Method, device, electronic device and storage medium for generating guidance information

Abstract

The present disclosure provides a method, apparatus, electronic device, and storage medium for generating guidance information, relating to the field of data processing technology, particularly to intelligent search, information flow, and other fields. A specific implementation scheme comprises: obtaining associated data of a target object, the associated data including behavioral data generated by the target object with respect to a target page; determining an associated feature set corresponding to the associated data, the associated feature set including behavioral features corresponding to the behavioral data; determining a conversion rate corresponding to the associated feature set; and generating target guidance information when it is determined that the conversion rate meets predetermined conditions.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to the fields of intelligent search and information flow. More specifically, the present disclosure provides a method, device, electronic device, storage medium, and computer program product for generating guidance information. Background Art

[0002] In the ad landing page scenario, call-to-action (CTA) components can be used to guide users to take conversion actions, such as leaving contact information, filling out a form, making a phone call, placing an order, registering, downloading an app, etc. These components can include pop-ups or other forms within the page the user is browsing. Summary of the Invention

[0003] The present disclosure provides a method, apparatus, electronic device, storage medium, and computer program product for generating guidance information.

[0004] According to one aspect of the present disclosure, a method for generating guidance information is provided, comprising: obtaining associated data of a target object, the associated data comprising behavioral data generated by the target object for a target page; determining an associated feature set corresponding to the associated data, the associated feature set comprising behavioral features corresponding to the behavioral data; determining a conversion rate corresponding to the associated feature set; and generating target guidance information when it is determined that the conversion rate meets predetermined conditions.

[0005] According to another aspect of the present disclosure, a device for generating guidance information is provided, comprising an acquisition module, a first determination module, a second determination module, and a generation module. The acquisition module is configured to acquire associated data of a target object, the associated data including behavioral data generated by the target object with respect to a target page. The first determination module is configured to determine an associated feature set corresponding to the associated data, the associated feature set including behavioral features corresponding to the behavioral data. The second determination module is configured to determine a conversion rate corresponding to the associated feature set. The generation module is configured to generate target guidance information upon determining that the conversion rate satisfies a predetermined condition.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method provided by the present disclosure.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the method provided by the present disclosure.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements the method provided in the present disclosure when executed by a processor.

[0009] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0011] Figure 1 is a schematic diagram of an application scenario of the method and apparatus for generating guidance information according to an embodiment of the present disclosure;

[0012] Figure 2 is a schematic flow chart of a method for generating guidance information according to an embodiment of the present disclosure;

[0013] Figure 3 is a schematic diagram of a method for generating guidance information according to an embodiment of the present disclosure;

[0014] Figure 4 is a schematic structural block diagram of an apparatus for generating guidance information according to an embodiment of the present disclosure; and

[0015] Figure 5 It is a structural block diagram of an electronic device used to implement the method for generating guidance information according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0016] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0017] In some technical solutions, guidance components designed to guide users toward conversion behaviors appear at fixed times. For example, after a user enters a reservation page, a pop-up window might be displayed immediately within the reservation page, prompting or guiding the user to take conversion actions such as leaving contact information, filling out a form, making a phone call, or placing an order. Another example is a pop-up window that appears immediately after the user closes the reservation page to retain the user.

[0018] It's understandable that the aforementioned technical solution employs a fixed-pattern guidance scheme to guide users, ignoring the varying preferences of different users regarding guidance timing. When the timing of the floating guidance display doesn't align with user expectations, it can create a sense of rejection in some users, hindering their willingness to convert on the intended page. Conversely, providing timely guidance after users have developed interest in the page they're currently browsing can have a positive effect.

[0019] The disclosed embodiments aim to provide a method for generating guidance information, which is applicable to advertising landing pages or similar application scenarios. This method can provide timely guidance to users based on their real-time behavior. For example, when a user browses to a certain page depth and clicks on page images and text multiple times, it can be assumed that the user has a high conversion intent at that moment. Therefore, guidance components such as floating layers and pop-ups can be used to guide the user to conversion, thereby achieving real-time and dynamic guidance.

