CN117093801A

CN117093801A - Page evaluation method and device, electronic equipment and storage medium

Info

Publication number: CN117093801A
Application number: CN202311307094.2A
Authority: CN
Inventors: 陈星宇; 刘梦思; 吴仕佳; 郑灿双; 魏辰芸
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2023-10-10
Filing date: 2023-10-10
Publication date: 2023-11-21
Anticipated expiration: 2043-10-10
Also published as: CN117093801B

Abstract

The application provides a page evaluation method, a page evaluation device, electronic equipment and a storage medium, and relates to the field of artificial intelligence. The page evaluation method comprises the following steps: receiving an evaluation request for a page to be evaluated; responding to the evaluation request, and establishing a scheduling task corresponding to the page to be evaluated; invoking at least one first service according to the scheduling task to obtain a characteristic value of the page to be evaluated in at least one classification dimension; processing the characteristic value of at least one classification dimension according to the rule file corresponding to the page to be evaluated to obtain a page evaluation result of the page to be evaluated; wherein the rule file includes rules that process feature values of at least one classification dimension. The embodiment of the application is beneficial to flexibly evaluating the page.

Description

Page evaluation method and device, electronic equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of Internet, in particular to a page evaluation method, a page evaluation device, electronic equipment and a storage medium.

Background

In internet marketing, a potential user clicks an advertisement or searches products by using a search engine, and then jumps to a webpage displayed to the user to be a landing page for displaying advertisement content and user behavior conversion. After the advertiser establishes the advertisement landing page, the quality and the effect of the landing page can be evaluated according to the characteristic value of the advertisement landing page in each dimension, for example, the experience grading of the landing page is carried out, the effect suggestion of the landing page is given to the advertiser, the advertiser is assisted to positively adjust the landing page, and the advertisement putting effect of the landing page is improved. However, the page evaluation system for the landing page is obvious in templating at present, and cannot flexibly perform page evaluation.

Disclosure of Invention

The application provides a page evaluation method, a page evaluation device, electronic equipment and a storage medium, which are beneficial to flexibly evaluating pages.

In a first aspect, an embodiment of the present application provides a page evaluation method, including:

receiving an evaluation request for a page to be evaluated;

responding to the evaluation request, and establishing a scheduling task corresponding to the page to be evaluated;

invoking at least one first service according to the scheduling task to obtain a characteristic value of the page to be evaluated in at least one classification dimension;

processing the characteristic value of the at least one classification dimension according to the rule file corresponding to the page to be evaluated to obtain a page evaluation result of the page to be evaluated; wherein the rule file includes rules that process feature values of the at least one classification dimension.

In a second aspect, an embodiment of the present application provides a page evaluation apparatus, including:

the receiving unit is used for receiving an evaluation request aiming at a page to be evaluated;

the task establishing unit is used for responding to the evaluation request and establishing a scheduling task corresponding to the page to be evaluated;

the calling unit is used for calling at least one first service according to the scheduling task to obtain a characteristic value of the page to be evaluated in at least one classification dimension;

The processing unit is used for processing the characteristic value of the at least one classification dimension according to the rule file corresponding to the page to be evaluated to obtain a page evaluation result of the page to be evaluated; wherein the rule file includes rules that process feature values of the at least one classification dimension.

In a third aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory for storing a computer program, the processor being for invoking and running the computer program stored in the memory for performing the method as in the first aspect.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium comprising instructions which, when run on a computer, cause the computer to perform a method as in the first aspect.

In a fifth aspect, embodiments of the present application provide a computer program product comprising computer program instructions for causing a computer to perform the method as in the first aspect.

In a sixth aspect, embodiments of the present application provide a computer program for causing a computer to perform the method as in the first aspect.

According to the embodiment of the application, the scheduling task corresponding to the page to be evaluated is established by responding to the evaluation request of the page to be evaluated, and then at least one first service is called according to the scheduling task to obtain the characteristic value of the page to be evaluated in at least one classification dimension, so that the characteristic data related to the page evaluation of the page to be evaluated is flexibly called according to the page to be evaluated, and the characteristic data is processed according to the corresponding rule file to obtain the page evaluation result. Therefore, the embodiment of the application is beneficial to flexibly evaluating the page.

Drawings

Fig. 1A is a schematic diagram of an application scenario of an embodiment of the present application;

FIG. 1B is a schematic diagram of a floor page experience subsystem interface according to an embodiment of the present application;

FIG. 1C is another schematic diagram of a floor page experience subsystem interface provided by an embodiment of the present application;

fig. 2 is a schematic diagram of another application scenario of the solution according to the embodiment of the present application;

FIG. 3 is a schematic diagram of a system architecture according to an embodiment of the present application;

FIG. 4 is a schematic flow chart of a page evaluation method according to an embodiment of the application;

FIG. 5 is a diagram of the relationship between CVR and indicators of different classification dimensions of a landing page according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a dispatch center and executor interaction process in accordance with an embodiment of the present application;

FIG. 7 is another schematic diagram of a dispatch center and executor interaction process in accordance with an embodiment of the present application;

FIG. 8 is a schematic diagram of a screenshot service performing a screenshot task according to an embodiment of the application;

FIG. 9 is a schematic flow chart diagram of another page evaluation method in accordance with an embodiment of the present application;

FIG. 10 is a schematic diagram of a Rete network;

FIG. 11 is a schematic diagram of rule matching by the rule engine;

FIG. 12 is a schematic diagram of a page evaluation process according to an embodiment of the application;

FIG. 13 is a schematic block diagram of a page evaluation apparatus according to an embodiment of the present application;

fig. 14 is a schematic block diagram of an electronic device in accordance with an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application.

It should be understood that in embodiments of the present application, "B corresponding to a" means that B is associated with a. In one implementation, B may be determined from a. It should also be understood that determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information.

In the description of the present application, unless otherwise indicated, "at least one" means one or more, and "a plurality" means two or more. In addition, "and/or" describes an association relationship of the association object, and indicates that there may be three relationships, for example, a and/or B may indicate: a alone, a and B together, and B alone, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.

It should be further understood that the description of the first, second, etc. in the embodiments of the present application is for illustration and distinction of descriptive objects, and is not intended to represent any limitation on the number of devices in the embodiments of the present application, nor is it intended to constitute any limitation on the embodiments of the present application.

It should also be appreciated that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

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 server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The embodiment of the application is applied to the technical field of artificial intelligence.

Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use 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 technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

With research and advancement of artificial intelligence technology, research and application of artificial intelligence technology is being developed in various fields, such as common smart home, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned, autopilot, unmanned, digital twin, virtual man, robot, artificial Intelligence Generated Content (AIGC), conversational interactions, smart medical, smart customer service, game AI, etc., and it is believed that with the development of technology, artificial intelligence technology will be applied in more fields and with increasing importance value.

