CN114697889A

CN114697889A - Method and device for processing information

Info

Publication number: CN114697889A
Application number: CN202011619500.5A
Authority: CN
Inventors: 王岩; 杨逸文
Original assignee: Samsung Guangzhou Mobile R&D Center; Samsung Electronics Co Ltd
Current assignee: Samsung Guangzhou Mobile R&D Center; Samsung Electronics Co Ltd
Priority date: 2020-12-31
Filing date: 2020-12-31
Publication date: 2022-07-01
Also published as: WO2022145836A1

Abstract

The present disclosure provides a method of processing information and an apparatus thereof. The method for processing information comprises the following steps: acquiring information; performing content analysis on the information to obtain an object included in the information; and determining whether to intercept the information based on the object. The present disclosure can efficiently intercept useless information and transmit desired information to a user for different users.

Description

Method and device for processing information

Technical Field

The present disclosure relates to the field of electronic device control technology and the field of Artificial Intelligence (AI), and more particularly, to a method and apparatus for processing information.

Background

The short message service is a short text information receiving and transmitting mode based on a mobile communication network. The message is received, stored and sent by the short message service center. The service is widely applied to all mobile communication networks, and has increasingly become one of the most frequently applied services for mobile phone users. And many businesses are also more and more favored to use the convenient and cheap advertising approach.

Because of the increasing number of notification information, mobile phone users receive a great amount of information every day. Among these information, which is valuable to the user requires the user to screen and authenticate himself. Information that is not valuable to the user may cause unnecessary burden and trouble to the user.

The information interception strategy applied to the current mobile phone intercepts the information received by the mobile phone by establishing a blacklist database. With the continuous update of the blacklist database, the mobile phone can intercept more information which is probably junk information. However, the information interception strategy at the present stage intercepts information one by one, and the information required by the user may be missed due to different times and different reasons.

Disclosure of Invention

Exemplary embodiments of the present disclosure provide a method of processing information and an apparatus thereof, which solve at least the above technical problems and other technical problems not mentioned above, and provide the following advantageous effects.

An aspect of the present disclosure is to provide a method of processing information, which may include: acquiring information; performing content analysis on the information to obtain an object included in the information; and determining whether to intercept the information based on the object.

Optionally, the step of obtaining information may comprise obtaining said information from information intercepted by a third party application.

Optionally, the object may include at least one of a good, a brand, a category, and a platform.

Optionally, the step of determining whether to intercept the information may comprise: determining whether the object meets the requirements of a user; and if the object meets the user requirement, the information is not intercepted, otherwise, the information is intercepted.

Optionally, the step of determining whether the object meets the user requirement may include: determining whether the object meets a user's needs based on historical data of shopping-related behavior of the user.

Optionally, the shopping-related behavior may include potential shopping behavior and factual shopping behavior.

Optionally, the historical data relating to the potential shopping behavior may include data collected when the user performs at least one of the following: launching or running a shopping class application in the electronic device, opening a link to the item, browsing the item, whether the item is added to a shopping cart, and whether the item is added to a favorite.

Alternatively, the historical data relating to the factual shopping behavior may include data collected by the user when purchasing goods within a predetermined period of time.

Optionally, the step of determining whether the object meets the user's requirements based on the historical data of the shopping-related behavior of the user may comprise: training an artificial intelligence model using historical data related to the potential shopping behavior, and determining whether the object meets a user demand based on the trained artificial intelligence model.

Optionally, the step of determining whether the object meets the user's requirements based on the trained artificial intelligence model may comprise: running the artificial intelligence model by utilizing data of shopping related behaviors in a recent preset time period to obtain a first object set meeting the requirements of a user; matching the object with elements in a first set of objects; if the object matches an element in the first set of objects, determining that the object satisfies the user requirement, otherwise determining that the object does not satisfy the user requirement.

Alternatively, the artificial intelligence model may be trained based on: generating characteristic data based on the category, the times and the duration of the commodity browsed by the user; generating tag data based on at least one of whether the item is added to the favorite and whether the item is added to the shopping cart, wherein if the item is not added to the favorite and not added to the shopping cart within a predetermined time, the tag is set not to meet the user requirement, otherwise the tag is set to meet the user requirement; training the artificial intelligence model using the feature data and the label data.

Optionally, the step of determining whether the object meets the user's requirements based on the historical data of the shopping-related behavior of the user may comprise: determining a second set of objects involved in a user's purchasing habits based on historical data related to the factual shopping behavior; matching the object with elements in a second set of objects; and if the object is matched with elements in the second object set, determining that the object meets the user requirement, otherwise, determining that the object does not meet the user requirement.

Another aspect of the present disclosure is to provide an apparatus for processing information, which may include: a receiving module configured to acquire information; a parsing module configured to perform content parsing on the information to obtain an object included in the information; and a determination module configured to determine whether to intercept the information based on the object.

Optionally, the receiving module may be configured to obtain the information from information intercepted by the third party application.

Optionally, the object may include at least one of a commodity, a brand, a category, and a platform.

Optionally, the determining module may be configured to determine whether the object meets a user requirement; and if the object meets the user requirement, the information is not intercepted, otherwise, the information is intercepted.

Optionally, the determination module may be configured to determine whether the object meets the user's requirements based on historical data of shopping-related behavior of the user.

Optionally, the determination module may be configured to train an artificial intelligence model using historical data related to the potential shopping behavior, and determine whether the object meets the user's needs based on the trained artificial intelligence model.

Optionally, the determining module may be configured to: running the artificial intelligence model by utilizing data of shopping related behaviors in a recent preset time period to obtain a first object set meeting the requirements of a user; matching the object with elements in a first set of objects; if the object matches an element in the first set of objects, determining that the object satisfies the user requirement, otherwise determining that the object does not satisfy the user requirement.

Optionally, the determining module may be configured to: determining a second set of objects involved in a user's purchasing habits based on historical data related to the factual shopping behavior; matching the object with elements in a second set of objects; and if the object is matched with elements in the second object set, determining that the object meets the user requirement, otherwise, determining that the object does not meet the user requirement.

According to an exemplary embodiment of the present disclosure, there is provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements the method of processing information as described above.

According to another exemplary embodiment of the present disclosure, a computer is provided, comprising a readable medium having a computer program stored thereon and a processor, characterized in that the method of processing information as described above is performed when the processor runs the computer program.

According to another exemplary embodiment of the present disclosure, a computer program product is provided, in which instructions are executed by at least one processor in an electronic device to perform the method of processing information as described above.