[0020] The technical solutions provided by the present disclosure will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] Figure 1 3 is a schematic diagram of an application scenario of the method and device for generating guidance information according to an embodiment of the present disclosure.

[0022] It should be noted that Figure 1 The examples shown are merely examples of system architectures to which the embodiments of the present disclosure may be applied, to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure may not be used in other devices, systems, environments or scenarios.

[0023] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0024] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Terminal devices 101, 102, and 103 can be various electronic devices with display screens and support web browsing, including but not limited to smartphones, tablet computers, laptop computers, and desktop computers, etc.

[0025] The server 105 may be a server that provides various services, such as a background management server (for example only) that supports websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process received data such as user requests, and feed back processing results (such as target guidance information obtained or generated according to user requests) to the terminal device.

[0026] It should be noted that the method for generating guidance information provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the apparatus for generating guidance information provided in the embodiment of the present disclosure can generally be set in the server 105. The method for generating guidance information provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the apparatus for generating guidance information provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0027] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0028] Figure 2 is a schematic flowchart of a method for generating guidance information according to an embodiment of the present disclosure.

[0029] like Figure 2 As shown, the method 200 for generating guidance information may include operations S210 to S240.

[0030] In operation S210 , associated data of a target object is acquired, where the associated data includes behavior data generated by the target object with respect to a target page.

[0031] For example, the target object may be a user, and the target page may be an e-commerce shopping page, a video browsing page, or the like.

[0032] For example, behavioral data may include data generated by users browsing and operating on a page. For example, behavioral data may include browsing depth, dwell time, number of page swipes, number of image and text clicks, etc. For example, a page may be divided into 10 screens based on length. When a user browses to the 7th screen, the browsing depth is 70%.

[0033] For example, the associated data may be acquired at a predetermined time frequency, such as once every 1 second, thereby achieving an effect of collecting the associated data in real time.

[0034] In operation S220 , a correlation feature set corresponding to the correlation data is determined, where the correlation feature set includes a behavior feature corresponding to the behavior data.

[0035] For example, feature extraction can be performed on the associated data to obtain features corresponding to the associated data. The embodiment of the present disclosure does not limit the method of extracting features.

[0036] In operation S230 , a conversion rate corresponding to the associated feature set is determined.

[0037] For example, the conversion rate can represent the ratio between the number of conversions and the number of clicks on the target page. The conversion rate can also reflect the target audience's willingness to convert on the target page.

[0038] In one example, training samples can be pre-constructed. For example, historical ad logs and user behavior data on a page can be used as basic data. Features can be extracted from this basic data, including behavioral features. Clicks and conversions on the guidance component are used as sample labels. Training samples are constructed using the behavioral features and sample labels.

[0039] For example, after constructing the training samples, the conversion rate model can be trained using the training samples. The disclosed embodiments do not limit the network architecture of the conversion rate model. For example, the conversion rate model can include DNN (Deep Neural Networks). The disclosed embodiments do not limit the training method.

[0040] For example, after training the conversion rate model, the predetermined features can be processed into target samples, and then the trained conversion rate model can be used to process the target samples to obtain the conversion rate. For example, the conversion rate output by the conversion rate model can be a value between 0 and 1.

[0041] In operation S240 , if it is determined that the conversion rate satisfies a predetermined condition, target guide information is generated.

[0042] For example, a conversion rate threshold may be pre-set, and then the conversion rate is compared with the conversion rate threshold. If the conversion rate is greater than or equal to the conversion rate threshold, it is determined that the conversion rate meets the predetermined condition, and target guidance information is generated. For example, the conversion rate threshold may be 0.7.

[0043] For example, the front-end display page can be rendered according to the guidance information, thereby displaying floating layers, pop-up windows and other content to the user, thereby achieving the effect of guiding the user.

[0044] It is understandable that, when it is determined that the conversion rate does not meet the predetermined condition, the target guidance information may not be generated, and the process may return to the above operation S210 to determine whether to generate the target guidance information based on the re-acquired predetermined information.