Embodiments of the present application may relate to natural language processing (Nature Language processing, NLP) in artificial intelligence technology, an important direction in the computer science and artificial intelligence fields. It is studying various theories and methods that enable effective communication between a person and a computer in natural language. Natural language processing is a science that integrates linguistics, computer science, and mathematics. Thus, the research in this field will involve natural language, i.e. language that people use daily, so it has a close relationship with the research in linguistics. Natural language processing techniques typically include text processing, semantic understanding, machine translation, robotic questions and answers, knowledge graph techniques, and the like.

The embodiment of the application can relate to Computer Vision (CV) technology in artificial intelligence technology, wherein the Computer Vision is a science for researching how to make a machine "see", and further refers to using a camera and a Computer to replace human eyes to recognize, monitor, measure and other machine Vision of a target, and further performing graphic processing, so that the Computer processing becomes an image more suitable for human eyes to observe or transmit to an 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. Computer vision techniques typically include image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content/behavior recognition, three-dimensional object reconstruction, 3D techniques, virtual reality, augmented reality, synchronous positioning, and map construction, among others, as well as common biometric recognition techniques such as face recognition, fingerprint recognition, and others.

Related terms related to the embodiments of the present application are described below.

Landing page: also referred to as "landing pages", "guide pages". In internet marketing, a landing page is a web page that a potential user clicks an advertisement or searches products by using a search engine and then jumps to display to the user, and is used for displaying advertisement content and performing user behavior conversion.

Floor page experience is divided into: and scoring results of page evaluation are carried out on the landing page aiming at the characteristic values of the landing page in all dimensions, such as the content, the material, the screen number, the benefit points, the conversion component number and other dimensional information of the landing page. Illustratively, the experience score may be between 1-100 points.

Conversion Rate (CVR), which is an index for measuring the effect of advertisements Charged (CPA) according to the behavior (Action) as an index, is the Conversion Rate of users clicking advertisements to become an active activation or registration, even pay users. In particular, the CVR may be the number or percentage of people that complete the desired overall process on the landing page. For example, if there is one page of sales items, the conversion rate will be equal to the total number of sales obtained from each visitor.

Facts (fact): the multi-element relationships between objects and between object attributes in a rule engine can be simply understood as attributes and attribute values of the objects.

Rule (rule): the inference statement in the rules engine, consisting of conditions and conclusions, is generally denoted if … then. One regular if part is called left-hand-side (LHS), and the other part is called right-hand-side (RHS).

In the related art, after an advertiser creates an advertisement landing page, the quality and effect of the landing page can be evaluated according to the characteristic values of the advertisement landing page in each dimension, for example, the landing page experience score is carried out, the modification suggestion of the landing page is given to the advertiser, the advertiser is assisted to positively adjust the landing page, and the advertisement putting effect of the landing page is improved. By evaluating the advertisement landing page, a low-quality page can be found out and optimization suggestions can be provided before advertisement delivery; in the advertisement putting process, the flow inclination can be carried out on the page with the quality meeting certain requirements on the landing page, so that the page obtains more showing opportunities; the data of the actual putting effect can be combined after the advertisement is put, the landing page evaluation effect is clearly shown, the actual advertisement effect brought by the landing page evaluation is displayed, and the using power of an advertisement player is increased. However, the page evaluation system for the landing page is obvious in templating at present, and cannot flexibly perform page evaluation.

In order to solve the technical problems, the application provides a method, a device, electronic equipment and a storage medium for evaluating pages, which are beneficial to flexibly evaluating the pages.

Specifically, when an evaluation request for a page to be evaluated is received, a scheduling task corresponding to the page to be evaluated is established in response to the evaluation request; invoking at least one first service according to the scheduling task to obtain a characteristic value of the page to be evaluated in at least one classification dimension; and processing the characteristic value of the at least one classification dimension according to the rule file corresponding to the page to be evaluated to obtain a page evaluation result of the page to be evaluated. Wherein the rule file includes rules that process the feature values of the at least one classification dimension.

Optionally, in the embodiment of the application, in response to an evaluation request of the page to be evaluated, a target industry type to which the page to be evaluated belongs is determined in at least one preset industry type, and then a scheduling task of the page to be evaluated can be established according to the target industry type. Based on the method, the device and the system, the service can be flexibly called according to the industry type of the page to be evaluated to extract the characteristic data related to the page evaluation of the page to be evaluated, and further the page is flexibly evaluated.

The embodiment of the application can be applied to any business scene needing page evaluation, such as an advertisement landing page experience scoring system. The floor page experience scoring system is a function created based on the association of the actual conversion effect and the page configuration request after a large amount of learning analysis is carried out on the advertisement page, and can find problems in page experience and manufacturing. The floor page experience scoring system can also scientifically identify, analyze and judge page conditions through the access of AI capability, and give reasonable optimization guidance.

As shown in FIG. 1A, the landing page experience scoring system can realize the landing page quality inspection function from two aspects of user experience specification and AI learning high conversion characteristics, and obtain the landing page experience score. The user experience specification is a precondition of conversion, so that the user experience friendliness can be improved, and the basic experience problem is eliminated. For example, the page needs to be visible, audible, and quick in page opening, and high in page quality, so that the user's trust is higher. For another example, the conversion component in the page needs to be reasonably used, and can be converted without causing user objection. The AI learning high conversion characteristics can acquire the high conversion page characteristics liked by the user, and the advertising marketing influence is improved. For example, the AI may find common features from pages that are high in conversion, the more similar the high conversion page, the higher the score. For another example, AI intelligence analysis page situation, compare with high conversion page model, know that the page can promote the space.

By means of the method, the page identification and semantic analysis are achieved through AI, image-text content and configuration data of the landing page can be understood, data of multiple dimensions such as element quality, marketing selling points and conversion interaction are extracted, and the data information of the multiple dimensions is input into the experience scoring model. The experience score model can provide the experience score of the detected page by taking the page with high conversion effect as a marker post. In addition, the experience scoring model can also give optimization suggestions of different modules of the landing page, and help understanding by assisting with cases of industry excellent pages, so that page optimization is assisted in multiple aspects, and the conversion effect of the landing page is improved.

The scheme of the embodiment of the application is applied to an actual throwing scene, on one hand, page adjustment analysis suggestions can be given by combining the data condition of the pages, page tuning is helped in real time, and on the other hand, the advertisement exposure strategy can be adjusted according to the experience score of the landing page.