The device and the method can effectively intercept useless information and send required information to the user aiming at different users, thereby not only reducing the burden and trouble of reading the information by the user, but also meeting the requirements of the user.

Additional aspects and/or advantages of the present general inventive concept will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the general inventive concept.

Drawings

These and/or other aspects and advantages of the present disclosure will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 is a flowchart illustrating a method of processing information according to an exemplary embodiment of the present disclosure;

FIG. 2 is a flowchart illustrating a method of processing information according to another exemplary embodiment of the present disclosure;

fig. 3 is a block diagram illustrating an apparatus for processing information according to an exemplary embodiment of the present disclosure;

FIG. 4 is a schematic diagram illustrating a computing device according to an example embodiment of the present disclosure;

FIG. 5 is a distribution diagram of purchase dates for a commodity within a cycle period according to an exemplary embodiment of the present disclosure.

Detailed Description

The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of the embodiments of the disclosure as defined by the claims and their equivalents. Various specific details are included to aid understanding, but these are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the disclosure, as detailed in the appended claims.

Although the current information interception strategy can intercept spam, the definition of spam is not exactly the same for each real and specific user. For example, a user may often browse through items to be purchased but not discard them, and may purchase them at a certain time (for example, at a shopping festival such as "double 11" or "6, 18"). The shopping node has high discount strength, and merchants can push out a lot of discount information and send the coupon playing method to users for reference. At this point, the user may prefer to have access to such associated offer information and purchase a long-lived item at a more favorable price. At this time, the user no longer regards the promotion information as spam but rather a flash report of the product preference information, but the information is still intercepted as spam. Therefore, the definition of the spam information is different from person to person, and the spam information is intercepted from time to time and cannot meet the personalized requirements of users.

However, the method and the device can perform personalized information interception aiming at the requirements of different users in different periods, namely effectively acquire the requirements of different users on information, thereby effectively screening and intercepting the information, customizing personalized information interception strategies for different users to realize that the users acquire required information and intercept useless junk information.

Reference will now be made in detail to the exemplary embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the like elements throughout. Hereinafter, according to various embodiments of the present disclosure, an apparatus and a method of the present disclosure will be described with reference to the accompanying drawings.

Fig. 1 is a flowchart illustrating a method of processing information according to an exemplary embodiment of the present disclosure. According to the embodiment of the disclosure, the spam intercepting function of the disclosure can be independently realized by a third party application or a manufacturer, that is, the method for processing information of the disclosure is added to the intercepting rule, and the judgment is completed when the electronic device receives (such as a mobile phone). Alternatively, the electronic device may obtain back the information intercepted/filtered by the third-party application or the manufacturer, that is, obtain the previously intercepted information from the information intercepted by the third-party application, and then execute the spam intercepting function of the present disclosure in the electronic device.

In the present disclosure, the electronic device may be any electronic device having a function of receiving and transmitting external information. In an example embodiment of the present disclosure, the electronic device may include, for example, but not limited to, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a wearable device, and the like. However, the electronic device is not limited to those mobile terminals described above.

Referring to fig. 1, in step S101, information is acquired. For example, the electronic device may receive a large amount of notification-like information from the outside, such as information on a certain product offer. Or the electronic device derives the information to be processed from the information filtered out by the third party application.

In step S102, content parsing may be performed on the acquired information to obtain an object included in the information. In the present disclosure, an object may be, but is not limited to, a certain commodity. The object may include at least one of a commodity, a brand, a category, and a platform, however the above examples are merely exemplary and the disclosure is not limited thereto.

As an example, when the electronic device receives a piece of information about a sales promotion of an item, the electronic device may parse textual content in the information to obtain information about at least one of the items, the purchase platform, the brand and category, and the like. The parsing method may include, but is not limited to, a semantic analysis method.

In step S103, it is determined whether to intercept the received information to the user based on the obtained object. According to the embodiment of the disclosure, the electronic device can determine whether an object in the information meets the user requirement, if the object meets the user requirement, the information received by the electronic device is sent to the user, that is, the information is not intercepted, otherwise, the information received by the electronic device is intercepted to the user, that is, the information is intercepted. Whether an object in the information meets the user's needs may be determined based on historical data of the user's shopping-related behavior. The user demand may include at least one of a user's desire to purchase and a user's purchasing habits, although the present disclosure is not limited thereto. For example, the information sent by the electronic device to the user may include promotion and preference information related to the product that the user wants to purchase. A method of how to intercept information received by the electronic device to a user will be explained in detail below with reference to fig. 2.

Fig. 2 is a flowchart illustrating a method of processing information according to another exemplary embodiment of the present disclosure. Referring to fig. 2, in step S201, the electronic device determines whether there is new information to be processed. For example, when the electronic device receives new information, the process proceeds to step S202, otherwise, the electronic device waits for receiving new information. For another example, the electronic device obtains information to be processed from the information intercepted by the third-party application, and proceeds to step S202, otherwise, waits for receiving new information.

In step S202, the electronic device parses the acquired information to obtain an object included in the information. In the present disclosure, the object may be at least one of, for example, a commodity, a purchase platform, a category, and a brand. However, the object is not limited thereto, and may include other objects. As an example, the electronic device may obtain the object included in the information by parsing the obtained information through a semantic analysis method.

In step S203, it is determined whether the object satisfies the user' S desire to purchase. According to an embodiment of the present disclosure, the electronic device may determine whether an object included in the information satisfies a user's purchase intention based on history data of shopping-related behavior of the user. Shopping-related behavior may include potential shopping behavior and factual shopping behavior. For example, an artificial intelligence model is trained using historical data related to potential shopping behavior, and a determination is made as to whether an object in the information satisfies a user's willingness to purchase based on the trained artificial intelligence model.

By way of example, historical data relating to potential shopping behavior may include data collected when a user performs at least one of the following: launching or running a shopping class application in the electronic device, opening a link to the item, browsing the item, whether the item is added to a shopping cart, and whether the item is added to a favorite. The electronic device monitors the application program or process of the electronic device to determine whether the user starts the application program or process of the shopping class. The shopping-like application or process may include, but is not limited to, a shopping-like application, a shopping-like applet, a shopping-like application, a link containing an introduction to a commodity, a link containing an evaluation of the commodity, a web link such as a link containing a group purchase of the commodity, a search for a name of the commodity in a browser, and the like. For example, when a user launches a shopping-like application, the electronic device may confirm that the user has potential shopping-related behavior.