[0045] According to the technical solution provided by the embodiment of the present disclosure, the real-time conversion rate of the landing page is determined by the real-time behavior of the user, and then whether the current time is appropriate for guidance is determined based on the conversion rate, and target guidance information is generated at the appropriate guidance time, thereby achieving the effect of timely guidance conversion, thereby improving the delivery efficiency and conversion effect of the landing page.

[0046] According to another embodiment of the present disclosure, the associated data further includes at least one of object data, page data, and advertisement data, and the associated feature set further includes at least one of object attribute features, page features, and advertisement features.

[0047] It can be seen that object data corresponds to object attribute features, page data corresponds to page features, and advertisement data corresponds to advertisement features.

[0048] In practical applications, the process of constructing training samples can use historical ad logs, user behavior data within a page, and page content as basic data. Features can be extracted from this basic data. These features can include behavioral features, object attribute features, page features, and ad features. Training samples can be generated based on these extracted features, using the click and conversion status of the guidance component as sample labels. The constructed training samples are then used to train a conversion rate model.

[0049] For example, a trained conversion rate model may be used to process target samples to obtain conversion rates. The target samples may be determined based on at least one of behavior features, object attribute features, page features, and advertisement features.

[0050] For example, behavioral characteristics can reflect browsing depth, dwell time, number of page swipes, number of image and text clicks, etc.

[0051] For example, object attribute characteristics may include age, gender, consumption intention, model of electronic device used, etc. A user profile label can be constructed for the target object in advance based on historical data such as the target object's historical behavior, and then the above object attribute characteristics can be determined based on the user profile label.

[0052] For example, page features may include the page title and conversion component information. A conversion component is a component used to collect leads. For example, a conversion component may include items such as a form box or a call button displayed on a page. Conversion component information may include the items included in the conversion component and the location of each item.

[0053] For example, ad features may include the target's search terms, traffic sources, province, city, etc. Traffic sources can represent the product channels that generate traffic. For example, product channels may include search terms, browsing information feeds, watching videos, and clicking on ads. Different traffic sources have corresponding source identifiers.

[0054] In addition, based on the features of the above-mentioned single categories, multiple cross-features can also be introduced, such as age-conversion component information and model-conversion component information. Age-conversion component information can be used to characterize the conversion tendencies of target objects of different ages to different conversion component information, and model-guide component style can be used to characterize the conversion tendencies of target objects with different electronic device models to different conversion component information.

[0055] According to the technical solution provided by the embodiment of the present disclosure, since the associated feature set is determined based on multiple dimensions such as behavioral characteristics, object attribute characteristics and page characteristics, the associated feature set can more accurately describe the conversion tendency of the target object to the guidance component, thereby improving the conversion effect.

[0056] According to another embodiment of the present disclosure, the above method may further include the following operation: according to the object data, retrieving an object attribute feature corresponding to the object data from a plurality of object features.

[0057] For example, multiple object attribute features can be pre-determined and stored, with each object attribute feature having a mapping relationship with object data (e.g., an object identifier). When needed, the object attribute feature corresponding to the object data can be directly retrieved from the stored multiple object features without having to calculate the object attribute features of the target object online, thereby improving data processing efficiency.

[0058] According to another embodiment of the present disclosure, the above method may further include the following operation: according to the page data, retrieving a page feature corresponding to the page data from a plurality of page features.

[0059] For example, similar to the object attribute features described above, multiple page features can be pre-determined and stored, with each page feature having a mapping relationship with page data (e.g., page identifier). When needed, the page feature corresponding to the page data can be directly retrieved from the stored multiple page features without the need to calculate the page features online, thereby improving data processing efficiency.

[0060] According to another embodiment of the present disclosure, the above method may further include the following operation: according to the advertisement data, retrieving an advertisement feature corresponding to the advertisement data from a plurality of advertisement features.

[0061] For example, similar to the object attribute features described above, multiple ad features can be pre-determined and stored, with each ad feature having a mapping relationship with ad data (e.g., ad identifier). When needed, the ad feature corresponding to the ad data can be directly retrieved from the stored ad features, eliminating the need to calculate the ad feature online, thereby improving data processing efficiency.