FIG. 1B shows a schematic diagram of a floor page experience subsystem interface providing a report details page of an evaluated page. As shown in fig. 1B, the interface mainly includes the following core modules:

firstly, the experience score, industry ranking and key optimization suggestion module 110 mainly feeds back the overall score condition of the page to the user rapidly, presents the problem of urgent need for optimization, and suggests the user to modify preferentially.

For example, in FIG. 1B the experience score is 88; industry rank is a peer page with a current total score of less than 35%; the key optimization suggestion module prompts 'friendly page experience, please receive and repeat again, and continuously optimizes'.

And secondly, a scoring star level and optimization suggestion module 120 of each configuration detail request, wherein the module displays the actual condition of the page under each scoring item in detail and provides optimization suggestions.

For example, in FIG. 1B the number of stars may show the rating star of the current scoring module; for the excellent configuration of the page, encouragement such as prompt 'accord with industry standard, please keep on'; for the configuration of the page to be optimized, an optimization suggestion can be provided, for example, when the number of the current page screens is short, the page length is prompted to be optimal when the page length is 4-6 screens, and proper adjustment is suggested.

Third, the highlight case module 130 helps the user to better understand the industry high conversion page features and draws the configuration experience of the high conversion page.

For example, the highlight case in FIG. 1B may support viewing configuration details and the excellent points of the industry excellent case.

Optionally, the drop-in page experience subsystem interface may also provide page content previews 140 that may support sliding up and down to view page configuration.

Optionally, the experience subsystem interface on the floor page can also display basic information of the page, for example, the basic information can include page name, page identification (id), and the like, without limitation.

Optionally, the embodiment of the application can also provide an interface for transversely comparing multiple scoring situations after scoring the same page for multiple times. As shown in fig. 1C, the interface may display 4 experience scoring cases of the page, where the horizontal axis is time and the vertical axis is experience scoring, so as to help the user to see the change trend of the page score and summarize the page optimization experience in the page modification and scoring process.

Therefore, according to the scheme provided by the embodiment of the application, the optimization suggestion can be well provided for the advertisement landing page, and the problem of unoccupied optimization for the landing page can be effectively solved. Meanwhile, the advertisement effect of the landing page can be optimized and the VCR of the landing page can be improved by improving the optimization suggestion provided by the application. In addition, the experience of landing pages can be combined with the traffic supporting policy of the advertisement publishing platform, so that higher-quality traffic is provided for high-quality landing pages.

Fig. 2 shows a schematic diagram of an application scenario according to an embodiment of the present application.

As shown in fig. 2, the application scenario involves a terminal 102 and a server 104, where the terminal 102 may communicate data with the server 104 via a communication network. Server 104 may be a background server of terminal 102.

By way of example, the terminal 102 may refer to a device that has rich man-machine interaction, has access to the internet, typically carries various operating systems, and has a high processing power. The terminal device may be a terminal device such as a smart phone, a tablet computer, a portable notebook computer, a desktop computer, a wearable device, a vehicle-mounted device, etc., but is not limited thereto.

The server 104 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs (Content Delivery Network, content delivery networks), basic cloud computing services such as big data and artificial intelligent platforms, and the like. Servers may also become nodes of the blockchain.

The server may be one or more. Where the servers are multiple, there are at least two servers for providing different services and/or there are at least two servers for providing the same service, such as in a load balancing manner, as embodiments of the application are not limited in this respect.

The terminal device and the server may be directly or indirectly connected through wired or wireless communication, which is not limited in the present application. The present application does not limit the number of servers or terminal devices. The scheme provided by the application can be independently completed by the terminal equipment, can be independently completed by the server, and can be completed by the cooperation of the terminal equipment and the server, and the application is not limited to the scheme. Optionally, in the embodiment of the present application, a page evaluation (scoring) system or service, or a page making tool including a page evaluation service, etc. are installed in the terminal 102 or the server 104, which is not limited.

Optionally, as shown in fig. 2, the application scenario may also include a data storage system 106. The data storage system 106 may store data required by the server 104. The data storage system may be integrated on the server 104, or may be deployed on a cloud or other server, without limitation.

It should be understood that fig. 2 is only an exemplary illustration, and does not specifically limit the application scenario of the embodiment of the present application. For example, fig. 2 illustrates one terminal device, one server, and may actually include other numbers of terminal devices and servers, which the present application is not limited to.

The following describes the technical scheme of the embodiments of the present application in detail through some embodiments. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.

Fig. 3 is a schematic diagram of a system architecture according to an embodiment of the present application. The system architecture includes a product layer 310, a gateway layer 320, a component middle stage 330, and a base service 340. Wherein the page evaluation system may be deployed on the in-component platform 330, the in-component platform 330 may further include an interface layer 331, an application layer 332, and a service layer 333. The business layer 333 and the base service 340 may constitute a core service.

The product layer 310 may provide or generate a page to be evaluated, such as various local or third party landing page generating platforms, without limitation.

Gateway layer 320 is responsible for enabling various advertisement landing page generation platforms to access the page assessment system (e.g., landing page experience scoring system) provided by embodiments of the present application. Optionally, the gateway layer 320 also performs at least one security protection such as authentication, current limiting, frequency limiting, etc. for the page evaluation system.

The interface layer 331 is responsible for interfacing with the interface services of various advertisement landing page generating platforms, such as scoring task creation, metadata acquisition, experience formulation encapsulation, index assembly according to industry, and other logic services. The application layer 332 is responsible for scheduling tasks in the page assessment system (by the scheduler), and for detecting messages, events, etc. For example, after receiving the scoring task, the application layer 332 may schedule task assembly according to the resource capability of the core service and the task that the industry needs to perform, and reasonably use the core service resource to complete calculation of each index required by the experience score.

In the core service, an executor in the service layer 333 receives the schedule of the scheduler in the application layer 332, invokes the basic service 340 to calculate and analyze the indexes of each dimension, such as page performance, content extraction, AI capability (content recognition, motion capture, OCR recognition) and the like, and finally provides the indexes to the service layer 333 to calculate experience scores.

The page evaluation method provided by the application will be described in detail below in connection with the above system architecture.

Fig. 4 is a schematic flow chart of a method 400 of page evaluation according to an embodiment of the present application, where the method 400 may be performed by any electronic device having data processing capabilities, for example, the electronic device may be implemented as a server or a terminal device, for example, the server 104 or the terminal 102 in fig. 4, and the present application is not limited in this regard. As shown in fig. 4, method 400 includes steps 410 through 440.

410, an evaluation request for a page to be evaluated is received.

Illustratively, referring to FIG. 3, after a page is created by the page generation platform in the product layer 310, the page may be used as a page to be evaluated to trigger an evaluation request to determine the page quality of the page. Correspondingly, the gateway layer 320 corresponding to the page evaluation system may receive the evaluation request and access the evaluation request to the component center 330.

