CN115687783A - Business application pushing method and device, storage medium and computer equipment - Google Patents
Business application pushing method and device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN115687783A CN115687783A CN202211425888.4A CN202211425888A CN115687783A CN 115687783 A CN115687783 A CN 115687783A CN 202211425888 A CN202211425888 A CN 202211425888A CN 115687783 A CN115687783 A CN 115687783A
- Authority
- CN
- China
- Prior art keywords
- pushing
- push
- semantic
- service
- application
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Stored Programmes (AREA)
Abstract
The invention discloses a pushing method and device of service application, a storage medium and computer equipment, relates to the technical field of digital medical treatment, and mainly aims to solve the problem that when the existing service application is accessed, the exposure rate of newly added service application is low due to a plurality of service applications configured in a page, so that the service application frequency is low. The method comprises the following steps: when detecting that a user accesses a target page of an application program, acquiring user basic information, and determining attribute information of the user in the application program based on the user basic information; determining semantic tags matched with the attribute information based on the constructed semantic tag library; calling a pushing path matched with the semantic tag and a pushing strategy, and extracting a target business application to be pushed based on a pushing service queue; and pushing the target service application under the pushing path according to the pushing strategy.
Description
Technical Field
The invention relates to the technical field of digital medical treatment and financial science and technology, in particular to a pushing method and device, a storage medium and computer equipment for business application.
Background
With the rapid development of digital medical and financial technologies, development of medical services and financial services based on internet applications has become a focus of attention. With the increase of service applications in the application program, user traffic may be dispersed, which may lead to dispersion of medical services, and the newly added service application is an important object that needs to be paid attention to, so that the newly added service application needs to be placed at the front end of the link.
At present, for a newly added service application, the newly added service application is generally configured in a page of a specified level, so that a user clicks and jumps in the page to perform a service operation for the newly added service application. However, because a large number of service applications are configured in the page, the user cannot be accurately indicated to select the newly added service application, the exposure rate of the service application is reduced, and the service efficiency of the service application is greatly reduced.
Disclosure of Invention
In view of this, the present invention provides a method and an apparatus for pushing a service application, and mainly aims to solve the problem that when an existing service application accesses, because many service applications configured in a page cause a low exposure rate of a newly added service application, the service application is used less frequently.
According to an aspect of the present invention, a method for pushing a service application is provided, including:
when detecting that a user accesses a target page of an application program, acquiring user basic information, and determining attribute information of the user in the application program based on the user basic information;
determining semantic tags matched with the attribute information based on a constructed semantic tag library, wherein the semantic tags matched with different attribute information are stored in the semantic tag library;
calling a push path and a push strategy matched with the semantic tag, and extracting a target business application to be pushed based on a push service queue, wherein a plurality of business applications to be pushed are stored in the push service queue according to business service requirements;
and pushing the target service application under the pushing path according to the pushing strategy.
Further, before determining the semantic tag matching the attribute information based on the constructed semantic tag library, the method further includes:
acquiring user portrait data and extracting attribute information from the user portrait data, wherein the attribute information comprises at least one of identity attribute, project attribute and time attribute;
extracting semantic labels corresponding to all business applications, wherein the semantic labels comprise labels for respectively marking words corresponding to business products and service contents;
and binding the attribute information and the semantic tags to construct a semantic tag library.
Further, before extracting semantic tags corresponding to all the service applications, the method further includes:
obtaining a semantic training sample set, wherein the semantic training sample set comprises all service field words with marked semantics;
performing model training on a semantic extraction model based on the semantic training sample set to obtain a trained semantic extraction model;
the extracting semantic tags corresponding to all the service applications comprises:
and performing semantic label processing on all business applications based on the trained semantic extraction model to obtain semantic labels of the business applications.
Further, the invoking a push path matching the semantic tag and a push policy includes:
extracting a push path corresponding to the semantic tag based on the established page push path corresponding relation, wherein the page push path corresponding relation comprises push paths of business applications corresponding to different semantic tags in the target page;
and calling a pushing strategy set configured by the target page, and screening a pushing strategy from the pushing strategy set according to the semantic tag and the pushing path, wherein the pushing strategy set comprises at least one of a frequency rule, a display type rule and a frequency rule for pushing each business application in the target page.
Further, the extracting the target business application to be pushed based on the push service queue comprises:
acquiring a push service queue bound with the target page, wherein all business applications pushed on the target page are stored in the push service queue;
and when the queue pointers point at the preset time intervals in sequence, selecting a target service application from the service applications pointed by the queue pointers at the current moment according to the page type of the target page.
Further, the pushing, by the target service application, under the push path according to the push policy includes:
determining a push area of the push path in the target page, wherein the push area is obtained by sequencing from different display areas corresponding to the push path according to the preset time interval;
and applying the target service to the push area for display according to at least one of a frequency rule, a display type rule and a frequency rule in the push strategy.
Further, the method further comprises:
when a push cut-through instruction of a user is received, configuring a jump triggering event of the target service application;
after the target service application is pushed in the push path according to the push strategy, the method further includes:
and jumping to enter the target service application based on the jump triggering event.