[0062] According to another embodiment of the present disclosure, the predetermined condition includes at least one of a first predetermined condition and a second predetermined condition.

[0063] For example, the first predetermined condition may include: a conversion rate greater than or equal to a first reference conversion rate of a predetermined object group, wherein the predetermined object group and the target object belong to the same category, and the first reference conversion rate is determined based on a historical conversion rate of the predetermined object group within a first predetermined period.

[0064] For example, based on the attribute information of the target object User_1, we know that the target object is a male user between the ages of 20 and 25 who uses a domestic mobile phone. The category of the target object User_1 can be determined based on different dimensions. For example, the category of the target object User_1 under the "age" dimension is "20-25 years old" and the category under the "gender" dimension is "male".

[0065] For example, categories in different dimensions can correspond to different target groups. In practical applications, for example, the target object's category information can be determined based on the object data. Then, based on this category information, a first reference conversion rate for the predetermined target group can be obtained. Furthermore, each target group has a corresponding first reference conversion rate. For example, the first reference conversion rate for the "male group" is 0.6, and the first reference conversion rate for the "20-25 year old user group" is 0.65. For example, the first reference conversion rate can be determined by taking the average conversion rate of the target group over other time periods over the past month.

[0066] For example, the conversion rate of the target object User_1 can be compared with the first reference conversion rate of the predetermined target group in each category to which it belongs. For example, if the conversion rate of the target object User_1 is 0.68, which is greater than the first reference conversion rate of the "20-25 year old user group," it can be determined that the conversion rate meets the first predetermined condition. Therefore, the target object User_1 is considered to have a high conversion tendency and can be guided using the guidance component.

[0067] For another example, you can pre-specify the target category, such as "gender". In this case, you can only compare the conversion rate of the target object User_1 with the reference conversion rate of the "male group", without comparing the conversion rate of the target object User_1 with the reference conversion rate of the "20-25 year old user group".

[0068] It can be seen that the conversion intention of the target object can be accurately determined by using the first reference conversion rate of the predetermined object group belonging to the same category as the target object.

[0069] For example, the second predetermined condition may include: the conversion rate is greater than or equal to a second reference conversion rate of the target page, wherein the second reference conversion rate is determined based on a historical conversion rate of the target page within a second predetermined period of time.

[0070] For example, multiple target pages may have respective second reference conversion rates. For example, the reference conversion rate of a page about selling high-end flagship mobile phones is 0.05, and the reference conversion rate of a page about selling discounted fruits is 0.4.

[0071] For example, a second reference conversion rate of the target page browsed by the current target object over a predetermined period of time in the past can be calculated in advance. For example, the average conversion rate of the target page over the past month or other period can be determined as the second reference conversion rate. For example, if the second reference conversion rate is 0.3 and the conversion rate of the target object is 0.5, since the conversion rate is greater than the second reference conversion rate, it can be determined that the conversion rate meets the second predetermined condition, and the target object has a high conversion tendency at this time, and can be guided using the guidance component.

[0072] It can be seen that by comparing with the second reference conversion rate of the target page, the conversion intention of the target object can be accurately determined.

[0073] According to another embodiment of the present disclosure, a target page is associated with at least two candidate navigation information; and the operation of determining an associated feature set corresponding to the associated data may include the following operation: for each of the plurality of candidate navigation information, determining an associated feature set corresponding to the candidate navigation information based on the candidate navigation information and the associated data, thereby obtaining a plurality of associated feature sets corresponding to the plurality of candidate navigation information. Each associated feature set includes features corresponding to the candidate navigation information and features corresponding to the associated data.