For example, the page may be an advertisement landing page, with the evaluation request requesting that an experience score for the advertisement landing page be determined. At this point, the page assessment system may score the system for the floor page experience.

420, in response to the evaluation request of the page to be evaluated, establishing a scheduling task corresponding to the page to be evaluated.

For example, with continued reference to fig. 3, the interface layer 331 in the component platform 330 may respond to the evaluation request of the page to be evaluated, and establish a scheduling task corresponding to the page to be evaluated, where the scheduling task is used to invoke a service to implement evaluation of the page to be evaluated, so as to obtain an evaluation result of the page to be evaluated.

In some embodiments, step 420 may be implemented specifically as:

and responding to the evaluation request of the page to be evaluated, determining a target industry type to which the page to be evaluated belongs in at least one preset industry type, and then establishing a scheduling task corresponding to the page to be evaluated according to the target industry type.

Specifically, after determining the target industry type to which the page to be evaluated belongs, a scheduling task of the page to be evaluated corresponding to the target industry type may be established. For example, different pages to be evaluated belonging to one industry type may correspond to the same or similar scheduling task, and different pages to be evaluated belonging to different industry types correspond to different scheduling tasks, so that the scheduling task corresponding to the page to be evaluated may be determined according to the industry type to which the page to be evaluated belongs.

For example, when the page to be evaluated is an advertisement landing page, if the landing page corresponds to the real estate industry, a scheduling task for landing page evaluation corresponding to the real estate industry may be established; if the landing page corresponds to the online gaming industry, a scheduled task for landing page evaluation corresponding to the online gaming industry may be established.

In some embodiments, as one implementation of establishing a scheduling task corresponding to the page to be evaluated according to the target industry type, an evaluation index set of the page to be evaluated may be determined according to the target industry type, and a corresponding scheduling task may be established according to the evaluation index set.

Specifically, the pages to be evaluated of the same industry type may correspond to the same or similar evaluation index sets, and the pages to be evaluated of different industry types may correspond to different evaluation index sets, so that the evaluation index sets of the pages to be evaluated can be determined according to the target industry type of the pages to be evaluated. By way of example, the scheduling center may configure and assemble the sequencing, parallel relationship, etc. of the executor according to the evaluation index sets corresponding to different industry types to obtain the scheduling task.

Wherein the set of evaluation metrics may comprise metrics types of at least one classification dimension. Here, the index type of the at least one classification dimension is an index type required for page evaluation, which is related to page quality and is a set of influencing factors of page quality. Illustratively, the landing page is the last kilometer of ad conversion, and it can affect the ad conversion rate for the set of evaluation indicators corresponding to the ad landing page.

In some embodiments, the set of evaluation metrics may be determined from a relationship of metrics of at least one classification dimension of the landing page corresponding to the target industry type to the conversion of the landing page. Here, the landing page may include a plurality of landing pages that have been put in, and the index of at least one classification dimension of the landing page may include at least one of page content and object behavior data. The object is a display object of the landing page, for example, a user browsing the landing page, and is not limited. Based on this, the index type of at least one classification dimension in the evaluation index set is related to the conversion rate of the landing page, for example, an influence factor having a large influence on the conversion rate of the landing page may be determined as an element in the evaluation index set.

Fig. 5 shows a specific example of the relationship of the index of different classification dimensions of the landing page to the CVR. In the graphs (a) - (d), the horizontal axis represents the eigenvalues, and the vertical axis represents the CVR. (a) The object stay time of the landing page in the figure is positively correlated with the CVR; (b) The number of selling points in the ground page assembly in the figure is positively correlated with CVR; (c) The first screen of the landing page in the figure contains benefit points positively correlated with CVR; (d) The number of conversion components in the landing page in the figure is positively correlated with the CVR. The object stay time is a specific example of object behavior data, and the number of selling points, whether the first screen contains benefit points, the number of conversion components and the like are specific examples of page contents. Based on this, it may be determined that the evaluation index set may include index types of classification dimensions such as object dwell time, number of selling points, whether the first screen contains benefit points, number of conversion components, and the like.

Illustratively, the at least one classification dimension may include at least one of an audiovisual experience, industrial content, conversion interactions, object behaviors. Optionally, each of the at least one classification dimension may also be a primary classification, which may be further divided into at least one secondary classification. As a specific example, as shown in Table 1, the at least one classification dimension may include a primary classification, a secondary classification, and a label. Wherein the labels may also be referred to as rules, which the present application is not limited to.

TABLE 1

The audio-visual experience, the industrialized content and the conversion interaction belong to the characteristic data before the landing page is put in, and can be acquired before the landing page is put in; the object behavior is characteristic data after the landing page is thrown (thrown), and the object behavior can be acquired after the landing page is thrown.

And 430, invoking at least one first service according to the scheduling task to obtain the characteristic value of the page to be evaluated in at least one classification dimension.

Illustratively, with continued reference to FIG. 3, an application layer 332 (e.g., scheduler) in the component 330 may invoke at least one first service according to the scheduling task to obtain a feature value of the page under evaluation in at least one classification dimension. Wherein each of the at least one classification dimension corresponds to a type of index required for the evaluation of the page.

Therefore, by calling at least one first service to acquire the characteristic value of the page to be evaluated in at least one classification dimension, the index capability required for acquiring the page evaluation can be split in a componentization manner, each index corresponds to a fine service (such as the first service), and a plurality of services can acquire the characteristic values of a plurality of dimensions of one page to be evaluated. Therefore, different services can be multiplexed by different pages to be evaluated to extract the characteristic values of the corresponding classification dimensions of the different pages to be evaluated, so that the reusability and the expansibility of the services can be improved, and the page evaluation can be flexibly performed.

In some embodiments, each first service may be structured as an executor, each executor being registered with the dispatch center as a separate function. Illustratively, the dispatch center may be deployed on an application layer 332 (e.g., a scheduler) in a station 330 in the assembly of FIG. 3. Fig. 6 shows a schematic flow chart of the interaction procedure of the dispatch center and the executor. As shown in fig. 6, the interaction process includes steps 601 to 604.

601, the executor sends registration information to the dispatch center.

By way of example, registration information may include actuator group information, internet protocol (Internet Protocol, IP) information, and the like.

The dispatch center updates the registration time or newly added registration 602.

Specifically, when the actuator is an already registered actuator, the scheduling center may update the registration time of the actuator according to the registration information. When the executor is an unregistered executor, the dispatch center may newly register the executor according to the registration information.

For example, the dispatch center may update the xxl _job_region table (where group=xxx and key=xxx value=xxx) based on the registration information. Wherein group is a packet name, and key and value are special identifications respectively.