According to another aspect of the present invention, there is provided a service application pushing apparatus, including:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring user basic information when detecting that a user accesses a target page of an application program, and determining attribute information of the user in the application program based on the user basic information;
the determining module is used for determining semantic tags matched with the attribute information based on a constructed semantic tag library, and the semantic tags matched with different attribute information are stored in the semantic tag library;
the calling module is used for calling a pushing path matched with the semantic tag and a pushing strategy;
the system comprises an extraction module, a service processing module and a service processing module, wherein the extraction module is used for extracting a target business application to be pushed based on a pushing service queue, and the pushing service queue stores a plurality of business applications to be pushed according to business service requirements;
and the pushing module is used for pushing the target service application under the pushing path according to the pushing strategy.
Further, the apparatus further comprises: the component modules are used for building the component modules,
the acquisition module is further used for acquiring user portrait data and extracting attribute information from the user portrait data, wherein the attribute information comprises at least one of identity attribute, project attribute and time attribute;
the extraction module is used for extracting semantic labels corresponding to all business applications, wherein the semantic labels comprise labels for respectively marking words corresponding to business products and service contents;
and the component module is used for binding the attribute information and the semantic tags to construct a semantic tag library.
Further, the apparatus further comprises: a model training module for training a model of the human body,
the acquisition module is also used for acquiring a semantic training sample set, and the semantic training sample set comprises all service field words with marked semantics;
the model training module is used for carrying out model training on a semantic extraction model based on the semantic training sample set to obtain a trained semantic extraction model;
the extraction module is specifically configured to perform semantic tag processing on all service applications based on the trained semantic extraction model to obtain semantic tags of the service applications.
Further, the invoking module is specifically configured to extract a push path corresponding to the semantic tag based on an established correspondence relationship between page push paths, where the correspondence relationship between page push paths includes push paths of service applications corresponding to different semantic tags in the target page; and calling a pushing strategy set configured by the target page, and screening a pushing strategy from the pushing strategy set according to the semantic tag and the pushing path, wherein the pushing strategy set comprises at least one of a frequency rule, a display type rule and a frequency rule for pushing each business application in the target page.
Further, the extracting module is specifically configured to obtain a push service queue bound to the target page, where all service applications pushed on the target page are stored in the push service queue; and when the queue pointers point in sequence according to a preset time interval, selecting a target service application from the service applications pointed by the queue pointers at the current moment according to the page type of the target page.
Further, the pushing module is specifically configured to determine a pushing area of the pushing path in the target page, where the pushing area is obtained by sorting different display areas corresponding to the pushing path according to the preset time interval; and applying the target service to the push area for display according to at least one of a frequency rule, a display type rule and a frequency rule in the push strategy.
Further, the apparatus further comprises:
the configuration module is used for configuring a jump triggering event of the target service application after receiving a push cut-through instruction of a user;
and the skipping module is used for skipping to enter the target service application based on the skipping trigger event. According to another aspect of the present invention, a storage medium is provided, where at least one executable instruction is stored, and the executable instruction causes a processor to perform an operation corresponding to the pushing method of the service application.
According to still another aspect of the present invention, there is provided a computer apparatus including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the pushing method of the business application.
By the technical scheme, the technical scheme provided by the embodiment of the invention at least has the following advantages:
compared with the prior art, the pushing method and device of the business application, the storage medium and the computer equipment are provided by the embodiment of the invention, when the condition that a user accesses a target page of an application program is detected, the basic information of the user is obtained, and the attribute information of the user in the application program is determined based on the basic information of the user; determining semantic tags matched with the attribute information based on a constructed semantic tag library, wherein the semantic tags matched with different attribute information are stored in the semantic tag library; calling a push path and a push strategy matched with the semantic tag, and extracting a target business application to be pushed based on a push service queue, wherein the push service queue stores a plurality of business applications to be pushed according to business service requirements; the target business application is pushed under the pushing path according to the pushing strategy, so that semantic tags of the business application are matched according to the user attribute information, the pushing path and the pushing strategy of the business application are matched according to the semantic tags, and finally the business to be pushed is pushed based on the matching items, so that the business application is pushed to more suitable people in a more suitable pushing mode, the pushing accuracy of the business application is improved, and the utilization rate of the business application is further improved.
The above description is only an overview of the technical solutions of the present invention, and the present invention can be implemented in accordance with the content of the description so as to make the technical means of the present invention more clearly understood, and the above and other objects, features, and advantages of the present invention will be more clearly understood.
Drawings
Various additional advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 shows a flowchart of a method for pushing a service application according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating another pushing method for a service application according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating a pushing method of a service application according to another embodiment of the present invention;
fig. 4 is a block diagram illustrating a pushing apparatus of a service application according to an embodiment of the present invention;
fig. 5 shows a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
For the current situation, the existing newly added service application is usually configured in a page of a specified level, so that a user can click and jump in the page, thereby performing the service operation. However, since there are many service applications configured in the page, the user cannot be accurately instructed to select a newly added service application, the exposure rate of the service application is reduced, and the service efficiency of the service application is greatly reduced, embodiments of the present invention provide a method for pushing a service application, as shown in fig. 1, the method includes:
101. when detecting that a user accesses a target page of an application program, acquiring user basic information, and determining attribute information of the user in the application program based on the user basic information.