[0074] For example, the associated data may correspond to certain features, which may include behavioral feature A, page feature B, object attribute feature C, and advertising feature D. The target page is associated with candidate guidance information E1, E2, and E3. The three types of candidate guidance information include different attribute information such as copywriting and product form. The three types of candidate guidance information E1, E2, and E3 correspond to guidance features E1', E2', and E3', respectively. In the process of determining the associated feature set, a first associated feature set M1 can be constructed based on behavioral feature A, page feature B, object attribute feature C, advertising feature D, and guidance feature E1'; a second associated feature set M2 can be constructed based on behavioral feature A, page feature B, object attribute feature C, advertising feature D, and guidance feature E2'; and a third associated feature set M3 can be constructed based on behavioral feature A, page feature B, object attribute feature C, advertising feature D, and guidance feature E3'.

[0075] It can be seen that the conversion rate determined based on the associated feature set including the guidance feature can reflect the target object's conversion tendency for different guidance information, thereby accurately evaluating the target object's current conversion intention and improving the conversion effect.

[0076] According to the technical solutions provided by the embodiments of this disclosure, it is possible to pre-design various styles of guidance information, and construct a set of associated features based on each style of guidance information. Therefore, when the associated data sets are subsequently processed and merged to obtain a conversion rate, the conversion rate can reflect the target subject's preference for the guidance information style. This can then lead to the selection of a specific style of guidance information for the target subject based on their preferences, presenting different guidance information to different target subjects, further improving conversion effectiveness.

[0077] It should be noted that, in the process of pre-constructing training samples and training the conversion rate model, it is also possible to construct training samples based on the guidance features corresponding to the guidance information, and train the conversion rate model based on the training samples including the guidance features, so that the conversion rate model can accurately calculate the conversion rate when the associated feature set includes the guidance features. In addition, in the process of constructing samples, in addition to using the above-mentioned single category features to construct the target sample, multiple cross-features can also be introduced, such as age-guidance information and model-guidance information. Age-guidance information can be used to characterize the conversion tendency of target objects of different ages to different styles of guidance information, and model-guidance information style can be used to characterize the conversion tendency of target objects with different mobile phone models to different styles of guidance information.

[0078] According to another embodiment of the present disclosure, the operation of determining the conversion rate corresponding to the associated feature set may include the following operations: determining the conversion rate corresponding to each of the multiple associated feature sets to obtain multiple conversion rates. Accordingly, the operation of generating target guidance information when the conversion rate is determined to meet a predetermined condition may include the following operations: when the maximum conversion rate among the multiple conversion rates is determined to meet the predetermined condition, determining the candidate guidance information corresponding to the maximum conversion rate as the target guidance information; and generating the target guidance information.

[0079] For example, after determining at least two associated feature sets, each feature set can be processed into a target sample, thereby obtaining at least two target samples. The target samples are then processed using a conversion rate model to obtain a conversion rate for each target sample.

[0080] For example, the conversion rates corresponding to the aforementioned associated feature sets M1, M2, and M3 are 0.8, 0.6, and 0.3, respectively. A conversion rate of 0.5 or greater is considered to satisfy the predetermined condition. It can be seen that both associated feature sets M1 and M2 satisfy the predetermined condition. Furthermore, the conversion rate of associated feature set M1 is higher than that of associated feature set M2, indicating that the target object has a higher conversion tendency towards guidance information E2. Therefore, guidance information E2 is selected as the target guidance information.

[0081] The embodiment of the present disclosure determines the target guidance information according to the candidate guidance information corresponding to the maximum conversion rate, so that the guidance information with the highest conversion tendency can be displayed to the current target object, thereby improving the guidance effect.

[0082] Figure 3 is a schematic diagram of a method for generating guidance information according to an embodiment of the present disclosure.

[0083] like Figure 3 As shown, in this embodiment, a front-end page 310 , a device 320 , a feature service 330 , a conversion rate model 340 and a database 350 may be involved.

[0084] The associated data is obtained through the front-end page 310. For example, the front-end page 310 may be an advertisement landing page, and the user may operate in the currently displayed target page. The front-end page 310 may send a request including predetermined data such as behavior data, page data, object data, and advertisement data to the back-end, which processes the request and then sends the processed request to the device 320.