603, the scheduling center sends scheduling information to the executor.

Specifically, the scheduling center may send scheduling information to the executor according to the scheduling task, so as to call the service corresponding to the executor to obtain the feature value of the page to be evaluated in the corresponding classification dimension.

Optionally, 604, the dispatch center clears the executor that has timed out of heartbeat.

For example, the timing thread may delete directly the executors that have not updated heartbeats more than x seconds from the current time. Wherein x is a positive integer.

FIG. 7 shows another schematic diagram of a dispatch center and executor interaction process. As shown in fig. 7, dispatch center 710 may include a task management 711, an executor management 712, a log management 713 module, a data center module 714, and the like. The task management 711 module may further include a scheduler, a task model, a job processing thread (Jobhander), and other modules, the executor management 712 module may further include a registration manner, an application name, a machine address list, and other modules, and the log management 713 module may further include a scheduling log, a running log, and other modules. Optionally, the dispatch center 710 may also include other modules, such as, but not limited to, running reports, failure alarms, rights control, and other modules.

An executor 720 may include an executor service 721, a job module 722, a log service 723, and a callback thread 724. The job module 722 further includes a scheduling request queue (queue), a job processing thread (Jobhander), and a task thread module.

Wherein the scheduler 715 in the dispatch center 710 invokes the executor service 721 in the executor 720 via a remote procedure call (Remote Procedure Call, RPC) to store the dispatch request in a dispatch request queue in the job module 722. Alternatively, job module 722 may call log service 723 to execute log files. Alternatively, the running log 716 in the dispatch center 710 (in real time) may call the log service 723 in the executor 720 through the RPC to execute the log file. The job module 722 may invoke a callback thread 724 to return the scheduling results from the scheduling result queue (queue) to a callback service 717 in the scheduling center. Illustratively, the callback thread 724 may return the scheduling result via hypertext transfer protocol (Hypertext Transfer Protocol, HTTP).

Optionally, a registration thread 725 may be included in the executor 720 for registering the executor with a registration service 718 in the dispatch center 710. Illustratively, the registration thread 725 may send registration messages to the registration service 718 via HTTP.

Wherein the scheduler 715 may be a scheduler in the task management 711 module; the travel log 716 may be a travel log module in the log management 713 module; callback service 717 may be a module in executor management 712, task management 711, or other services; registration service 718 is a module in executor management 712.

Optionally, after the feature value of at least one classification dimension is obtained, the feature value may be stored as execution data of the page under evaluation into a data layer, such as data center 714.

In some embodiments, the first service may comprise a screenshot service. At this time, the above step 430 may be specifically implemented as: invoking a screenshot service according to the scheduling task, wherein the screenshot service utilizes a system screenshot process to perform screenshot on a page to be evaluated to generate a snapshot picture of the page to be evaluated; and receiving a return result of the screenshot service, wherein the return result comprises a snapshot picture. The snapshot picture is used as input to obtain the feature values of each classification dimension.

For example, the screenshot service may be built according to the capabilities of the browser, producing snapshot pictures for various different pages, which may be used as input data for the audiovisual experience and content characterization of the pages. FIG. 8 illustrates a schematic diagram of a screenshot service performing a screenshot task. As shown in fig. 8, a client where the page assessment system resides may initiate a request to the screenshot service to generate a snapshot picture based on a scheduled task.

Optionally, with continued reference to fig. 8, upon receipt of the request, the screenshot service may perform a anti-swipe check and authentication to determine compliance of the client. For example, the anti-swipe check may be performed from a remote dictionary service (Redis) database. After the anti-swipe checksum identity authentication passes, the screenshot service may send a screenshot task to a message queue, such as a cloud message queue (Cloud Message Queue, CMQ). The screenshot task may include a link to the page to be evaluated. Correspondingly, the screenshot task is stored in a message queue to be executed. Then, the screenshot service may take out the screenshot tasks in the message queue in turn (for example, take out one screenshot task every 1.5 s) by using the system screenshot process, and perform screenshot on the page corresponding to the screenshot task and generate a corresponding snapshot picture. The screenshot may be performed here using the capabilities of the browser. Alternatively, the snapshot picture may be uploaded to cloud object storage (cloud object storage, COS) or creative platform. After the screenshot service acquires the snapshot picture, the snapshot picture can be returned to the client as a result.

In some embodiments, at least one second service may be invoked according to the scheduling task to obtain a rule file corresponding to the page to be evaluated.

Illustratively, with continued reference to fig. 3, an application layer 332 (e.g., a scheduler) in the component platform 330 may invoke at least one second service according to the scheduled task to obtain a rule file corresponding to the page to be evaluated. The rule file comprises rules for processing the characteristic value of at least one classification dimension corresponding to the page to be evaluated. That is, the rule file may be used to process the feature value of at least one classification dimension to obtain a page evaluation result.

Therefore, the rule files corresponding to the pages to be evaluated can be generated by calling at least one second service, so that the second service can be multiplexed by different pages to be evaluated, the reusability and expansibility of the service can be improved, and the page evaluation can be flexibly performed.

In some embodiments, referring to fig. 9, the rule file corresponding to the page to be evaluated may be obtained through the following steps 910 and 920.

910, calling a page evaluation model service to acquire a page evaluation model of a page to be evaluated; wherein the page assessment model includes computational rule logic for the index type of the at least one classification dimension.

The second service includes the page evaluation model service, and the page evaluation model service is used for generating a page evaluation model of the page to be evaluated. For example, when the page to be evaluated is a landing page, the page evaluation model may be a landing page experience score model, which is not limited by the present application.

Optionally, the page evaluation model corresponds to a target industry type to which the page to be evaluated belongs. That is, the page evaluation model of the page to be evaluated may be determined according to the type of the target industry to which the page to be evaluated belongs. The pages to be evaluated belonging to the same industry type correspond to the same or similar page evaluation models, and the pages to be evaluated belonging to different industry types correspond to different page evaluation models.

As one possible implementation, step 910 may be implemented specifically as the following steps 911 to 913.

911, determining an evaluation index set of the page to be evaluated.

Specifically, the evaluation index set includes index types of at least one classification dimension. Specifically, the determining process of the evaluation index set may refer to the description of step 420 in fig. 4, which is not repeated here.

At 912, a weight of the index type for the at least one classification dimension is determined.

Wherein the weight may be an attribute of an index type of the at least one classification dimension, and calculation rule logic for determining the index type for the at least one classification dimension. Specifically, the weight of the index type may represent the importance of the index type, and may also reflect the distinction of different index types to the page. Illustratively, the greater the weight of an index type, the more distinguishing the features of the corresponding index type.

