is configured to acquire a to-be-processed operation page. It is specifically understood that the foregoing description of step 301 in fig. 3 is referred to, and details are not repeated herein.

The extracting unit 502 is configured to extract an element feature vector and a text feature vector of the operation page to be processed, and determine element information of each page element in the operation page to be processed based on the element feature vector and the text feature vector, where the element feature vector is used to represent each page element, and the text feature vector is used to represent text content of each page element. It is specifically understood that the foregoing description of step 302 in fig. 3 is referred to, and details are not repeated herein.

The processing unit 503 is configured to determine a page identifier of the operation page to be processed based on element information of all page elements. It is specifically understood that the foregoing description of step 303 in fig. 3 is referred to, and details are not repeated herein.

The processing unit 503 is configured to update an element weight of each page element in the operation page to be processed, where the element weight is used to indicate a triggering degree when the corresponding page element is subjected to a triggering operation, based on a matching result between the page identifier of the operation page to be processed and the pre-stored page identifier. It is specifically understood that the foregoing description of step 304 in fig. 3 is referred to, and details are not repeated herein.

In some alternative embodiments, the processing unit 503 is configured to: calculating a page hash value of the operation page to be processed based on element information of all page elements, wherein the page hash value is used for indicating page identification of the operation page to be processed; updating the element weight of each page element in the operation page to be processed based on the comparison result between the page hash value and each hash threshold value, wherein each hash threshold value is used for indicating the corresponding prestored page identification.

In some alternative embodiments, the processing unit 503 is configured to: calculating a similar distance between the page hash value and each hash threshold; and updating the element weight of each page element in the operation page to be processed based on the comparison result between the similarity distance and the preset similarity threshold.

In some alternative embodiments, the processing unit 503 is configured to: when the similarity distance is smaller than a preset similarity threshold value, calculating a second weight value based on a first weight value, a target value and a preset weight change speed threshold value, wherein the first weight value is used for indicating the weight of a first page element when the trigger operation is performed on the first page element in the previous execution stage, the target value is the sum of the weights of all page elements in the previous execution stage, the second weight value is used for indicating the weight of the first page element after the trigger operation is performed on the first page element in the current execution stage, and the first page element is any page element in an operation page to be processed; and adjusting the element weight of the first page element from the first weight to the second weight, wherein the first weight is larger than the second weight.

In some alternative embodiments, the processing unit 503 is configured to: and when the similarity distance is greater than or equal to a preset similarity threshold value, performing assignment processing on the element weight of each page element in the operation page to be processed so as to update and obtain the element weight of each page element in the operation page to be processed.

In some alternative embodiments, the processing unit 503 is further configured to: when the similarity distance is larger than or equal to a preset similarity threshold value, generating page effective information of the operation page to be processed based on element information of each page element and the page hash value, wherein the page effective information is used for indicating page conditions of the operation page to be processed; and caching page valid information of the operation page to be processed.

In some alternative embodiments, the processing unit 503 is configured to: extracting element names of corresponding page elements from element information of each page element respectively; constructing a target character string based on element names of all page elements; and carrying out hash processing on the target character string to obtain a page hash value of the page to be operated.

In some alternative embodiments, the extraction unit 502 is configured to: carrying out feature extraction processing on the operation page to be processed to obtain a page feature vector of the operation page to be processed, wherein the page feature vector is used for representing page elements and text contents in the operation page to be processed; carrying out feature extraction processing on the page feature vector through a preset icon identification model to obtain an element feature vector of an operation page to be processed; and carrying out feature extraction processing on the page feature vector through a preset text recognition model to obtain a text feature vector of the operation page to be processed.

In some alternative embodiments, the extraction unit 502 is configured to: performing element identification detection processing on the element feature vector to obtain the icon type of the page element and the coordinate position of the page element, and performing text identification detection processing on the text feature vector to obtain the semantic information and the text type of the page element; element information of each page element in the operation page to be processed is determined based on the icon type and the coordinate position of the page element, and the semantic information and the text type of the page element.

In some alternative embodiments, the processing unit 503 is further configured to: before extracting element feature vectors and text feature vectors of an operation page to be processed and determining element information of each page element in the operation page to be processed based on the element feature vectors and the text feature vectors, determining a first page area in the operation page to be processed based on a preset device resolution, wherein the first page area is indicated as a changed page area. An extracting unit 502, configured to extract an element feature vector and a text feature vector of a second page area, and determine element information of each page element in the second page area based on the element feature vector and the text feature vector of the second page area, where the second page area is other page areas except the first page area in the operation page to be processed.

In some alternative embodiments, the processing unit 503 is configured to: extracting region width information and region length information from preset device resolution; a first page area in the operation page to be processed is determined based on the area width information and the area length information.

The page processing apparatus in the embodiment of the present application is described above from the viewpoint of a modularized functional entity, and the page processing apparatus in the embodiment of the present application is described below from the viewpoint of hardware processing. Fig. 6 is a schematic structural diagram of a page processing apparatus according to an embodiment of the present application. The page processing apparatus may vary considerably in configuration or performance. The page processing device may include at least one processor 601, communication lines 607, memory 603, and at least one communication interface 604.