In the embodiment of the invention, the current execution main body is a server side for pushing corresponding business application to the application program page, and the current execution main body and the application program form a business application access system. When a user accesses a page of an application program through a terminal device, detecting access to a target page, wherein the application program may be an application program APP in the terminal device or an applet embedded in the current application program, and the target page access detection may be implemented by configuring page access monitoring on a preset page, for example, taking a first page of a certain application program as the target page of the application program and configuring and monitoring access to the target page, so that when an executive agent detects that the user accesses the target page of the application program, basic information of the user is obtained, wherein the basic information of the user includes but is not limited to information filled when the user registers in the application program and data information generated during using the application program, and further determining attribute information in a medical program of the user according to the basic information of the user.
Further, the attribute information of the user in the application program at least includes at least one of an identity attribute, an item attribute, and a time attribute, where the identity attribute may be, for example, the age, the sex, the location, and the like of the user, the item attribute may be a serious illness, an emergency treatment item, a physical examination item, and the like, and the time attribute may be a time attribute corresponding to a medical item of the user and/or a time attribute of the user using the application program, which is not specifically limited in this embodiment of the present application.
In the embodiment of the application, by configuring the service application pushing system based on the application program, when the execution main body detects that the user accesses the target page of the application program, the execution main body can trigger to acquire the user basic information and determine the attribute information of the user in the current application program according to the user basic information, so as to recommend the service application corresponding to the attribute information of the user according to the attribute information of the user in the application program, wherein the service application can be a sub-service program or a sub-service model of the current application program, thereby improving the exposure rate of the service application and further improving the use efficiency of the service application.
It should be noted that the application program in the embodiment of the present invention may be a medical application program or a financial application program, that is, the pushing method of the business application implemented in steps 101 to 104 is applicable to the digital medical field or the financial technology field, and the embodiment of the present invention is not limited specifically.
102. And determining semantic tags matched with the attribute information based on the constructed semantic tag library.
The semantic tags may at least include tags for identifying a presentation layer and an information layer, the presentation layer may be in a presentation form in which the medical service is applied in the medical application, the information layer may be specific content of the service application, for example, tag information of a "physical examination card" medical service application in the medical application, the tag information corresponding to the presentation layer may be animation, flat, 3D, compact, bold, transparent, and the like, and the tag information corresponding to the information layer may be staged, middle-aged, elderly, whole body, time-limited preference, health, and the like, but is not limited thereto.
In the specific application process, because the semantic tags can identify the characteristics of the medical service application, the semantic tags can be easily understood, and the matching relationship between the user attribute information and the semantic tags can reflect the preference of users with different attributes to various medical service applications. Therefore, in the embodiment of the application, the mapping relationship between the semantic tags and the attribute information of the user can be created in advance, so that after the execution main body determines the attribute information of the user based on the basic information of the user, the semantic tags corresponding to the current user can be further determined based on the attribute information of the user and the semantic tag library created and stored in advance, so that the service application can be recommended according to the semantic tags matched with the user in a more targeted manner, and the service application use efficiency is improved.
103. And calling a pushing path matched with the semantic tag and a pushing strategy, and extracting the target business application to be pushed based on a pushing service queue.
Based on the above steps, the execution main body can determine attribute information of a user accessing the current target page and determine a semantic tag matched with the attribute information, so that in this step, a push path and a push policy matched with the semantic tag can be called according to the semantic tag, where the push path can be a data acquisition interface corresponding to service application push, a push call thread, a page level corresponding to a service application to be pushed in an application program, and the like, and the push policy can be a push frequency, a push period, and the like corresponding to the service application to be pushed. Specifically, a mapping relationship between the semantic tag and the push path and the push policy may be created in advance, and the push path and the push policy that are matched with the semantic tag may be retrieved based on the mapping relationship. Illustratively, a push path corresponding to a semantic tag "insurance product time-limited offer" is to call a thread a to obtain data of a medical service application to be pushed through a preset interface M, and push and display the data in an area B in a primary page of a medical application program, a push strategy corresponding to the semantic tag "insurance product time-limited offer" is to push the data 5 times per day, and a push cycle is 30 days, but in the embodiment of the present application, there is no specific limitation on the concept explanation of the push path and the push strategy, and the specific implementation manner of calling the matched push path and push strategy according to the semantic tag.
Further, after determining the push path and the push policy corresponding to the service application corresponding to the current user, the execution main body needs to acquire the service application to be pushed, so as to push the service application to be pushed based on the determined push path and the push policy. In the embodiment of the application, a plurality of business applications to be pushed can be stored in a pushing service queue in advance according to business service requirements, so that an execution main body can directly extract and obtain the business applications to be pushed from a pushing service contrast when acquiring the business applications to be pushed.