As a possible implementation manner, for the case that the page is a landing page, the weight corresponding to the index type may be determined in combination with the influence of the index type on the conversion rate, or in combination with the actual distribution of the index type in the industry. For example, a floor header screen with a conversion element is a very important index type, but in each particular industry, almost all floor header screens have conversion elements, so the index type does not distinguish between floor pages, and its corresponding weight may be low, for example, 1%. Table 2 shows one example of the weight value corresponding to each tag.

TABLE 2

And 913, calling a page evaluation model service, and obtaining a page evaluation model according to the evaluation index set and the weight. Wherein the calculation rule logic comprises a weighted summation of the eigenvalues of the at least one classification dimension according to the weights.

Alternatively, the calculation rule logic may also be referred to as a scoring formula, i.e. a scoring formula for determining an experience scoring value according to a characteristic value of at least one classification dimension, which is not limited by the present application.

That is, the page assessment model may determine the weight of the index type of each feature dimension, and then perform weighted summation on the feature values of each feature dimension to obtain a page assessment result, such as an experience score.

In some embodiments, the calculation rule logic may include normalizing the feature values of the at least one classification dimension and weighted summing according to weights corresponding to the normalized feature values. That is, the page evaluation model may determine the weight of the index type of each feature dimension, normalize the feature value of each feature dimension, and then perform weighted summation on the feature value after normalization according to the weight to obtain the page evaluation result.

Specifically, the original value ranges of the feature values of different classification dimensions are different, for example, the page loading time is 800 milliseconds (ms), and whether the page has a feature value of 0/1 feature (where 0 may indicate that the page has no video, and 1 may indicate that the page contains video), so that normalization processing needs to be performed on the feature values of different dimensions, for example, normalization of the feature values to be consistent with the experience range (for example, a range of 0-100).

For example, the normalization processing may be performed by a linear normalization method (may also be referred to as a max-min normalization method, (x-min)/(max-min)), a zero-mean normalization method (z-score), or the like, without limitation. As a specific example, for whether a page has a feature value of a video, a normalization process may be performed by using a max-min normalization method, as shown in table 3 below:

TABLE 3 Table 3

By the normalization processing of table 3, whether the page has a feature value of 0/1 of video can be expressed as a feature value of 0/100.

And 920, calling a rule extraction service to extract rules of the page evaluation model to obtain a rule file corresponding to the page to be evaluated.

Specifically, a rule extraction service may be invoked to perform rule extraction on the calculation rule logic of the index type of each classification dimension included in the page evaluation model, so as to obtain a rule file of the page to be evaluated.

In some embodiments, a rule extraction service may be invoked, and the computation rule logic of the index of the at least one classification dimension is processed by using a Rete algorithm to obtain a Rete network; and obtaining a rule file according to the Rete network.

The rule extraction service may split the scoring formula corresponding to the calculation rule logic by using a Rete algorithm to obtain a corresponding Rete network, where the scoring formula includes facts (fact), rules (rule), LHS, RHS, and rule patterns (pattern), and further, a rule file may be obtained according to the Rete network.

Fig. 10 shows a schematic diagram of a Rete network. The root node is an entry for all objects to enter the network, and only one root node exists in one network. The fact that a type node (type node) is entered immediately after entering the Rete network from the root node provides the ability to filter objects by object type, by which the rule engine can do no additional work. The type node may be propagated to the select node (select node), the left input node (LeftInputAdapterNode) of the Beta node, and the Beta node. A select node (also known as Alpha node) is a model of the conditional part of a rule, typically used to evaluate the literal condition. The input node on the left of the Beta node acts to input an object and propagates as a list of single objects. Beta nodes are nodes with two inputs for comparing two objects. Beta nodes mainly contain connection nodes (Join nodes). The connection node is a node for a Join operation, and corresponds to a table Join operation of the database. Propagation to one end node (Terminal node) indicates that a single rule matches all conditions. There may be multiple end nodes in the network, which may also occur when there is an or in a single rule. When pattern matching is performed, the inference engine asserts facts, establishes a work storage element (working memory element, WME) for each fact, and then starts matching WME from the root node of the Rete network until entering the end node. When a rule is activated, a corresponding activation may be established and a rule file stored to the agenda.

The Rete algorithm adopts a space time-shifting strategy to buffer the intermediate calculation results, such as the calculation results of Alpha nodes are buffered in Alpha buffers (Alpha Memory), and the calculation results of Beta nodes are buffered in Beta buffers (Beta Memory), so that the calculation efficiency can be improved.

In some embodiments, each second service may be structured as an executor that may register with the dispatch center as a separate function. Specifically, the process of scheduling the second service (such as the page evaluation model service and the rule extraction service) is similar to that of scheduling the first service, and reference may be made to the related descriptions in fig. 6 and fig. 7, which are not repeated here.

By way of example, the rule file may be a standard domain specific language (Domain Specific Language, DSL) rule file. As a specific example, DSL may be Java language, C language, or the like, without limitation.

Alternatively, the rule file may correspond to an industry type to which the page to be evaluated belongs. For example, rule files corresponding to pages to be evaluated belonging to the same industry type are the same, and rule files corresponding to pages to be evaluated belonging to different industry types are different.

And 440, processing the characteristic value of at least one classification dimension according to the rule file corresponding to the page to be evaluated to obtain a page evaluation result of the page to be evaluated.

In some embodiments, the rule file corresponds to a target industry type to which the page to be evaluated belongs. For example, the rule file can be extracted and matched according to the type of the target industry to which the page to be evaluated belongs, so that the rule file corresponding to the type of the industry performs evaluation feedback on the page to obtain the page evaluation result of the page.

FIG. 11 illustrates a schematic diagram of rule matching by the rule engine. As shown in fig. 11, the rules may be generated as business rules 1110 by encapsulation of the business codes and stored in a rule space (production memory) 1121 in a rule engine 1120. When evaluating the page, the rule engine 1120 may store the feature value of each classification dimension obtained by each first service as a fact in the working space (working memory) 1123, and the matching fact and rule (match between facts and rules) 1122 module selects a corresponding business rule to process the feature value of each classification dimension, and outputs a page evaluation result of the page to be evaluated corresponding to the agenda 1123. Wherein both the rule space 1121 and the workspace 1123 may be provided in a data storage layer.

Illustratively, the feature values of each classification dimension are input as facts to the root node of the rete network in fig. 10, and then propagated into the corresponding type node and the selection node according to the classification, and reach the corresponding terminal node according to the stored corresponding attribute and the connection node. As an example, the feature value of each classification dimension may reach one terminal node, and the experience score stack corresponding to each terminal node may obtain the total experience score corresponding to the page to be evaluated.