[0085] Device 320 can request feature service 330 and use it to determine a set of associated features corresponding to the predetermined data. For example, feature service 330 may pre-store multiple object features, multiple page features, and multiple advertisement features. Feature service 330 can then retrieve object attribute features corresponding to the object data from the multiple object features, retrieve page features corresponding to the page data from the multiple page features, and retrieve advertisement features corresponding to the advertisement data from the multiple advertisement features. Feature extraction can also be performed on the behavioral data to obtain features corresponding to the behavioral data. Furthermore, the target page can be associated with at least two candidate guidance information. That is, the target page can display a certain candidate guidance information to guide the user to perform a conversion action, while the target page can also display another candidate guidance information to guide the user to perform a conversion action. Feature service 330 can also retrieve guidance features corresponding to the candidate guidance information from the multiple guidance features based on the candidate guidance information associated with the target page. Feature service 330 can then return the behavioral features, object attribute features, page features, advertisement features, and guidance features to device 320.

[0086] The device 320 may include a real-time feature processing module 321 and an evaluation module 322 .

[0087] The real-time feature processing module 321 in device 320 can process the acquired multiple features to obtain target samples. For example, the real-time feature processing module 321 performs predetermined processing such as cleaning and discretization on the multiple features to obtain target samples. Device 320 can then send the target samples to a pre-trained conversion rate model 340. Conversion rate model 340 processes the target samples and outputs a conversion rate, which is then returned to device 320.

[0088] It should be noted that when the target page is associated with at least two candidate guidance information, the real-time feature processing module 321 can construct a target sample based on the candidate guidance information. For example, if the target page is associated with candidate guidance information E1, E2, and E3, any one of the candidate guidance information E1, E2, and E3 can be displayed on the target page to guide the user. The real-time feature processing module 321 can construct a first target sample based on the characteristics corresponding to the associated data (e.g., behavioral characteristics, object attribute characteristics, page characteristics, advertising characteristics, etc.) and candidate guidance information E1. It can also construct a second target sample based on the characteristics corresponding to the associated data and candidate guidance information E2. It can also construct a third target sample based on the characteristics corresponding to the associated data and candidate guidance information E3. The device 320 then sends the first, second, and third target samples to the pre-trained conversion rate model 340. The conversion rate model 340 determines three conversion rates corresponding to the first, second, and third target samples, respectively. These three conversion rates can reflect the user's conversion tendency towards the candidate guidance information E1, E2, and E3 on the target page.

[0089] Next, the evaluation module 322 in the device 320 can obtain reference conversion rates from the database 350. For example, the first reference conversion rate for a group of objects belonging to the same category as the target object can be retrieved from the database 350 based on the object data, and the second reference conversion rate for the target page can be retrieved from the database 350 based on the page data. The evaluation module 322 can then compare the first and second reference conversion rates with the conversion rate, and if either the first or second reference conversion rate is lower than the conversion rate, the evaluation module 322 can determine that the user currently has a high conversion propensity and is suitable for conversion guidance. Therefore, the predetermined conditions are determined to be met and target guidance information is generated.

[0090] Next, the device 320 returns the guidance information to the front-end page 310 , and the front-end page 310 renders the guidance information, thereby guiding the user to convert.

[0091] Figure 4 It is a schematic structural block diagram of an apparatus for generating guidance information according to an embodiment of the present disclosure.

[0092] like Figure 4 As shown, the device 400 for generating guidance information may include an acquisition module 410 , a first determination module 420 , a second determination module 430 and a generation module 440 .

[0093] The acquisition module 410 is used to acquire the associated data of the target object, where the associated data includes the behavior data generated by the target object with respect to the target page.

[0094] The first determining module 420 is configured to determine a set of associated features corresponding to the associated data, where the set of associated features includes behavioral features corresponding to the behavioral data.

[0095] The second determining module 430 is configured to determine a conversion rate corresponding to the associated feature set.

[0096] The generating module 440 is configured to generate target guidance information when it is determined that the conversion rate meets a predetermined condition.