According to an embodiment of the present disclosure, the history data of shopping-related behavior may include data of user browsing merchandise (hereinafter, may be referred to as browsing data) collected and counted when the user is detected to have potential shopping behavior. When the potential shopping-related behaviors of the user are monitored, the electronic equipment starts to collect data related to browsing or purchasing commodities of the user. If the electronic device does not monitor the user for potential shopping-related behavior, the monitoring continues.

As an example, when it is monitored that the user starts the shopping application, the electronic device starts to collect behavior data of browsing/purchasing goods by the user, including but not limited to starting a background assistant tool, analyzing a control of a currently displayed page of the shopping application, and capturing content.

The data of the commodities browsed by the user can comprise the attributes of the commodities and behavior data of the commodities browsed by the user. The behavior data of the user browsing the goods may include at least one of whether the goods are added to the shopping cart, whether the goods are added to the favorites, and whether the goods are purchased.

As an example, when it is monitored that a currently displayed page is a commodity detail page, the electronic device starts to acquire HTML commodity description information contained in the page, performs text content analysis on the information, acquires attributes of a brand, a category and the like of a commodity viewed by a user, and monitors whether the user has operations of entering a shopping cart, collecting the commodity and purchasing the commodity.

In addition, when data of browsing the commodities by the user is collected, the browsing times, browsing duration and browsing date of the browsed commodities can be counted. For example, in the process of browsing the commodity by the user, the electronic device performs timing processing to obtain the browsing duration for the user to browse the commodity, and the browsing times for the user to browse the commodity is increased by 1 time, and the browsing date for browsing the commodity is recorded.

As an example, a period time T may be set, for example, the period time T is set to 1 day, and each browsing data records only the number of times that the user browses the corresponding product within the period time T, the accumulated browsing duration, the browsing date, and the related operations (such as whether to join a shopping cart, whether to collect, whether to purchase, etc.). If the user has the action of adding the corresponding commodity into the shopping cart within a period time T, marking 'whether to add the shopping cart' in the browsing data related to the corresponding commodity as 'yes'; otherwise, the flag is "no". If the user has the behavior of collecting the corresponding commodity in a period T, marking whether to collect or not in the browsing data related to the corresponding commodity as yes; otherwise, the flag is "no". If the user has an action of purchasing a corresponding commodity within a period time T, "purchase or not" in the browsing data related to the corresponding commodity is marked as "yes"; otherwise, the flag is "no".

The identification for the item may be determined by an attribute of the item. Two items are considered to be the same item if they are of the same brand, category and purchase platform. In the case of the same article, the browsing behavior of the user during one cycle time T may correspond to only one browsing data.

According to an embodiment of the present disclosure, after obtaining history data of shopping-related behavior of a user, an Artificial Intelligence (AI) model may be trained using the history data of shopping-related behavior of the user, and whether the user has a desire to purchase an object included in information may be confirmed based on the trained AI model.

In the present disclosure, the AI model may include a general model and a user model. Here, the general model may be trained based on data collected for a plurality of users by a server connected to the electronic device, and the user model may be trained based on data for a single user using the electronic device. The AI model of the present disclosure may be, but is not limited to, a binary model.

AI models according to the present disclosure may include a general model, which may be an AI model suitable for a large number of users, and a user model, which may be a proprietary AI model suitable for a single user.

The generic model may be used until the amount of data (e.g., browsing data) collected by the electronic device satisfies a predetermined value, and the user model may be used or both the user model and the generic model may be used after the amount of data collected by the electronic device satisfies the predetermined value. For example, the generic model may be applied to the early stage, solving the "cold start problem". This is because the data of a single user collected by the electronic device at an early stage is very small, and the AI model trained using a small amount of data cannot accurately determine the purchase intention of the user, while the general model is trained by collecting a large amount of data of the user and conforms to the usage habits of most people, so that the general model can be used at the early stage. In the middle and later stages, the user model may be trained with personal data to obtain a more accurate AI model.

Alternatively, the generic model may be used at an early stage (e.g., the electronic device has not collected enough for 100 pieces of browsing data) and the user model may be used at a later stage (e.g., the electronic device has collected enough for 100 pieces of browsing data).

Alternatively, the generic model may be used at a previous stage and the integrated model at a later stage, i.e. the generic model and the user model are used in combination to determine whether the user has a desire to purchase the item contained in the information. In the case of using the integrated model, different weights may be set for the general model and the user model, for example, the weight of the user model is set to 3 and the weight of the general model is set to 1. However, the above examples are merely exemplary, and the present disclosure is not limited thereto.

The general model may use a model suitable for processing large-scale data, such as a neural network, a gradient boosting tree (GBDT), or the like. The user model may use a model such as a Support Vector Machine (SVM) suitable for processing small and medium scale data. However, the above example model is merely exemplary, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, an artificial intelligence model is trained based on: generating feature data based on a category, a number of times, and a duration that a user browses a commodity, generating tag data based on at least one of whether the commodity is added to a favorite and whether the commodity is added to a shopping cart, wherein if the commodity is not added to the favorite and not added to the shopping cart within a predetermined time, the tag is set not to satisfy a user requirement, otherwise the tag is set to satisfy the user requirement, and then training an artificial intelligence model using the feature data and the tag data.

As an example, feature data (such as purchase platform, category and brand of goods, category, number and duration of browsing goods) and tag data (such as whether to join a shopping cart, whether to collect and whether to purchase) of a large number of users may be used as training data to train parameters of the generic model. The parameters of the user model may be trained using only feature data and label data of a single user as training data.

The generic model may be trained on the server side in connection with the electronic device. The user model may be trained in an electronic device (e.g., a cell phone). For example, the user model may be trained when the mobile terminal is charged, so as to avoid consuming more power of the mobile terminal due to training.

The generic model may be downloaded to the electronic device for use. When the universal model is updated, the electronic equipment can download the new universal model from the server side so as to realize the updating of the universal model. Alternatively, the user's purchase intention may be predicted directly by using a general model on the server side, and then the electronic device completes the task of predicting the user's purchase intention by accessing the server interface.

User models may be trained and used in electronic devices. In addition, information collected in the electronic device may be sent to a server, which implements training of the user model.

According to another embodiment, when the received information includes a brand, a category, and a purchase platform of an item, the electronic device may retrieve an element matching an attribute (object) of the item in a first set of objects (also referred to as a purchase intention database), and utilize the element to determine a user's purchase intention for the item. Specifically, an object in the information is matched with elements in the first object set, if the object is matched with the elements in the first object set, the object is determined to meet the purchase intention of the user, and otherwise, the object is determined not to meet the purchase intention of the user.