Therefore, in the embodiment of the application, the scheduling task corresponding to the page to be evaluated is established by responding to the evaluation request of the page to be evaluated, and then at least one first service is called according to the scheduling task to obtain the characteristic value of the page to be evaluated in at least one classification dimension, so that the characteristic data related to the page evaluation of the page to be evaluated is flexibly called according to the page to be evaluated, and the characteristic data is processed according to the corresponding rule file to obtain the page evaluation result. Therefore, the embodiment of the application is beneficial to flexibly evaluating the page.

Fig. 12 shows a schematic diagram of a page evaluation flow provided by an embodiment of the present application. The page assessment flow applies to the experience score scoring system, including business system 1210, middle gateway 1220, component middle 1230, and core services 1230. Wherein business system 1210 may be an example of product layer 310 in fig. 3, middle stage gateway 1220 may be an example of gateway layer 320 in fig. 3, middle stage in component 1230 may be an example of middle stage in component 330 in fig. 3, and core service 1230 may be an example of base service 340 in fig. 3, particularly as described with reference to fig. 3.

As shown in fig. 12, the page evaluation flow includes steps S1 to S7.

S1, the business system 1210 initiates a page scoring process.

Specifically, the business system 1210, such as the triggering experience sub-function therein, may send a business request to the component middle station 1230 through the middle station gateway 1220 to initiate the page scoring process.

S2, the interface layer in the in-component station 1230 generates scheduling tasks.

For example, a task creation interface may be included in the interface layer for generating scheduling tasks in response to page scoring flows triggered by business system 1210. As shown in fig. 12, the scheduled tasks may be stored in a task queue or database (db) and the queuing scheduler executes the corresponding tasks.

S3, the scheduler 1231 in the in-component station 1230 dispatches tasks to the executor.

Illustratively, the scheduler 1230 may perform reasonable task processing according to the scheduled task and the resource allocation situation, and may dispatch specific tasks to each executor. By way of example, scheduler 1231 may dispatch tasks to various executives via an RPC, as the application is not limited in this regard.

S4, an executor 1231 in the in-component platform 1230 runs logic corresponding to each task.

As one example, the executor 1 may perform task 1, and task 1 may include tasks such as rule extraction, picture scoring, landing page scoring, and the like. As another example, the executor 2 may execute task 2, task 2 including tasks of rule extraction, picture scoring, scoring models, and the like.

S5, the executor 1231 invokes the core service 1240.

Specifically, the executor 1231 invokes the corresponding service to complete the corresponding task according to the specific task type. By way of example, core services 1240 may include, without limitation, a landing page extraction service, a picture AI service, a landing page scoring model service, and so forth.

S6, the in-assembly platform 1230 aggregates the processing results of the executor to generate results.

For example, when the executor calls the service to obtain the characteristic values of the pages to be evaluated in each classification dimension and calls the service to obtain the rule file, the characteristic values can be used as the fact input rule file to output page experience scores, so that the aggregation of the processing results of the executors is realized.

S7, the in-component platform 1230 returns the results to the business system 1210.

Specifically, the component middle stage 1230 may return the result obtained by aggregation in S6 to the service system 1210 through the middle stage gateway 1220. As one possible implementation, an experience score pull interface may be provided in an interface layer 1232 in the in-component platform 1230, which may return experience scores to the business system 1210 in response to an experience score query request of the experience score query in the business system 1210.

Therefore, in the embodiment of the application, the scheduling task corresponding to the page to be evaluated is established in response to the page scoring flow, and at least one core service is called according to the scheduling task, so that the service is flexibly called to obtain the page experience scoring result. Therefore, the embodiment of the application is beneficial to flexibly evaluating the page.

The specific embodiments of the present application have been described in detail above with reference to the accompanying drawings, but the present application is not limited to the specific details of the above embodiments, and various simple modifications can be made to the technical solution of the present application within the scope of the technical concept of the present application, and all the simple modifications belong to the protection scope of the present application. For example, the specific features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various possible combinations are not described further. As another example, any combination of the various embodiments of the present application may be made without departing from the spirit of the present application, which should also be regarded as the disclosure of the present application.

It should be further understood that, in the various method embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present application. It is to be understood that the numbers may be interchanged where appropriate such that the described embodiments of the application may be practiced otherwise than as shown or described.

The method embodiments of the present application are described above in detail, and the apparatus embodiments of the present application are described below in detail with reference to fig. 13 to 14.

Fig. 13 is a schematic block diagram of the page evaluating apparatus 10 of the embodiment of the present application. As shown in fig. 13, the page evaluating apparatus 10 may include a receiving unit 11, a task establishing unit 12, a calling unit 13, and a processing unit 14.

A receiving unit 11 for receiving an evaluation request for a page to be evaluated;

a task establishing unit 12, configured to establish a scheduling task corresponding to the page to be evaluated in response to the evaluation request;

a calling unit 13, configured to call at least one first service according to the scheduling task, so as to obtain a feature value of the page to be evaluated in at least one classification dimension;

the processing unit 14 is configured to process the feature value of the at least one classification dimension according to the rule file corresponding to the page to be evaluated, so as to obtain a page evaluation result of the page to be evaluated; wherein the rule file includes rules that process feature values of the at least one classification dimension.

In some embodiments, the task creation unit 12 is specifically configured to:

responding to the evaluation request, and determining a target industry type to which the page to be evaluated belongs from at least one preset industry type;

And establishing a scheduling task corresponding to the page to be evaluated according to the target industry type.

In some embodiments, the task creation unit 12 is specifically configured to:

determining an evaluation index set of the page to be evaluated according to the target industry type; wherein the set of evaluation metrics includes a metric type of the at least one classification dimension;

and establishing the scheduling task according to the evaluation index set.

In some embodiments, the rule file corresponds to the target industry type.

In some embodiments, the scheduling unit 13 is specifically configured to:

invoking a screenshot service according to the scheduling task, wherein the screenshot service utilizes a system screenshot process to perform screenshot on the page to be evaluated to generate a snapshot picture of the page to be evaluated; the snapshot picture is used for obtaining the characteristic value as input; wherein the first service comprises the screenshot service;

and receiving a return result of the screenshot service, wherein the return result comprises the snapshot picture.

In some embodiments, the scheduling unit 13 is further configured to:

and calling at least one second service according to the scheduling task to obtain the rule file.

In some embodiments, the scheduling unit 13 is specifically configured to:

Calling a page evaluation model service to acquire a page evaluation model of the page to be evaluated; wherein the page assessment model includes computational rule logic for the index type of the at least one classification dimension;

invoking a rule extraction service to extract rules of the page evaluation model to obtain the rule file;

wherein the second service includes the page evaluation model service and the rule extraction service.