104. And pushing the target service application under the pushing path according to the pushing strategy.
In the embodiment of the invention, when a user accesses a target page of an application program, the execution main body acquires the basic information and the attribute information of the user, further determines the semantic tag matched with the basic information according to the attribute information, calls the push path and the push strategy matched with the semantic tag according to the semantic tag, and finally acquires the target business application to be pushed, so that the target business application can be pushed under the corresponding push path according to the corresponding push strategy, the business application to be pushed is recommended to the matched user while the business service requirement is met, the exposure rate of each business application is improved, and the use efficiency of the business application is further improved.
In another embodiment of the present invention, for further definition and explanation, as shown in fig. 2, before the step of determining the semantic tag matching the attribute information based on the constructed semantic tag library, the method further includes:
201. acquiring user portrait data and extracting attribute information from the user portrait data;
202. extracting semantic labels corresponding to all service applications;
203. and binding the attribute information with the semantic tags to construct a semantic tag library.
The user portrait data may be data generated during the operation performed by the user in the business application and capable of identifying the target, behavior, viewpoint, etc. of the user, for example, the user portrait data in the medical application program may be data related to personal information input by the user, may be data for browsing the data such as browsing content, staying time, etc. when the user uses the medical application program, and may also be order data, reservation data, etc. in the medical application program. Further, the attribute information is extracted from the user portrait data by using a preset feature extraction algorithm or a preset matching rule, where the attribute information at least includes at least one of an identity attribute, an item attribute, and a time attribute, where the identity attribute may be, for example, the age, the sex, the region where the user is located, and the like of the user, the item attribute may be a serious disease, an emergency treatment item, a physical examination item, and the like in a specific medical item attribute, and the time attribute may be a time attribute corresponding to the medical item of the user and/or a time attribute of using the application program by the user, and the like.
Generally, semantic tags corresponding to different industries are different, and in order to form a mapping relationship between the user attribute information and the semantic tags, the execution subject needs to acquire the semantic tags corresponding to the medical service industry. Specifically, the execution main body extracts, based on, for example, the content of the display page, the display form, and the like of each medical service application of the medical application program, semantic tags, which can mark words corresponding to the service products and the service content, of each service application by using, for example, a crawler technology, a feature extraction technology, and the like, where the semantic tags may also include tags identifying the presentation layer and the information layer as described above, and details of the embodiment of the present application are not repeated herein. Furthermore, the mode of binding the attribute information and the semantic tags may be binding manually, or binding based on an intelligent algorithm or a machine learning model trained in advance for binding the user attribute information and the semantic tags.
In the embodiment of the application, the labels for identifying the behavior characteristics, the consumption behaviors and the like of the user can be marked according to the user portrait data, so that the labels are matched according to the attribute information labels and the semantic labels of the business application, the adaptation degree between the business application and the user is improved, the adaptation degree between the business application to be pushed and the user is improved, and the utilization rate of the pushed business application is improved.
In another embodiment of the present invention, for further definition and explanation, before the step of extracting semantic tags corresponding to all the service applications, the method further includes:
obtaining a semantic training sample set;
performing model training on a semantic extraction model based on the semantic training sample set to obtain a trained semantic extraction model;
the extracting semantic tags corresponding to all the service applications comprises:
and performing semantic label processing on all business applications based on the trained semantic extraction model to obtain semantic labels of the business applications.
When pushing of business applications is optimized by combining user attribute information, it is important to match the user attribute information with the business applications to be pushed, in order to improve the matching degree between the business applications to be pushed and users and thus improve the utilization rate of the business applications, an execution main body needs to accurately identify semantic tags of the business applications to acquire accurate cognition of the business applications, and therefore the execution main body performs semantic tag processing on the business applications to obtain semantic tags which are used for respectively marking words corresponding to business products and service contents in the business applications.
Specifically, the execution main body obtains a sample set containing all service field words with marked semantics as a semantic training sample set of the machine learning model, and trains the semantic extraction model based on the semantic training sample set to obtain the trained semantic extraction model, wherein the semantic extraction model to be trained may be based on, but not limited to, a full connectivity Neural network (DNN), a Convolutional Neural Network (CNN), and the like. Because the trained semantic extraction model can extract words corresponding to the identification business products and the service contents in the business application, the execution subject can acquire the words corresponding to the business products (such as medical products and financial products) and the service contents of the business application based on the trained semantic extraction model and use the words as semantic labels of the business application.
In the embodiment of the application, the semantic extraction model is subjected to model training by using the semantic training sample set, and the semantic label processing is performed on the business application based on the trained semantic extraction model to obtain the semantic label corresponding to the business application, so that the accuracy and the high efficiency of obtaining the semantic label of the business application are ensured, and the accuracy and the utilization rate of pushing the business application are improved.
In another embodiment of the present invention, for further definition and explanation, the step of retrieving a push path matching the semantic tag and the push policy includes:
extracting a push path corresponding to the semantic tag based on the established page push path corresponding relation;
and calling a pushing strategy set configured by the target page, and screening a pushing strategy from the pushing strategy set according to the semantic tag and the pushing path.