For example, when the received information includes any two objects in a brand, a category, and a purchase platform of the goods, the electronic device may search the purchase intention database for elements matching the any two objects, and determine the purchase intention of the goods by the user using tag statistics for the searched elements. Here, each element in the purchase intention database may include an attribute of a specific item and a tag indicating a user's purchase intention for the specific item.

As an example, the first set of objects (purchase intention database) may be obtained using the AI model described above. Specifically, the artificial intelligence model is operated by using data of shopping related behaviors in a recent preset time period to obtain a purchase intention database meeting the purchase intention of the user. By using the AI model to determine whether the user has a desire to purchase the browsed goods, a purchase desire collection/purchase desire database can be obtained, wherein each element in the collection represents the purchase desire of the current user for a certain goods. For example, each element may include a purchase platform, brand, category of the item, and a user's willingness to purchase the item.

In the present disclosure, the AI model may only predict for items that are not clear to the user's desire to purchase. The product for which the user's intention of purchase is not clear means that "whether to join a shopping cart", "whether to collect", and "whether to purchase" in the browsing data of the corresponding product are all "no", that is, when the user browses a certain product, actions such as joining a shopping cart, adding to a favorite, or purchasing do not occur, it is not possible to determine the user's intention of purchase of the corresponding product. For example, if the value of "purchase or not" in the browsing data of a certain product is "yes", the intention of purchase is not predicted for the product. If at least one of the values of "add to shopping cart" and "collect or not" in the browsing data of an item is "yes", it is determined that the user has a purchase intention for the item, and the electronic device may add the item to the purchase intention set as an element of the purchase intention set.

Optionally, an expiration time D may be set, when an element including information and a purchase intention of a certain product already exists in the purchase intention set, and the user does not browse a corresponding product in the element within the expiration time D, that is, a date when the user browses the product last time passes the expiration time D from the current time, it may be determined that the user has lost the purchase intention for the product, and at this time, the electronic device may delete the element including the information and the purchase intention of the product from the purchase intention set, such a design better meets the current requirements of the user.

As an example, when a purchase platform (e.g., when), a brand (e.g., lily), a category (e.g., clothing) of a corresponding item is extracted according to the received new information, the electronic device may search for elements in a purchase intent set that match attributes of the corresponding item. If the elements related to the commodity exist in the purchase intention set, the new information is processed according to the purchase intention value of the commodity in the purchase intention set. For example, if the user ' S purchase intention of the item in the purchase intention set is "yes", step S205 is performed, the new information is normally sent to the user, and if the user ' S purchase intention of the item in the purchase intention set is "no", a judgment needs to be made according to the user ' S purchase habit, which will be explained below; if the commodity does not exist in the purchase intention set, the electronic equipment determines that the purchase intention of the commodity is 'no' by the user, and the information can be intercepted for the user.

When the new information to be processed does not include three attributes of the product platform, the product brand, and the product category, for example, only includes one or two attributes of the product platform, the product brand, and the product category, the one or two attributes may be used as search keywords, elements of a product including the two attributes of the corresponding product are searched from a purchase intention set predicted by using the AI model, and a search result is determined. For example, assuming that there are N items that simultaneously conform to the attributes of two items in the purchase intention set, if the purchase intention of (N +1)/2 items is "yes", the purchase intention of the item included in the information by the user may be determined as "yes", step S205 is performed, and the electronic device may normally transmit the information to the user; on the contrary, the user's desire to purchase the product included in the information may be determined as "no", and further judgment may be made according to the user's purchasing habits, which will be explained below.

For example, according to the information to be processed, two attributes of a purchase platform (easy-to-select net) and a category (mask) of the corresponding commodity are extracted, but the brand of the commodity is not included in the information. At this time, elements including all the commodities having the same platform and the same category may be retrieved from the purchase intention set predicted by the AI model, and the purchase intention values corresponding to the retrieved set elements may be analyzed. Assuming that 25 items in the purchase intention set and items corresponding to the information have the same platform and the same category and that the purchase intention of 18 items is yes, where 18> (25+1)/2), at this time, the electronic device may determine that the purchase intention of the item included in the information by the user is yes, then step S205 may be performed, the received information may be normally sent to the user, otherwise, step S204 may be performed, and whether to send the information to the user may be determined according to a user habit explained below.

According to another embodiment of the present disclosure, the parameters of the AI model may be updated based on data collected by the user when browsing and purchasing items within a predetermined period of time. When the potential shopping behavior of the user occurs, the electronic equipment can periodically collect data of browsing or purchasing commodities of the user, and the collected browsing data or purchasing data is used as training data to periodically train the AI model, so that the AI model is more consistent with the current shopping willingness and habit of the user, and the prediction is more accurate.

If the object included in the information satisfies the user' S desire to purchase, the process proceeds to step S205, and the information received by the electronic device is transmitted to the user. If the object included in the information does not satisfy the user' S desire to purchase, the process proceeds to step S204.

In step S204, it is determined whether the object in the information conforms to the user' S purchasing habits. The electronic device may determine whether the object in the information conforms to the shopping habit of the user by comparing the commodity attribute included in the history data of the shopping-related behavior of the user with the object in the information. Specifically, a second set of objects (hereinafter, referred to as a commodity purchase database) related to the purchasing habits of the user may be determined based on historical data related to the actual shopping behaviors, the object in the information is matched with elements in the second set of objects, and if the object is matched with elements in the second set of objects, the object is determined to be in accordance with the shopping habits of the user, otherwise, the object is determined not to be in accordance with the shopping habits of the user.

According to embodiments of the present disclosure, the history data of shopping-related activities may include purchase data collected and counted when a user is detected to purchase a commodity. For example, the historical data related to the actual shopping behavior includes data collected when the user purchases a good within a predetermined period of time. For example, the electronic device may analyze, via the accessibility tool, whether a control such as "submit an order" or "buy immediately" exists on a page currently viewed by the user. When the situation that the user clicks a control such as 'purchase immediately' is monitored, the user is considered to be purchasing commodities. At this time, the electronic device may obtain HTML commodity description information included in the page, perform text content analysis on the information, obtain a brand, a category, a purchase platform, and a purchase time of the commodity, and mark "purchase or not" in the purchase data of the commodity as "yes"; if "purchase or not" in the purchase data corresponding to the commodity is marked as "yes", the electronic device may update only the purchase date in the purchase data of the commodity, and add the latest purchase date to the purchase date of the purchase data of the commodity.