[0097] According to another embodiment of the present disclosure, the predetermined condition includes at least one of the following: a conversion rate greater than or equal to a first reference conversion rate of a predetermined target group, wherein the predetermined target group and the target target belong to the same category, and the first reference conversion rate is determined based on the historical conversion rate of the predetermined target group within a first predetermined time period; and a conversion rate greater than or equal to a second reference conversion rate of the target page, wherein the second reference conversion rate is determined based on the historical conversion rate of the target page within a second predetermined time period.

[0098] According to another embodiment of the present disclosure, the associated data further includes at least one of object data, page data, and advertisement data, and the associated feature set further includes at least one of object attribute features, page features, and advertisement features.

[0099] According to another embodiment of the present disclosure, the apparatus further includes at least one of a first retrieval module, a second retrieval module, and a third retrieval module. The first retrieval module is configured to retrieve, based on the object data, object attribute features corresponding to the object data from a plurality of object features. The second retrieval module is configured to retrieve, based on the page data, page features corresponding to the page data from a plurality of page features. The third retrieval module is configured to retrieve, based on the advertisement data, advertisement features corresponding to the advertisement data from a plurality of advertisement features.

[0100] According to another embodiment of the present disclosure, a target page is associated with at least two candidate guidance information. A first determination module includes a first determination unit configured to determine, for each of the at least two candidate guidance information, a set of associated features corresponding to the candidate guidance information based on the candidate guidance information and associated data, thereby obtaining at least two associated feature sets corresponding to the at least two candidate guidance information, respectively; wherein each associated feature set includes features corresponding to the candidate guidance information and features corresponding to the associated data.

[0101] According to another embodiment of the present disclosure, the second determination module includes: a second determination unit configured to determine a conversion rate corresponding to each of at least two associated feature sets, thereby obtaining at least two conversion rates. Accordingly, the generation module includes a third determination unit and a generation unit. The third determination unit is configured to, upon determining that the maximum conversion rate of the at least two conversion rates satisfies a predetermined condition, determine the candidate guidance information corresponding to the maximum conversion rate as the target guidance information. The generation unit is configured to generate the target guidance information.

[0102] According to another embodiment of the present disclosure, the conversion rate represents the ratio between the number of conversions and the number of clicks of the target page.

[0103] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0104] In the technical solution disclosed herein, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0105] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, including at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above-mentioned method of generating guidance information.

[0106] According to an embodiment of the present disclosure, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the above method for generating guidance information.

[0107] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, including a computer program, which implements the above method for generating guidance information when executed by a processor.

[0108] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0109] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0110] Various components in device 500 are connected to I / O interface 505, including: an input unit 506, such as a keyboard, mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, optical disk, etc.; and a communication unit 509, such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0111] The computing unit 501 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as the method for generating boot information. For example, in some embodiments, the method for generating boot information can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the method for generating boot information described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the method for generating boot information by any other appropriate means (e.g., by means of firmware).

[0112] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0114] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0115] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0116] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0117] Computer systems may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The client and server relationship arises through computer programs running on the respective computers and having a client-server relationship to each other.

[0118] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0119] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for generating guidance information, comprising: Acquire associated data of a target object, wherein the associated data includes behavior data generated by the target object with respect to a target page; Determining a set of associated features corresponding to the associated data, wherein the set of associated features includes a behavior feature corresponding to the behavior data; determining a conversion rate corresponding to the associated feature set; Retrieving, based on the object data of the target object, a first reference conversion rate of a predetermined group of objects belonging to the same category as the target object; The first reference conversion rate is determined based on a historical conversion rate of the predetermined target group within a first predetermined time period; Retrieving a second reference conversion rate of the target page according to the page data of the target page; The second reference conversion rate is determined based on a historical conversion rate of the target page within a second predetermined period; When the conversion rate is greater than or equal to the first reference conversion rate and the conversion rate is greater than or equal to the second reference conversion rate, determining that the conversion rate satisfies a predetermined condition; as well as When it is determined that the conversion rate meets the predetermined condition, target guidance information is generated.

2. The method according to claim 1, wherein The associated data further includes at least one of object data, page data, and advertisement data, and the associated feature set further includes at least one of object attribute features, page features, and advertisement features.