The processor 601 may be a general purpose central processing unit (central processing unit, CPU), microprocessor, application-specific integrated circuit (server IC), or one or more integrated circuits for controlling the execution of programs in accordance with aspects of the present application.

Communication line 607 may include a path to communicate information between the above components.

The communication interface 604 uses any transceiver-like device for communicating with other devices or communication networks, such as ethernet, radio access network (radio access network, RAN), wireless local area network (wireless local area networks, WLAN), etc.

The memory 603 may be a read-only memory (ROM) or other type of static storage device that may store static information and instructions, a random access memory (random access memory, RAM) or other type of dynamic storage device that may store information and instructions, and the memory may be stand-alone and coupled to the processor via a communication line 607. The memory may also be integrated with the processor.

The memory 603 is used for storing computer-executable instructions for executing the embodiments of the present application, and is controlled by the processor 601 to execute the instructions. The processor 601 is configured to execute computer-executable instructions stored in the memory 603, thereby implementing the method for page processing provided in the above-described embodiments of the present application.

Alternatively, the computer-executable instructions in the embodiments of the present application may be referred to as application program codes, which are not specifically limited in the embodiments of the present application.

In a specific implementation, the page processing device may include multiple processors, such as processor 601 and processor 602 in fig. 6, as one embodiment. Each of these processors may be a single-core (single-CPU) processor or may be a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (e.g., computer program instructions).

In a specific implementation, the page processing device may also include an output device 605 and an input device 606, as one embodiment. The output device 605 communicates with the processor 601 and may display information in a variety of ways. The input device 606 is in communication with the processor 601 and may receive input of a target object in a variety of ways. For example, the input device 606 may be a mouse, a touch screen device, a sensing device, or the like.

The page processing apparatus described above may be a general-purpose device or a special-purpose device. In a specific implementation, the page processing apparatus may be a server, a terminal, or the like, or a device having a similar structure in fig. 6. The embodiments of the present application are not limited to the type of the page processing apparatus.

It should be noted that the processor 601 in fig. 6 may cause the page processing apparatus to execute the method in the embodiment of the method as in fig. 3 by calling the computer-executable instructions stored in the memory 603.

In particular, the functions/implementation of the extraction unit 502 and the processing unit 503 in fig. 5 may be implemented by the processor 601 in fig. 6 invoking computer executable instructions stored in the memory 603. The functions/implementation of the acquisition unit 501 in fig. 5 may be implemented through the communication interface 604 in fig. 6.

The present application also provides a computer storage medium storing a computer program for electronic data exchange, the computer program causing a computer to execute some or all of the steps of any one of the page processing methods described in the above method embodiments.

The present application also provides a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any one of the methods of page processing as described in the method embodiments above.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.

In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

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

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

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

The above-described embodiments may be implemented in whole or in part by software, hardware, firmware, or any combination thereof, and when implemented in software, may be implemented in whole or in part in the form of a computer program product.

The computer program product includes one or more computer instructions. When the computer-executable instructions are loaded and executed on a computer, the processes or functions in accordance with embodiments of the present application are fully or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). Computer readable storage media can be any available media that can be stored by a computer or data storage devices such as servers, data centers, etc. that contain an integration of one or more available media. Usable media may be magnetic media (e.g., floppy disks, hard disks, magnetic tape), optical media (e.g., DVD), or semiconductor media (e.g., SSD)), or the like.

The above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.

Claims

1. A method of page processing, comprising:

acquiring an operation page to be processed;

extracting element feature vectors and text feature vectors of the operation page to be processed, and determining element information of each page element in the operation page to be processed based on the element feature vectors and the text feature vectors, wherein the element feature vectors are used for representing each page element, and the text feature vectors are used for representing text content of each page element;

determining the page identification of the operation page to be processed based on the element information of all the page elements;

updating the element weight of each page element in the operation page to be processed based on a matching result between the page identifier of the operation page to be processed and the pre-stored page identifier, wherein the element weight is used for indicating the triggering degree when the triggering operation is executed on the corresponding page element.

2. The method of claim 1, wherein determining the page identity of the pending operations page based on element information for all of the page elements comprises:

calculating a page hash value of the operation page to be processed based on element information of all the page elements, wherein the page hash value is used for indicating a page identifier of the operation page to be processed;

updating the element weight of each page element in the operation page to be processed based on the matching result between the page identifier of the operation page to be processed and the prestored page identifier, wherein the updating comprises the following steps:

updating the element weight of each page element in the operation page to be processed based on the comparison result between the page hash value and each hash threshold, wherein each hash threshold is used for indicating the corresponding prestored page identifier.

3. The method of claim 2, wherein updating the element weight of each of the page elements in the pending operations page based on the comparison between the page hash value of the pending operations page and each hash threshold comprises:

calculating a similar distance between the page hash value and each hash threshold;

And updating the element weight of each page element in the operation page to be processed based on a comparison result between the similarity distance and a preset similarity threshold.