According to an embodiment of the present disclosure, the purchase data may include a purchase time at which the user purchased the goods and an attribute of the goods within a predetermined cycle period. For example, each purchase data may include commodity information including a platform of the commodity, a category to which the commodity belongs, and a brand of the commodity, and behavior data of purchasing the commodity including a "purchase or not purchase commodity" flag value and a date set of purchasing the commodity.

A cycle period M may be set in advance, for example, the cycle period M is set to 1 year, that is, the purchase data of the user is in a cycle of one year. The purchase date of the corresponding commodity purchased by the user is marked on the time axis within the cycle period M. If the user purchases the same commodity multiple times, the purchase date of the commodity is marked on the time axis in a cycle. For example, when recording the date of purchase of the user, only the month and day may be recorded, and not the year.

For example, suppose there is an item P with a brand a, a category B, and a purchasing platform JD, and the purchasing behavior data of the item P is shown in fig. 5. In fig. 5, when the purchase date of the commodity is projected on the time axis, the distribution of the dates of purchase of the commodity in the cycle period of one year can be visually seen, thereby determining that the commodity belongs to commodities requiring multiple purchases, which indicates that the commodity may be a consumable. And the time for the user to purchase the commodity is generally concentrated on months 3, 6 and 11. The above examples are merely illustrative, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, a commodity purchase database may be formed based on purchase data of a user. In the present disclosure, the user's purchasing habits may be determined from a commodity purchase database.

As an example, the purchase data of the commodities of all the same categories and the same purchase platforms in the purchase data may be selected, and the purchase dates of the selected corresponding commodities are all projected on a time axis with a time length of a predetermined cycle period (for example, 1 year), so as to determine in which time periods the user may purchase the commodities of the corresponding categories on the corresponding purchase platforms.

Alternatively, the purchase data of all the commodities of the same category and the same brand in the purchase data may be selected, and the purchase dates of the selected corresponding commodities are all projected on a time axis with a time length of a predetermined cycle period (for example, 1 year), so as to determine the time periods in which the user is likely to purchase the commodities of the corresponding category on the corresponding purchase platform.

Alternatively, the purchase data of all the commodities with the same purchase platform and the same brand in the purchase data may be selected, and the purchase dates of the selected corresponding commodities are all projected on a time axis with a time length of a predetermined cycle period (for example, 1 year), so as to determine the time periods in which the user is likely to purchase the commodities of the corresponding category on the corresponding purchase platform.

When the received information comprises the brand, the category and the purchasing platform of the corresponding commodity, the electronic equipment searches the commodity purchasing database for an element matched with the object in the information, and determines whether the content of the commodity conforms to the shopping habit of the user or not by using the element.

When the received information includes any two objects in the brand, category and purchase platform of the corresponding goods, the electronic device searches the goods purchase database for elements matching the any two objects, and determines whether the goods is a good that the user needs to purchase a plurality of times and whether the current time is near the purchase time when the user purchased the corresponding goods using the searched elements to determine whether the content of the received information conforms to the purchase habit of the user.

As an example, if the new information to be processed includes three objects of a platform, a brand and a category of a commodity, the electronic device may directly match with elements in a commodity purchase database of the user, and if the commodity belongs to a commodity that the user needs to purchase for a plurality of times, that is, the user has purchased the commodity for a plurality of times, and a time node that the user has purchased for a plurality of times coincides with the current time by a certain time range, the electronic device determines that the commodity conforms to the purchasing habits of the user. If the new information to be processed does not completely include three objects of a platform, a brand and a category of a commodity and includes any two objects of the three objects, the electronic equipment searches in a commodity purchase database of a user by taking the two objects as search keywords, integrates purchase dates of the commodities in the searched elements on the same time axis, and judges whether the commodities included in the information are purchased for a plurality of times by the user and whether the purchase time and the current time are overlapped in a certain time range. If the above condition is satisfied, the electronic device determines that the commodity conforms to the purchasing habits of the user, and vice versa.

For example, a product platform (JD), a product brand (cattle identified) and a product category (milk) may be obtained from a short message, but since the user does not browse the record of the product in the near future, if the user's desire to purchase the product is predicted according to the AI model, the purchase will of the product is "no". At this time, it is necessary to determine whether the product conforms to the purchasing habit of the user according to the product purchasing database of the user. For example, the user purchased the product 6 times in the past, belongs to purchasing the product a plurality of times, and purchased the product at the corresponding time in the last year, so it can be determined that the product conforms to the purchasing habit of the user.

For another example, only the brand (hundred orchards) and the category (fruits) of the commodity are acquired according to another short message, and at this time, elements including the commodity having the same brand and the same category as the commodity may be extracted from the commodity purchase database of the user. Through statistics, if the commodity is a related commodity which is purchased by the user for multiple times, and the once purchase time and the current time are overlapped in a certain time range, the electronic equipment can determine that the commodity conforms to the purchase habit of the user.

When it is determined that the object included in the information received by the electronic device conforms to the user' S purchasing habits, the electronic device proceeds to step S205, and transmits the information to the user. When it is determined that the object included in the information received by the electronic device does not conform to the purchasing habit of the user, the step S206 is entered, and the electronic device intercepts the information from the user, so that the information which may be spam is effectively prevented, and the burden and trouble of reading the information by the user are reduced.

In the present disclosure, the order of step S203 and step S204 may be interchanged. That is, it may be determined whether the object included in the information conforms to the user's purchasing habit, and then the user's willingness to purchase the object may be determined.

Further, according to embodiments of the present disclosure, both the first set of elements obtained by the AI model and the second set of objects involved in the user's buying habits may be merged into one set, and upon receiving new information, the objects in the information may be matched with the elements in the merged set, and if so, the information is sent to the user, otherwise the information is intercepted.

When the electronic equipment receives new information needing to be processed, the electronic equipment analyzes the text content of the new information, and according to the user personalized intelligent information processing strategy, if the new information is commodity information which is interesting to the user, the electronic equipment normally sends the new information to the user and displays the new information in the notification information, otherwise, the new information is intercepted, so that trouble is avoided for the user.

Fig. 3 is a block diagram illustrating an apparatus for processing information according to an exemplary embodiment of the present disclosure. The apparatus 300 for processing information according to an embodiment of the present disclosure may be implemented by software or hardware, such as a chip on a chip. According to an embodiment of the present disclosure, a description is given taking an example of processing new information in an electronic device.