The page pushing path corresponding relation comprises a pushing path of business applications corresponding to different semantic tags in the target page, and the pushing strategy set comprises at least one of a frequency rule, a display type rule and a frequency rule for pushing each business application in the target page.
In the specific implementation process of pushing the medical service application, the medical service application corresponding to different types of semantic tags usually corresponds to different page levels, and exemplarily, for a semantic tag with a higher click rate and/or conversion rate, the page level of the medical service application corresponding to the semantic tag is relatively higher; or for semantic tags with higher preset pushing degree, the page level of the medical service application corresponding to the semantic tags is higher. The page level may be a level used for identifying a page display order during page design, such as a first level page, a second level page, a third level page, and the like. In order to better adapt to medical services, in the embodiment of the present application, a correspondence between a page push path and a push path corresponding to a semantic tag may be created in advance, and as described above, the push path of the medical service application corresponding to the semantic tag with priority may be configured to be a page with higher priority, so that the execution subject can subsequently determine the push path of the medical service application to be pushed according to the semantic tag matched with the user attribute information.
Similarly, in the implementation process of pushing the medical service application, the pushing policy is related to the semantic tag and the pushing path, that is, different semantic tags and/or different pushing paths correspond to different pushing policies. In the embodiment of the application, a pushing policy set including multiple pushing policies corresponding to the pushing paths and the semantic tags may be created in advance, and the execution subject may invoke the adapted pushing policy from the pushing policy set based on the previously determined pushing paths and semantic tags and perform pushing of the medical service application when executing pushing of the medical service application. The push policy set includes a number rule, a display type rule, a frequency rule, and the like for pushing a medical service application in a medical application program page, where the number rule is a push number corresponding to the medical service application, the display type rule is a display manner of an image, a text, a video, and the like for the medical service application to be pushed in the page, and the frequency rule is a display frequency corresponding to each medical service application, but not limited thereto.
It should be noted that, when an adaptive push policy is called from a push policy set according to a semantic tag and a push path, the push path and the relationship between the semantic tag and the push policy may be in a one-to-one correspondence and/or a many-to-one correspondence and/or a one-to-many correspondence, and the step of calling the push policy may be to perform a preliminary push policy matching based on any one of the semantic tag and the push path, then screen the preliminarily matched push policy according to the other one of the semantic tag and the push path, and if a plurality of push policies corresponding to the service application to be pushed are obtained at this time, select one of the push policies at random or preferentially select one of the push policies based on other display contents in the page and an intelligent algorithm, and the embodiment of the present application does not specifically limit this.
In the embodiment of the application, when the push path and the push strategy corresponding to the current service application to be pushed are obtained based on the semantic tag, multi-level matching screening is performed based on the semantic tag through the pre-established push path corresponding relation and the push strategy set, so that the obtained push path and the obtained push strategy respectively have higher matching degrees with the user and the target page, and the utilization rate of the pushed service application is improved.
In another embodiment of the present invention, for further definition and explanation, the step of extracting the target business application to be pushed based on the push service queue includes:
acquiring a push service queue bound with the target page, wherein all business applications pushed on the target page are stored in the push service queue;
and when the queue pointers point in sequence according to a preset time interval, selecting a target service application from the service applications pointed by the queue pointers at the current moment according to the page type of the target page.
In this embodiment, one push service queue is created according to a certain number of business applications, and each service to be pushed in the push service queue can be displayed in a target page bound to the push service queue, where the binding between the target page and the push service queue can be achieved through a manual binding manner, or can be achieved by determining and binding a corresponding relationship between the target page and the push service queue based on an intelligent algorithm. That is to say, in the embodiment of the present application, after the target page is bound with the push service queue, the range of the business application to be pushed in the target page is determined and wide, but the execution subject needs to determine the push path and the push policy based on the attribute information of the user. However, in the prior art, each/every type of user pushes the corresponding service application with the same delivery path and/or push strategy, so compared with the prior art, the medical service push in the embodiment of the present application has higher efficiency and wider push effect on the premise of ensuring accurate push.
Further, after the push service queue bound to the target page is obtained, a suitable target business application to be recommended may be selected according to the page type of the current target page in the multiple business applications pointed by the queue pointer.
In the embodiment of the application, the business applications to be pushed are uniformly stored in the pushing service queue and the pushing service queue is bound with the target page, so that when the execution main body executes business application pushing, the pushing service queue bound with the target page can be obtained, the business applications to be pushed are selected to be recommended according to the business applications to be pushed and the types of the business applications to be recommended are matched with the types of the target page, matching degree check of each business application to be recommended and each or no user is not required, and pushing paths and pushing strategies corresponding to the business applications with different semantic tags are different, so that the pushing performance of the business applications is improved on the premise of ensuring accurate business application pushing.
In another embodiment of the present invention, for further limitation and description, the step of pushing, by the target service application, the target service application in the push path according to the push policy includes:
determining a pushing area of the pushing path in the target page;
and applying the target service to the push area for display according to at least one of a frequency rule, a display type rule and a frequency rule in the push strategy.