In some embodiments, the scheduling unit 13 is specifically configured to:

determining an evaluation index set of the page to be evaluated; wherein the set of evaluation metrics includes a metric type of the at least one classification dimension;

determining a weight of an index type of the at least one classification dimension;

calling the page evaluation model service, and obtaining the page evaluation model according to the evaluation index set and the weight; wherein the computation rule logic comprises a weighted summation of the eigenvalues of the at least one classification dimension according to the weights.

In some embodiments, the page assessment model corresponds to a target industry type to which the page to be assessed belongs.

In some embodiments, the scheduling unit 13 is specifically configured to:

Invoking the rule extraction service, and processing the calculation rule logic of the index of the at least one classification dimension by utilizing a Rete algorithm to obtain a Rete network;

and obtaining the rule file according to the Rete network.

In some embodiments, the task creation unit 12 is specifically configured to:

and determining the evaluation index set according to the relation between at least one of the page content and the object behavior data of at least one landing page corresponding to the target industry type and the conversion rate of the at least one landing page.

In some embodiments, the at least one classification dimension comprises at least one of:

audiovisual experience, industrialised content, conversion interactions, object behaviour.

It should be understood that apparatus embodiments and method embodiments may correspond with each other and that similar descriptions may refer to the method embodiments. To avoid repetition, no further description is provided here. Specifically, the apparatus 10 shown in fig. 13 may perform the above-described method embodiments, and the foregoing and other operations and/or functions of each module in the apparatus 10 are respectively for implementing the corresponding flows in the above-described method 400, which are not repeated herein for brevity.

The apparatus of the embodiments of the present application is described above in terms of functional modules with reference to the accompanying drawings. It should be understood that the functional module may be implemented in hardware, or may be implemented by instructions in software, or may be implemented by a combination of hardware and software modules. Specifically, each step of the method embodiment in the embodiment of the present application may be implemented by an integrated logic circuit of hardware in a processor and/or an instruction in a software form, and the steps of the method disclosed in connection with the embodiment of the present application may be directly implemented as a hardware decoding processor or implemented by a combination of hardware and software modules in the decoding processor. Alternatively, the software modules may be located in a well-established storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, and the like. The storage medium is located in a memory, and the processor reads information in the memory, and in combination with hardware, performs the steps in the above method embodiments.

Fig. 14 is a schematic block diagram of an electronic device 30 provided by an embodiment of the present application.

As shown in fig. 14, the electronic device 30 may include:

a memory 31 and a processor 32, the memory 31 being for storing a computer program and for transmitting the program code to the processor 32. In other words, the processor 32 may call and run a computer program from the memory 31 to implement the method in the embodiment of the present application.

For example, the processor 32 may be configured to perform the above-described method embodiments according to instructions in the computer program.

In some embodiments of the present application, the processor 32 may include, but is not limited to:

a general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like.

In some embodiments of the present application, the memory 31 includes, but is not limited to:

volatile memory and/or nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (Double Data Rate SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and Direct memory bus RAM (DR RAM).

In some embodiments of the present application, the computer program may be divided into one or more modules, which are stored in the memory 31 and executed by the processor 32 to perform the methods provided by the present application. The one or more modules may be a series of computer program instruction segments capable of performing the specified functions, which are used to describe the execution of the computer program in the electronic device.

As shown in fig. 14, the electronic device 30 may further include:

a transceiver 33, the transceiver 33 being connectable to the processor 32 or the memory 31.

The processor 32 may control the transceiver 33 to communicate with other devices, and in particular, may send information or data to other devices or receive information or data sent by other devices. The transceiver 33 may include a transmitter and a receiver. The transceiver 33 may further include antennas, the number of which may be one or more.

It will be appreciated that the various components in the electronic device are connected by a bus system that includes, in addition to a data bus, a power bus, a control bus, and a status signal bus.

The present application also provides a computer storage medium having stored thereon a computer program which, when executed by a computer, enables the computer to perform the method of the above-described method embodiments. Alternatively, embodiments of the present application also provide a computer program product comprising instructions which, when executed by a computer, cause the computer to perform the method of the method embodiments described above.

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 loaded and executed on a computer, produces a flow or function in accordance with embodiments of the application, in whole or in part. 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), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.

It will be appreciated that in the specific implementation of the present application, when the above embodiments of the present application are applied to specific products or technologies and relate to data related to user information and the like, user permission or consent needs to be obtained, and the collection, use and processing of the related data needs to comply with the relevant laws and regulations and standards.

Those of ordinary skill in the art will appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software 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.

In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple modules 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 modules, which may be in electrical, mechanical, or other forms.

The modules illustrated as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. For example, functional modules in various embodiments of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module.

The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily appreciate variations or alternatives within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for evaluating a page, comprising:

receiving an evaluation request for a page to be evaluated;

2. The method of claim 1, wherein the establishing a scheduled task corresponding to the page under evaluation in response to the evaluation request comprises:

3. The method of claim 2, wherein the establishing a scheduling task corresponding to the page to be evaluated according to the target industry type comprises:

And establishing the scheduling task according to the evaluation index set.

4. A method according to claim 3, wherein the rule file corresponds to the target industry type.

5. The method according to claim 1, wherein the invoking at least one first service according to the scheduling task, to obtain a feature value of the page to be evaluated in at least one classification dimension, comprises:

6. The method as recited in claim 1, further comprising:

7. The method of claim 6, wherein invoking at least one second service according to the scheduled task results in the rule file comprising:

8. The method of claim 7, wherein the invoking the page assessment model service to obtain the page assessment model for the page under assessment comprises:

9. The method of claim 7, wherein the page assessment model corresponds to a target industry type to which the page to be assessed belongs.

10. The method of claim 7, wherein invoking the rule extraction service to extract rules from the page assessment model results in the rule file comprises:

and obtaining the rule file according to the Rete network.

11. The method according to claim 3 or 8, wherein said determining the set of evaluation indicators of the page to be evaluated comprises:

and determining the evaluation index set according to the relation between the index of at least one classification dimension of the landing page corresponding to the target industry type to which the page to be evaluated belongs and the conversion rate of the landing page.

12. The method of any one of claims 1-10, wherein the at least one classification dimension comprises at least one of:

13. A page evaluation apparatus, comprising:

14. An electronic device comprising a processor and a memory, the memory having instructions stored therein that when executed by the processor cause the processor to perform the method of any of claims 1-12.

15. A computer storage medium for storing a computer program, the computer program comprising instructions for performing the method of any one of claims 1-12.

16. A computer program product comprising computer program code which, when run by an electronic device, causes the electronic device to perform the method of any one of claims 1-12.