Referring to fig. 3, the apparatus 300 may include a receiving module 301, a parsing module 302, and a determining module 303. Each module in the apparatus 300 may be implemented by one or more modules, and names of the corresponding modules may vary according to types of the modules. In various embodiments, some modules in apparatus 300 may be omitted, or additional modules may also be included. Furthermore, modules/elements according to various embodiments of the present disclosure may be combined to form a single entity, and thus the functions of the respective modules/elements may be equivalently performed prior to the combination.

The receiving module 301 may receive information from the outside, and the parsing module 302 may perform content parsing on the received information to obtain an object included in the information. In the present disclosure, the object may be at least one of, for example, a commodity, a purchase platform, a category, and a brand. However, the object is not limited thereto, and other objects may be included.

The determination module 303 may determine whether to intercept information received by the electronic device to the user based on the obtained object.

As an example, the determination module 303 may determine whether the user has a desire to purchase the object according to the obtained object. According to an embodiment of the present disclosure, the determination module 303 may determine whether the user has a desire to purchase the object included in the information based on history data of shopping-related behavior of the user.

According to an embodiment, the shopping-related behavior may include potential shopping behavior and shopping behavior. The potential shopping behavior may include at least one of whether the user launches a shopping class application in the electronic device, whether a link is opened with respect to the item. The electronic device monitors the application or process to determine whether the user has started a shopping-like application or process. The shopping-like application or process may include, but is not limited to, a shopping-like application, a shopping-like applet, a shopping-like application, a link containing an introduction to a commodity, a link containing an evaluation of the commodity, a web link such as a link containing a group purchase of the commodity, a search for a name of the commodity in a browser, and the like. The historical data of shopping-related activities may include data of user browsed goods collected and counted when the user's presence of potential shopping activities is detected. The data of the commodities browsed by the user can comprise the attributes of the commodities and behavior data of the commodities browsed by the user. The behavior data of the user browsing the goods may include at least one of whether the goods are added to the shopping cart, whether the goods are added to the favorites, and whether the goods are purchased. In addition, when collecting data of browsing the goods by the user, the determining module 303 may count browsing times, browsing duration, and browsing date of browsing the goods.

After obtaining the historical data of the shopping-related behavior of the user, the determination module 303 may train an Artificial Intelligence (AI) model using the historical data of the shopping-related behavior of the user, and confirm whether the user has a desire to purchase an object included in the information based on the trained AI model. In addition, the AI model can be trained in other devices or servers, and then the electronic device receives the trained AI model.

In the present disclosure, the AI model may include a general model and a user model. Here, the general model may be trained based on data collected for a plurality of users by a server connected to the electronic device, and the user model may be trained based on data for a single user using the electronic device. The determination module 303 may use feature data of a large number of users (such as purchase platform, category, and brand of goods) and tag data (such as whether to join a shopping cart, whether to collect, and whether to purchase) as training data to train parameters of the generic model. The parameters of the user model may be trained using only the feature data and the label data of a single user as training data.

The determination module 303 may use the generic model until the amount of data (e.g., browsing data) collected by the electronic device satisfies a predetermined value, and the determination module 303 may use the user model or both the user model and the generic model after the amount of data collected by the electronic device satisfies the predetermined value. For example, the determination module 303 may use the generic model at an early stage (e.g., the electronic device has not collected enough browsing data) and use the user model at a later stage (e.g., the electronic device has collected enough browsing data). Alternatively, the determination module 303 may use a generic model at an early stage and an integration model at a later stage.

The determination module 303 may use the AI model described above to obtain a purchase intent database. By using the AI model to determine whether the user has a desire to purchase the browsed goods, the determining module 303 may obtain a purchase desire set/purchase desire database, where each element in the set represents a purchase desire of the current user for a certain goods.

The determining module 303 may set an expiration time D, and when the element including the information of a certain product and the purchase intention already exists in the purchase intention set, and in the expiration time D, the user does not browse the corresponding product in the element again, that is, the date when the user browses the product last time passes the expiration time D from the current time, it may be determined that the user has lost the purchase intention for the product, and at this time, the electronic device may delete the element including the information of the product and the purchase intention from the purchase intention set, such a design better meets the current requirements of the user.

The determination module 303 may update the parameters of the AI model based on data collected by the user when browsing and purchasing items within a predetermined time period.

The determination module 303 may determine whether the object conforms to the user's purchasing habits from the obtained object. The determination module 303 may determine whether the object conforms to the shopping habit of the user by comparing the commodity attributes included in the history data of the shopping-related behavior of the user with the object in the information.

According to embodiments of the present disclosure, the history data of shopping-related activities may include purchase data collected and counted when a user is detected to purchase a commodity. The purchase data may include a purchase time at which the user purchased the goods and attributes of the goods within a predetermined cycle period.

The determination module 303 may form a goods purchase database based on the purchase data of the user. The user's purchasing habits may be determined from a database of commercial purchases.

When it is determined that an object (e.g., an article) included in the information received by the electronic device conforms to a user's purchasing habit or the user has a desire to purchase the article. The determination module may send the information to the user. When determining that the object included in the information received by the electronic device does not conform to the user's purchasing habit or the user does not have a purchase intention, the determining module 303 intercepts the information to the user, thereby effectively preventing the information which may be junk information, and reducing the burden and trouble of the user in reading the information.

As an example, when there is new information that needs to be processed in the mobile phone, the parsing module 302 parses the text content of the new information, and extracts keywords (including commodity information such as a commodity, a commodity platform, a commodity brand, and a commodity category). The determining module 303 matches the information of the goods (platform, brand, category) with elements in the set of buying intentions of the user for the goods, and determines whether the user has buying intentions for the goods. If the new information does not include all the product platforms, product brands and product categories, the determining module 303 performs fuzzy matching and analyzes the searched result, so as to determine whether the user has a purchase intention on the product in the new information. For example, where "Taobao brand A" is mentioned in the new information, but no category is mentioned, the determination module 303 analyzes all purchase intention elements of items that match the "Taobao" platform and the "A" brand in the purchase intention set. If there are N items satisfying brand a of panning and there is a willingness to purchase for (N +1)/2 items, the determination module 303 determines that there is a willingness to purchase for the items to which the new information relates by the user. Otherwise, the determining module 303 precisely matches the commodity information (platform, brand, category) with the purchasing habit of the user on the commodity, and determines whether the user has a purchase intention on the commodity in the current time period. If the new information does not include all the product platforms, product brands and product categories, the determining module 303 performs fuzzy matching and analyzes the searched result, so as to determine whether the user has a purchase intention on the product in the new information. For example, if the new information mentions "Taobao B" category but does not mention brands, then the purchase habit elements of all the goods that match the "Taobao" platform and the "B" category in the set of purchase habits are analyzed. If there are L items satisfying the B category of panning, which are purchased K times in total, and there is a purchase period near the time node, the determination module 303 determines that the user has a desire to purchase the item provided by the new information. If the user is determined to have a desire to purchase the commodity, the determination module 303 determines that new information content is available for the user, and displays the new information to the user normally, otherwise, intercepts the information.