It should be noted that, after determining a push path corresponding to a service application to be pushed based on user attribute information and a semantic tag, for example, a data interface, a database, a data thread, and the like for obtaining the service application to be pushed are determined, however, in a specific application process, a display area corresponding to a same push path in a target page may include multiple push areas for displaying different service applications, for example, a middle section of the page in a target page X is a display area corresponding to a push path Q, the display area includes three push areas, which are a push area 1, a push area 2, and a push area 3, respectively, and the three push areas can simultaneously display three pushed medical service applications and can alternately display the pushed medical service applications at certain time intervals. For this purpose, the executing body needs to further acquire a push area of the push path in the target page, so as to expose the target medical business application in the push area based on the previously determined push strategy.
In the embodiment of the application, the display area corresponding to the business application to be pushed is further determined according to the pushing path, and the business application is displayed in the display area based on the pushing strategy, so that the accuracy of displaying the business application is improved, and the accuracy of pushing the business application is further improved.
In another embodiment of the present invention, for further definition and explanation, as shown in fig. 3, the method further comprises:
301. when a push cut-through instruction of a user is received, configuring a jump triggering event of the target service application;
after the target service application is pushed in the push path according to the push strategy, the method further includes:
302. and jumping to enter the target service application based on the jumping trigger event.
In a specific application process, a service application is usually displayed in a corresponding display area according to a preset push path and a push strategy, and a page corresponding to the service application is displayed or pushed for closing the service application in response to a click access or closing instruction of a user. In this embodiment of the application, in order to reduce user interaction operations, whether to receive push cut-through instruction request information may be output to a user in advance, where a push cut-through instruction is used to identify that a direct jump to a target service application based on a push path and a push policy may be performed without user interaction, for example, when a user registers a medical application program, or when the user starts the medical application program according to a preset time interval or a preset number of times, whether to receive the push cut-through instruction request information is triggered to be output, and response information corresponding to the request information input by the user is received, and after receiving the push cut-through instruction of the user, a jump trigger event of the target medical service application is configured, so that an execution subject may jump directly into the corresponding medical service application based on the jump trigger event after pushing the target medical service application to be pushed in the push path according to the push policy. The specific configuration principle may be set according to different application scenarios, for example, the configuration principle may be triggered based on page access, or based on a click event, or based on browsing time, and the like, which is not specifically limited in this embodiment of the present application.
In the embodiment of the application, by obtaining the user authorization push cut-through, the pushed service application can be displayed by reducing the interactive operation with the user on the premise of being based on the push path and the push strategy matched with the user, so that the utilization rate of the service application is further improved, and the display efficiency of the service application is improved.
Further, as an implementation of the method shown in fig. 1, an embodiment of the present invention provides a pushing device for service application, and as shown in fig. 4, the pushing device includes:
an obtaining module 41, configured to, when it is detected that a user accesses a target page of an application program, obtain user basic information, and determine, based on the user basic information, attribute information that the user is in the application program;
a determining module 42, configured to determine, based on a constructed semantic tag library, a semantic tag that matches the attribute information, where semantic tags that match different attribute information are stored in the semantic tag library;
the retrieving module 43 is configured to retrieve a push path matched with the semantic tag and a push policy;
an extracting module 44, configured to extract a target business application to be pushed based on a push service queue, where a plurality of business applications to be pushed are stored in the push service queue according to business service requirements;
and the pushing module 45 is configured to push the target service application in the pushing path according to the pushing policy.
Further, the apparatus further comprises: the component modules are used for building the component modules,
the obtaining module 41 is further configured to obtain user portrait data and extract attribute information from the user portrait data, where the attribute information includes at least one of an identity attribute, an item attribute, and a time attribute;
the extraction module 44 is configured to extract semantic tags corresponding to all service applications, where the semantic tags include tags that respectively mark words corresponding to service products and service contents;
and the component module is used for binding the attribute information and the semantic tags to construct a semantic tag library.
Further, the apparatus further comprises: a model training module for training a model of the human body,
the obtaining module 41 is further configured to obtain a semantic training sample set, where the semantic training sample set includes all service field words with marked semantics;
the model training module is used for carrying out model training on a semantic extraction model based on the semantic training sample set to obtain a trained semantic extraction model;
the extraction module 44 is specifically configured to perform semantic tag processing on all service applications based on the trained semantic extraction model to obtain semantic tags of the service applications.
Further, the invoking module 43 is specifically configured to extract a push path corresponding to the semantic tag based on an established page push path corresponding relationship, where the page push path corresponding relationship includes a push path of a service application corresponding to different semantic tags in the target page; and calling a push strategy set configured by the target page, and screening push strategies from the push strategy set according to the semantic tags and the push paths, wherein the push strategy set comprises at least one of a frequency rule, a display type rule and a frequency rule for pushing each service application in the target page.
Further, the extracting module 44 is specifically configured to obtain a push service queue bound to the target page, where all service applications pushed on the target page are stored in the push service queue; and when the queue pointers point at the preset time intervals in sequence, selecting a target service application from the service applications pointed by the queue pointers at the current moment according to the page type of the target page.