4. A method according to claim 3, wherein updating the element weight of each of the page elements in the operation to be processed page based on the comparison between the similarity distance and a preset similarity threshold comprises:

when the similarity distance is smaller than a preset similarity threshold value, calculating a second weight value based on a first weight value, a target value and a preset weight change speed threshold value, wherein the first weight value is used for indicating the weight of a first page element when the trigger operation is executed on the first page element in the previous execution stage, the target value is the sum of the weights of all page elements in the previous execution stage, the second weight value is used for indicating the weight of the first page element after the trigger operation is executed on the first page element in the current execution stage, and the first page element is any one of the page elements in the operation page to be processed;

and adjusting the element weight of the first page element from the first weight value to the second weight value, wherein the first weight value is larger than the second weight value.

5. A method according to claim 3, wherein updating the element weight of each of the page elements in the operation to be processed page based on the comparison between the similarity distance and a preset similarity threshold comprises:

and when the similarity distance is greater than or equal to the preset similarity threshold, performing assignment processing on the element weight of each page element in the operation page to be processed so as to update and obtain the element weight of each page element in the operation page to be processed.

6. The method of claim 5, wherein the method further comprises:

when the similarity distance is greater than or equal to the preset similarity threshold value, generating page effective information of the operation page to be processed based on the element information of each page element and the page hash value, wherein the page effective information is used for indicating the page condition of the operation page to be processed;

and caching page effective information of the operation page to be processed.

7. The method according to any one of claims 2 to 6, wherein calculating a page hash value of the operation page to be processed based on element information of all the page elements comprises:

Extracting element names corresponding to the page elements from the element information of each page element respectively;

constructing a target character string based on the element names of all the page elements;

and carrying out hash processing on the target character string to obtain a page hash value of the page to be operated.

8. The method according to any one of claims 1 to 6, wherein extracting element feature vectors and text feature vectors of the operation page to be processed comprises:

performing feature extraction processing on the operation page to be processed to obtain a page feature vector of the operation page to be processed, wherein the page feature vector is used for representing the page elements and the text contents in the operation page to be processed;

performing feature extraction processing on the page feature vector through a preset icon recognition model to obtain an element feature vector of the operation page to be processed;

and carrying out feature extraction processing on the page feature vector through a preset text recognition model to obtain the text feature vector of the operation page to be processed.

9. The method of any one of claims 1 to 6, wherein determining element information for each page element in the operational page to be processed based on the element feature vector and the text feature vector comprises:

Performing element identification detection processing on the element feature vector to obtain the icon type of the page element and the coordinate position of the page element, and performing text identification detection processing on the text feature vector to obtain the semantic information and the text type of the page element;

element information of each page element in the operation page to be processed is determined based on the icon type and the coordinate position of the page element, and the semantic information and the text type of the page element.

10. The method according to any one of claims 1 to 6, wherein before extracting the element feature vector and the text feature vector of the operation page to be processed, and determining the element information of each page element in the operation page to be processed based on the element feature vector and the text feature vector, the method further comprises:

determining a first page area in the operation page to be processed based on preset equipment resolution, wherein the first page area is indicated as a changed page area;

the extracting the element feature vector and the text feature vector of the operation page to be processed, and determining the element information of each page element in the operation page to be processed based on the element feature vector and the text feature vector, includes:

Extracting element feature vectors and text feature vectors of a second page area, and determining element information of each page element in the second page area based on the element feature vectors and the text feature vectors of the second page area, wherein the second page area is other page areas except the first page area in the operation page to be processed.

11. The method of claim 10, wherein determining the first page region in the operational page to be processed based on a preset device resolution comprises:

extracting region width information and region length information from the preset device resolution;

and determining a first page area in the operation page to be processed based on the area width information and the area length information.

12. The method of any one of claims 1 to 6, wherein the pending operations page comprises a game operations page.

13. A page processing apparatus, comprising:

the acquisition unit is used for acquiring an operation page to be processed;

the extraction unit is used for extracting element feature vectors and text feature vectors of the operation pages to be processed, determining element information of each page element in the operation pages to be processed based on the element feature vectors and the text feature vectors, wherein the element feature vectors are used for representing each page element, and the text feature vectors are used for representing text content of each page element;

The processing unit is used for determining the page identification of the operation page to be processed based on the element information of all the page elements;

the processing unit is used for updating the element weight of each page element in the operation page to be processed based on the matching result between the page identifier of the operation page to be processed and the prestored page identifier, and the element weight is used for indicating the triggering degree when the corresponding page element is executed to trigger operation.

14. A page processing apparatus, characterized by comprising: an input/output (I/O) interface, a processor, and a memory, the memory having program instructions stored therein;

the processor is configured to execute program instructions stored in a memory to perform the method of any one of claims 1 to 12.

15. A computer readable storage medium comprising instructions which, when run on a computer device, cause the computer device to perform the method of any of claims 1 to 12.

16. A computer program product comprising instructions which, when run on a computer device, cause the computer device to perform the method of any of claims 1 to 12.