According to the embodiment of the disclosure, the device 300 collects and analyzes behavior data of a user browsing and purchasing commodities on a shopping platform by monitoring whether the user has a potential shopping behavior, obtains whether the user has a potential purchase intention on the commodities by an artificial intelligence model, and extracts a purchase habit of the user by historical purchase behavior data of the user, thereby forming an intelligent information processing strategy based on the user purchase behavior. The method and the device can process the new information received in the electronic equipment of the user, push the information needed by the user to the user, namely normally display the information in the user notification type information, and intercept the garbage information not needed by the user.

In the present disclosure, at least one of the plurality of modules may be implemented by an Artificial Intelligence (AI) model. The functions associated with the AI may be performed by the non-volatile memory, the volatile memory, and the processor.

As an example, the artificial intelligence model may be composed of multiple neural network layers. Each layer has a plurality of weight values, and a layer operation is performed by calculation of a previous layer and operation of the plurality of weight values. Examples of neural networks include, but are not limited to, Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), Bidirectional Recurrent Deep Neural Networks (BRDNNs), generative countermeasure networks (GANs), and deep Q networks.

A learning algorithm may be a method of using a plurality of learning data to train a predetermined target device (e.g., a robot) to cause, allow, or control the target device to make a determination or prediction. Examples of learning algorithms include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

Fig. 4 shows a schematic diagram of a computing device according to an exemplary embodiment of the present disclosure.

Referring to fig. 4, a computing device 400 according to an exemplary embodiment of the present disclosure includes a memory 401 and a processor 402, the memory 401 having stored thereon a computer program that, when executed by the processor 402, implements a method of processing information according to an exemplary embodiment of the present disclosure.

The computing devices in the embodiments of the present disclosure may include, but are not limited to, devices such as mobile phones, notebook computers, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, and the like. The computing device illustrated in fig. 4 is only one example and should not impose any limitations on the functionality or scope of use of embodiments of the present disclosure.

As an example, the computer program, when executed by the processor 402, may implement the steps of: acquiring information; performing content analysis on the information to obtain an object included in the information; and determining whether to intercept the information based on the object.

The computer program, when executed by the processor 402, may further implement the steps of: determining whether the object meets the requirements of a user; if the object meets the user requirement, the information is not intercepted, otherwise, the information is intercepted; determining whether the object meets a user's requirements based on historical data of shopping-related behavior of the user; training an artificial intelligence model using historical data relating to the potential shopping behavior, and determining whether the object meets a user demand based on the trained artificial intelligence model; running the artificial intelligence model by utilizing data of shopping related behaviors in a recent preset time period to obtain a first object set meeting the requirements of a user; matching the object with elements in a first set of objects; determining that the object satisfies the user requirement if the object matches an element in a first set of objects, otherwise determining that the object does not satisfy the user requirement; updating parameters of the artificial intelligence model and the like based on data collected when the user browses and purchases goods within a predetermined period of time; determining a second set of objects involved in a user's purchasing habits based on historical data related to the factual shopping behavior; matching the object with elements in a second set of objects; and if the object is matched with elements in the second object set, determining that the object meets the user requirement, otherwise, determining that the object does not meet the user requirement.

For new information needing to be processed, the computing device 400 obtains a product label (including a purchasing platform, a brand, a category and the like) by analyzing the text content of the new information, if the user is judged to have a purchase intention on the product, the computing device 400 normally sends the information to the user, otherwise, the information is intercepted.

Further, in relation to determining whether the user has a purchase intention for a certain item, the computing device 400 may determine whether the user has a purchase intention for a certain item in consideration of the user's purchase intention for an item predicted by the AI model and the user's purchase habits derived from the user's historical purchase behavior data to determine whether to intercept some information. However, the above examples are merely exemplary, and other user requirements may be considered to determine the user's intention.

Processor 402 may include one or more processors. At this time, the one or more processors may be general-purpose processors such as a Central Processing Unit (CPU), an Application Processor (AP), etc., processors for graphics only (e.g., a Graphics Processor (GPU), a Vision Processor (VPU), and/or an AI-specific processor (e.g., a Neural Processing Unit (NPU)).

The one or more processors control the processing of the input data according to predefined operating rules or AI models stored in the non-volatile memory and the volatile memory. Predefined operating rules or artificial intelligence models may be provided through training or learning. Here, the provision by learning means that a predefined operation rule or AI model having a desired characteristic is formed by applying a learning algorithm to a plurality of learning data. The learning may be performed in the device itself performing the AI according to the embodiment, and/or may be implemented by a separate server/device/system.

The intelligent information processing strategy can normally display part of information which is possibly intercepted by the interception function of the electronic equipment according to the requirements of users. Therefore, different users can use different interception strategies, so that the users can not miss interested information while avoiding troubles caused by a large amount of junk information.

As used herein, the term "module" may include units implemented in hardware, software, or firmware, and may be used interchangeably with other terms (e.g., "logic," "logic block," "portion," or "circuitry"). A module may be a single integrated component adapted to perform one or more functions or a minimal unit or portion of the single integrated component. For example, according to an embodiment, the modules may be implemented in the form of Application Specific Integrated Circuits (ASICs).

Various embodiments set forth herein may be implemented as software including one or more instructions stored in a storage medium readable by a machine (e.g., a mobile device or an electronic device). For example, under control of a processor, the processor of the machine may invoke and execute at least one of the one or more instructions stored in the storage medium with or without the use of one or more other components. This enables the machine to be operable to perform at least one function in accordance with the invoked at least one instruction. The one or more instructions may include code generated by a compiler or code capable of being executed by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Where the term "non-transitory" simply means that the storage medium is a tangible device and does not include a signal (e.g., an electromagnetic wave), the term does not distinguish between data being semi-permanently stored in the storage medium and data being temporarily stored in the storage medium.