Further, the pushing module 45 is specifically configured to determine a pushing area of the pushing path in the target page, where the pushing area is obtained by sorting different display areas corresponding to the pushing path according to the preset time interval; and displaying the target service application in the push area according to at least one of a frequency rule, a display type rule and a frequency rule in the push strategy.
Further, the apparatus further comprises:
the configuration module is used for configuring a jump triggering event of the target service application after receiving a push cut-through instruction of a user;
and the skipping module is used for skipping to enter the target service application based on the skipping trigger event.
Compared with the prior art, the pushing method and the pushing device for the business application have the advantages that the user basic information is obtained when the fact that the user accesses the target page of the application program is detected, and the attribute information of the user in the application program is determined based on the user basic information; determining semantic tags matched with the attribute information based on a constructed semantic tag library, wherein the semantic tags matched with different attribute information are stored in the semantic tag library; calling a push path and a push strategy matched with the semantic tag, and extracting a target business application to be pushed based on a push service queue, wherein the push service queue stores a plurality of business applications to be pushed according to business service requirements; the target service application is pushed in the pushing path according to the pushing strategy, the matching of the semantic tags of the service application according to the user attribute information is achieved, the pushing path and the pushing strategy of the service application are matched according to the semantic tags, and finally the medical service to be pushed is pushed based on the matching items, so that the service application is pushed to more suitable people in a more suitable pushing mode, the pushing accuracy of the service application is improved, and the utilization rate of the service application is improved.
According to an embodiment of the present invention, a storage medium is provided, where the storage medium stores at least one executable instruction, and the computer executable instruction may execute the pushing method of the service application in any method embodiment described above.
Fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computer device.
As shown in fig. 5, the computer apparatus may include: a processor (processor) 502, a communication interface (Commun I cat I ons I interface) 504, a memory 506, and a communication bus 508.
Wherein: the processor 502, communication interface 504, and memory 506 communicate with one another via a communication bus 508.
A communication interface 504 for communicating with network elements of other devices, such as clients or other servers.
The processor 502 is configured to execute the program 510, and may specifically execute relevant steps in the pushing method embodiment of the service application.
In particular, program 510 may include program code that includes computer operating instructions.
The processor 502 may be a central processing unit CPU, or a specific integrated circuit AS IC (Appl I cat I on Spec I C I registered Ci), or one or more integrated circuits configured to implement embodiments of the present invention. The computer device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors, such AS one or more CPUs and one or more AS ics.
A memory 506 for storing a program 510. The memory 506 may comprise high-speed RAM memory, and may also include non-volatile memory (non-vo at i e memory), such as at least one disk memory.
The program 510 may specifically be used to cause the processor 502 to perform the following operations:
when detecting that a user accesses a target page of an application program, acquiring user basic information, and determining attribute information of the user in the application program based on the user basic information;
determining semantic tags matched with the attribute information based on a constructed semantic tag library, wherein the semantic tags matched with different attribute information are stored in the semantic tag library;
calling a push path and a push strategy matched with the semantic tag, and extracting a target business application to be pushed based on a push service queue, wherein a plurality of business applications to be pushed are stored in the push service queue according to business service requirements;
and pushing the target service application under the pushing path according to the pushing strategy.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made without departing from the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A method for pushing a business application is characterized by comprising the following steps:
when detecting that a user accesses a target page of an application program, acquiring user basic information, and determining attribute information of the user in the application program based on the user basic information;
determining semantic tags matched with the attribute information based on a constructed semantic tag library, wherein the semantic tags matched with different attribute information are stored in the semantic tag library;
calling a push path and a push strategy matched with the semantic tag, and extracting a target business application to be pushed based on a push service queue, wherein a plurality of business applications to be pushed are stored in the push service queue according to business service requirements;
and pushing the target service application under the pushing path according to the pushing strategy.
2. The method of claim 1, wherein before determining the semantic tag matching the attribute information based on the constructed semantic tag library, the method further comprises:
acquiring user portrait data and extracting attribute information from the user portrait data, wherein the attribute information comprises at least one of identity attribute, item attribute and time attribute;
extracting semantic labels corresponding to all business applications, wherein the semantic labels comprise labels for respectively marking words corresponding to business products and service contents;
and binding the attribute information with the semantic tags to construct a semantic tag library.
3. The method of claim 2, wherein before extracting the semantic tags corresponding to all the business applications, the method further comprises:
obtaining a semantic training sample set, wherein the semantic training sample set comprises all service field words with marked semantics;
performing model training on a semantic extraction model based on the semantic training sample set to obtain a trained semantic extraction model;
the extracting semantic tags corresponding to all the service applications comprises:
and performing semantic label processing on all business applications based on the trained semantic extraction model to obtain semantic labels of the business applications.
4. The method of claim 1, wherein the invoking of the push path matching the semantic tag and the push policy comprises:
extracting a push path corresponding to the semantic tag based on an established page push path corresponding relation, wherein the page push path corresponding relation comprises push paths of business applications corresponding to different semantic tags in the target page;
and calling a pushing strategy set configured by the target page, and screening a pushing strategy from the pushing strategy set according to the semantic tag and the pushing path, wherein the pushing strategy set comprises at least one of a frequency rule, a display type rule and a frequency rule for pushing each business application in the target page.