3. The method according to claim 2, further comprising at least one of the following: Retrieving, according to the object data, an object attribute feature corresponding to the object data from a plurality of object features; Retrieving, according to the page data, a page feature corresponding to the page data from a plurality of page features; and According to the advertisement data, an advertisement feature corresponding to the advertisement data is retrieved from a plurality of advertisement features.

4. The method according to any one of claims 1 to 3, wherein: The target page is related to at least two candidate guidance information; and determining the associated feature set corresponding to the associated data includes: For each of the at least two candidate guidance information, determining, based on the candidate guidance information and the association data, a set of associated features corresponding to the candidate guidance information, to obtain at least two sets of associated features corresponding to the at least two candidate guidance information, respectively; Each associated feature set includes features corresponding to the candidate guidance information and features corresponding to the associated data.

5. The method according to claim 4, wherein Determining the conversion rate corresponding to the associated feature set includes: determining a conversion rate corresponding to each of the at least two associated feature sets to obtain at least two conversion rates; Wherein, when it is determined that the conversion rate satisfies a predetermined condition, generating target guidance information includes: If it is determined that the maximum conversion rate among the at least two conversion rates satisfies the predetermined condition, determining the candidate guidance information corresponding to the maximum conversion rate as the target guidance information; and The target guidance information is generated.

6. The method according to claim 1, wherein The conversion rate represents the ratio between the number of conversions and the number of clicks on the target page.

7. A device for generating guidance information, comprising: An acquisition module, configured to acquire associated data of a target object, wherein the associated data includes behavior data generated by the target object with respect to a target page; a first determining module, configured to determine a set of associated features corresponding to the associated data, wherein the set of associated features includes a behavior feature corresponding to the behavior data; A second determining module is used to determine a conversion rate corresponding to the associated feature set; a processing module, configured to retrieve, based on the object data of the target object, a first reference conversion rate of a predetermined group of objects belonging to the same category as the target object; The first reference conversion rate is determined based on a historical conversion rate of the predetermined target group within a first predetermined period; and a second reference conversion rate of the target page is retrieved based on page data of the target page; The second reference conversion rate is determined based on a historical conversion rate of the target page within a second predetermined period; if the conversion rate is greater than or equal to the first reference conversion rate and the conversion rate is greater than or equal to the second reference conversion rate, it is determined that the conversion rate meets the predetermined condition; as well as A generating module is used to generate target guidance information when it is determined that the conversion rate meets the predetermined condition.

8. The device according to claim 7, wherein The associated data further includes at least one of object data, page data, and advertisement data, and the associated feature set further includes at least one of object attribute features, page features, and advertisement features.

9. The apparatus of claim 8, further comprising at least one of the following: A first retrieval module is configured to retrieve, based on the object data, an object attribute feature corresponding to the object data from a plurality of object features; A second retrieval module is configured to retrieve, based on the page data, a page feature corresponding to the page data from a plurality of page features; as well as The third retrieval module is configured to retrieve, based on the advertisement data, an advertisement feature corresponding to the advertisement data from a plurality of advertisement features.

10. The device according to any one of claims 7 to 9, wherein: The target page is related to at least two candidate guidance information; the first determining module includes: a first determining unit configured to determine, for each of the at least two candidate guidance information, a set of associated features corresponding to the candidate guidance information based on the candidate guidance information and the associated data, to obtain at least two sets of associated features corresponding to the at least two candidate guidance information, respectively; Each associated feature set includes features corresponding to the candidate guidance information and features corresponding to the associated data.

11. The device according to claim 10, wherein The second determining module includes: a second determining unit, configured to determine a conversion rate corresponding to each of the at least two associated feature sets, to obtain at least two conversion rates; Wherein, the generation module includes: a third determining unit, configured to, if it is determined that a maximum conversion rate among the at least two conversion rates satisfies the predetermined condition, determine the candidate guidance information corresponding to the maximum conversion rate as the target guidance information; and A generating unit is configured to generate the target guidance information.

12. The device according to claim 7, wherein The conversion rate represents the ratio between the number of conversions and the number of clicks on the target page.

13. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 6.

15. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images