According to embodiments, methods according to various embodiments of the present disclosure may be included and provided in a computer program product. The computer program product may be used as a product for conducting a transaction between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium, such as a compact disc read only memory (CD-ROM), or may be distributed (e.g., downloaded or uploaded) online via an application store (e.g., a Play store), or may be distributed (e.g., downloaded or uploaded) directly between two user devices (e.g., smartphones). At least part of the computer program product may be temporarily generated if it is published online, or at least part of the computer program product may be at least temporarily stored in a machine readable storage medium, such as a memory of a manufacturer's server, a server of an application store, or a forwarding server.

According to various embodiments, each of the above components (e.g., modules or programs) may comprise a single entity or multiple entities. According to various embodiments, one or more of the above-described components may be omitted, or one or more other components may be added. Alternatively or additionally, multiple components (e.g., modules or programs) may be integrated into a single component. In such cases, the integrated component may still perform one or more functions of each of the plurality of components in the same or similar manner as the corresponding one of the plurality of components performed the one or more functions prior to integration, according to various embodiments. Operations performed by a module, program, or another component may be performed sequentially, in parallel, repeatedly, or in a heuristic manner, or one or more of the operations may be performed in a different order or omitted, or one or more other operations may be added, in accordance with various embodiments.

While the disclosure has been shown and described with reference to exemplary embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the disclosure as defined by the appended claims and their equivalents.

Claims

1. A method of processing information, the method comprising:

acquiring information;

performing content analysis on the information to obtain an object included in the information; and is provided with

Determining whether to intercept the information based on the object.

2. The method of claim 1, wherein the step of obtaining information comprises:

and acquiring the information from the information intercepted by the third-party application.

3. The method of claim 1, wherein the object comprises at least one of a good, a brand, a category, and a platform.

4. The method of claim 1, wherein determining whether to intercept the information comprises:

determining whether the object meets the requirements of the user;

and if the object meets the user requirement, the information is not intercepted, otherwise, the information is intercepted.

5. The method of claim 4, wherein determining whether the object meets a user's requirements comprises: determining whether the object meets a user's needs based on historical data of shopping-related behavior of the user.

6. The method of claim 5, wherein the shopping-related behavior comprises potential shopping behavior and factual shopping behavior.

7. The method of claim 6, wherein the historical data relating to the potential shopping behavior comprises data collected when the user performs at least one of: launching or running a shopping class application in the electronic device, opening a link to the item, browsing the item, whether the item is added to a shopping cart, and whether the item is added to a favorite.

8. The method of claim 6, wherein the historical data related to the factual shopping behavior comprises data collected by the user when purchasing merchandise within a predetermined period of time.

9. The method of claim 6, wherein determining whether the object meets the user's requirements based on historical data of shopping-related behavior of the user comprises:

training an artificial intelligence model using historical data related to the potential shopping behavior, and determining whether the object meets a user demand based on the trained artificial intelligence model.

10. The method of claim 9, wherein determining whether the object meets the user's requirements based on the trained artificial intelligence model comprises:

running the artificial intelligence model by utilizing data of shopping related behaviors in a recent preset time period to obtain a first object set meeting the requirements of a user;

matching the object with elements in a first set of objects;

if the object matches an element in the first set of objects, determining that the object satisfies the user requirement, otherwise determining that the object does not satisfy the user requirement.

11. The method of claim 9, wherein the artificial intelligence model is trained based on:

generating characteristic data based on the category, the times and the duration of browsing the commodities by the user;

generating tag data based on at least one of whether the item is added to the favorite and whether the item is added to the shopping cart, wherein if the item is not added to the favorite and not added to the shopping cart within a predetermined time, the tag is set not to meet the user requirement, otherwise the tag is set to meet the user requirement;

training the artificial intelligence model using the feature data and the label data.

12. The method of claim 6, wherein determining whether the object meets the user's requirements based on historical data of shopping-related behavior of the user comprises:

determining a second set of objects involved in a user's purchasing habits based on historical data related to the factual shopping behavior;

matching the object with elements in a second set of objects;

and if the object is matched with elements in the second object set, determining that the object meets the user requirement, otherwise, determining that the object does not meet the user requirement.

13. An apparatus for processing information, the apparatus comprising:

a receiving module configured to acquire information;

a parsing module configured to perform content parsing on the information to obtain an object included in the information; and is

A determination module configured to determine whether to intercept the information based on the object.

14. The apparatus of claim 13, wherein the receiving module is configured to:

15. The apparatus of claim 13, wherein the object comprises at least one of a good, a brand, a category, and a platform.

16. The apparatus of claim 13, wherein the determination module is configured to:

determining whether the object meets the requirements of a user;

17. The apparatus of claim 16, wherein the determination module is configured to determine whether the object meets the user's needs based on historical data of shopping-related behavior of the user.

18. The apparatus of claim 17, wherein the shopping-related behavior comprises potential shopping behavior and factual shopping behavior.

19. The apparatus of claim 18, wherein the historical data related to the potential shopping behavior comprises data collected while the user performs at least one of: launching or running a shopping class application in the electronic device, opening a link to the item, browsing the item, whether the item is added to a shopping cart, and whether the item is added to a favorite.

20. The apparatus of claim 18, wherein the historical data relating to the factual shopping behavior comprises data collected by a user when purchasing goods within a predetermined period of time.

21. The apparatus of claim 18, wherein the determination module is configured to:

22. The apparatus of claim 21, wherein the determination module is configured to:

matching the object with elements in a first set of objects;

23. The apparatus of claim 21, wherein the artificial intelligence model is trained based on:

generating characteristic data based on the category, the times and the duration of the commodity browsed by the user;

generating tag data based on at least one of whether the item is added to the favorite and whether the item is added to the shopping cart, wherein if the item is not added to the favorite and not added to the shopping cart within a predetermined time, the tag is set not to satisfy the user requirement, otherwise the tag is set to satisfy the user requirement;

24. The apparatus of claim 18, wherein the determination module is configured to:

matching the object with elements in a second set of objects;

25. An electronic device, comprising:

a memory for storing a program; and

one or more processors for performing one or more of the above-described operations,

wherein the one or more processors perform the method of any one of claims 1 to 12 when the program is run.

26. A computer-readable recording medium in which a program is stored, characterized in that the program comprises instructions for executing the method according to any one of claims 1 to 12.