5. The method of claim 4, wherein the extracting the target business application to be pushed based on the push service queue comprises:
acquiring a push service queue bound with the target page, wherein all business applications pushed on the target page are stored in the push service queue;
and when the queue pointers point in sequence according to a preset time interval, selecting a target service application from the service applications pointed by the queue pointers at the current moment according to the page type of the target page.
6. The method of claim 5, wherein pushing by the target business application under the push path according to the push policy comprises:
determining a pushing area of the pushing path in the target page, wherein the pushing area is obtained by sequencing from different display areas corresponding to the pushing path according to the preset time interval;
and displaying the target service application in the push area according to at least one of a frequency rule, a display type rule and a frequency rule in the push strategy.
7. The method of any one of claims 1-6, further comprising:
when a push cut-through instruction of a user is received, configuring a jump triggering event of the target service application;
after the target service application is pushed in the push path according to the push policy, the method further includes:
and jumping to enter the target service application based on the jump triggering event.
8. A pushing device for business applications, comprising:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring user basic information when detecting that a user accesses a target page of an application program, and determining attribute information of the user in the application program based on the user basic information;
the determining module is used for determining semantic tags matched with the attribute information based on a constructed semantic tag library, and the semantic tags matched with different attribute information are stored in the semantic tag library;
the extraction module is used for calling a push path and a push strategy matched with the semantic tag, and extracting a target business application to be pushed based on a push service queue, wherein a plurality of business applications to be pushed are stored in the push service queue according to business service requirements;
and the pushing module is used for pushing the target service application under the pushing path according to the pushing strategy.
9. A storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to perform operations corresponding to the pushing method of the business application according to any one of claims 1 to 7.
10. A computer device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the pushing method of the business application according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211425888.4A CN115687783A (en) | 2022-11-15 | 2022-11-15 | Business application pushing method and device, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211425888.4A CN115687783A (en) | 2022-11-15 | 2022-11-15 | Business application pushing method and device, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115687783A true CN115687783A (en) | 2023-02-03 |
Family
ID=85052207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211425888.4A Pending CN115687783A (en) | 2022-11-15 | 2022-11-15 | Business application pushing method and device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115687783A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116503107A (en) * | 2023-06-25 | 2023-07-28 | 青岛华正信息技术股份有限公司 | Business big data processing method and system applying artificial intelligence |
-
2022
- 2022-11-15 CN CN202211425888.4A patent/CN115687783A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116503107A (en) * | 2023-06-25 | 2023-07-28 | 青岛华正信息技术股份有限公司 | Business big data processing method and system applying artificial intelligence |
| CN116503107B (en) * | 2023-06-25 | 2023-10-03 | 青岛华正信息技术股份有限公司 | Business big data processing method and system applying artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI743773B (en) | Method and device for identifying abnormal collection behavior based on privacy data protection | |
| CN112231586A (en) | Course recommendation method, device, equipment and medium based on transfer learning | |
| CN111949708A (en) | Multi-task prediction method, device, equipment and medium based on time sequence feature extraction | |
| CN110414989A (en) | Method for detecting abnormality and device, electronic equipment and computer readable storage medium | |
| CN113051503A (en) | Browser page rendering method and device, electronic equipment and storage medium | |
| CN115687783A (en) | Business application pushing method and device, storage medium and computer equipment | |
| CN112214588A (en) | Multi-intention recognition method and device, electronic equipment and storage medium | |
| CN115205225A (en) | Training method, device and equipment of medical image recognition model and storage medium | |
| CN115222443A (en) | Client group division method, device, equipment and storage medium | |
| CN110874570A (en) | Face recognition method, device, equipment and computer readable storage medium | |
| CN113704511A (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| CN117473130A (en) | Service processing method, device, equipment, medium and program product | |
| CN109033078B (en) | The recognition methods of sentence classification and device, storage medium, processor | |
| CN115809889A (en) | Intelligent passenger group screening method, system, medium and equipment based on marketing effect | |
| CN114722280A (en) | User portrait based course recommendation method, device, equipment and storage medium | |
| CN114066507A (en) | Promotion information analysis method and device, electronic equipment and storage medium | |
| CN113806540A (en) | Text labeling method and device, electronic equipment and storage medium | |
| Rahman | Visual attention strategies for target object detection | |
| CN114625442A (en) | Cold start recommendation method and device, electronic equipment and readable storage medium | |
| CN117219253A (en) | Medical interface generation method and device | |
| CN114880512A (en) | Method and device for processing expression package picture and server | |
| CN117056629A (en) | Cache configuration method, device, computer equipment and storage medium | |
| CN113887621A (en) | Method, device and equipment for adjusting question and answer resources and storage medium | |
| CN117034173A (en) | Data processing method, device, computer equipment and storage medium | |
| CN117252362A (en) | Scheduling method and device based on artificial intelligence, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |