WO2022145836A1

WO2022145836A1 - Method and apparatus for processing information

Info

Publication number: WO2022145836A1
Application number: PCT/KR2021/019312
Authority: WO
Inventors: Yan Wang; Yiwen Yang
Original assignee: Samsung Electronics Co., Ltd.
Priority date: 2020-12-31
Filing date: 2021-12-17
Publication date: 2022-07-07
Also published as: CN114697889A

Abstract

The present disclosure provides a method and apparatus for processing information. The method for processing information comprises acquiring information received from external device, analyzing contents of the acquired information to obtain an object included in the information, determine whether the object meets a user requirement based on historical data of a shopping related behavior of a user, providing the information to the user if the object meets the user requirement otherwise, intercepting the information. According to the present disclosure, useless information may be effectively intercepted for a different user, and the required information may be sent to the user.

Description

METHOD AND APPARATUS FOR PROCESSING INFORMATION

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

　A short message service is a way to send and receive short text information based on the mobile communication network. A message is received, transferred and sent by a short message service center. This service is widely applied to all mobile communication networks and https://cn.bing.com/dict/search?q=is&FORM=BDVSP6&mkt=zh-cn become one of the most frequently applied services by mobile phone users. Moreover, many businesses are also increasingly favoring this convenient and low-cost advertising channel.

　As there is now more and more notification information, a mobile phone user receives a large amount of information every day. For these information, the user himself needs to filter and distinguish which information is valuable to the user. The information that is of no value to the user will bring unnecessary burden and distress to the user.

　According to the conventional information interception strategy applied to a mobile phone, the information received by the mobile phone is intercepted by establishing a database of blacklist (“blacklist database”). With the continuous update of the blacklist database, the mobile phone will intercept more information that may be junk information. However, the information interception strategy at the present stage intercepts information blindly, and cannot vary from person to person and time to time, and thus, the information required by the user may be missed.

　In an aspect, the present disclosure provides a method for processing information. The method may comprise acquiring information; analyzing contents of the acquired information to obtain an object included in the information and determining whether to intercept the acquired information based on the object.

　By combining the accompanying drawings, these and/or other aspects and advantages of the present disclosure will become apparent and more readily understood from the following description of the embodiments. In the accompanying drawings:

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

　Fig. 2 is a flowchart illustrating a method for 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 apparatus according to an exemplary embodiment of the present disclosure.

　Fig. 5 is a distribution diagram of a purchase date of a certain commodity in a cycle period, according to an exemplary embodiment of the present disclosure.

　Exemplary embodiments of the present disclosure provide a method and apparatus for processing information to solve at least the above technical problems and other technical problems are not mentioned above and provide the following beneficial effects.

　In an aspect, the present disclosure provides a method for processing information. The method may comprise acquiring information received from external device, analyzing contents of the acquired information to obtain an object included in the information, determining whether the object meets a user requirement based on historical data of a shopping related behavior of a user and providing the information to the user if the object meets the user requirement otherwise, intercepting the information.

　Alternatively, the acquiring may comprise acquiring the information from information intercepted by a third party application.

　Alternatively, the object may comprise at least one of a commodity, a brand, a category, or a platform.

　Alternatively, the determining whether to intercept the acquired information may comprise determining whether the object meets a user requirement; and not intercepting the information if the object meets the user requirement; otherwise, intercepting the information.

　Alternatively, the determining whether the object meets a user requirement may comprise determining whether the object meets the user requirement based on historical data of a shopping related behavior of a user.

　Alternatively, the shopping related behavior may comprise a potential shopping behavior and a factual shopping behavior.

　Alternatively, historical data related to the potential shopping behavior may comprise data collected when the user performs at least one of starting or running a shopping application in an electronic device, opening a link concerning a commodity, browsing the commodity, whether the commodity is added to a shopping cart, or whether the commodity is added to a favorites list.

　Alternatively, historical data related to the factual shopping behavior may comprise data collected when the user purchases the commodity within a predetermined time period.

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

　Alternatively, the determining whether the object meets the user requirement based on the trained artificial intelligence model may comprise: running the artificial intelligence model using data of a recent shopping related behavior within a preset time period, to obtain a first object set satisfying the user requirement; determining whether the object is matched with an element in the first object set; and determining that the object satisfies the user requirement, if the object matches the element in the first object set; otherwise, determining that the object does not satisfy the user requirement.

　Alternatively, the artificial intelligence model may be trained by: generating characteristic data based on a category, a number of times and a time length when the user browses the commodity; generating tag data based on at least one of whether the commodity is added to the favorites list or whether the commodity is added to the shopping cart, wherein if the commodity is not added to the favorites list and not added to the shopping cart within predetermined time, a tag is set to not satisfying the user requirement; otherwise, the tag is set to satisfying the user requirement; and training the artificial intelligence model using the characteristic data and the tag data.

　Alternatively, the determining whether the object meets the user requirement based on historical data of a shopping related behavior of a user may comprise: determining a second object set in relation to a purchase habit of the user, based on the historical data related to the factual shopping behavior; determining whether the object is matched with an element in the second object set; and determining that the object satisfies the user requirement, if the object matches the element in the second object set; otherwise, determining that the object does not satisfy the user requirement.

　In another aspect, the present disclosure provides an apparatus for processing information. The apparatus may comprise at least one memory and at least one processor coupled to the at least one memory and configured to: acquire information received from external device, analyze contents of the acquired information to obtain an object included in the information, determine whether the object meets a user requirement based on historical data of a shopping related behavior of a user and provide the information to the user if the object meets the user requirement; otherwise, intercept the information.

　Alternatively, the receiving module may be configured to acquire the information from information intercepted by a third party application.

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

　Alternatively, the determining module may be configured to determine whether the object meets the user requirement based on historical data of a shopping related behavior of a user.

　Alternatively, the determining module may be configured to train an artificial intelligence model using the historical data related to the potential shopping behavior, and determine whether the object meets the user requirement based on the trained artificial intelligence model.

　Alternatively, the determining module may be configured to: run the artificial intelligence model using data of a recent shopping related behavior within a preset time period, to obtain a first object set satisfying the user requirement; determine whether the object is matched with an element in the first object set; and determine that the object satisfies the user requirement, if the object matches the element in the first object set; otherwise, determine that the object does not satisfy the user requirement.

　Alternatively, the determining module may be configured to determine a second object set in relation to a purchase habit of the user, based on the historical data related to the factual shopping behavior, determine whether the object is matched with an element in the second object set and determine that the object satisfies the user requirement, if the object matches the element in the second object set otherwise, determine that the object does not satisfy the user requirement.

　According to an exemplary embodiment, the present disclosure provides a computer readable storage medium storing a computer program. The computer program, when executed by a processor, performs the method for processing information as described above.

　According to another exemplary embodiment, the present disclosure provides a computer. The computer comprises a readable medium storing a computer program, and a processor. The computer program, when run by the processor, performs the method for processing information as described above.

　According to another exemplary embodiment, the present disclosure provides a computer program product. An instructions in the computer program product is run by at least one processor in an electronic apparatus, to perform the method for processing information as described above.

　According to the apparatus and method described above, useless information can be effectively intercepted for a different user and the required information is sent to the user, which not only reduces the burden and distress of the user in reading information, but also satisfies the requirement of the user.

　In addition, other aspects and/or advantages of the overall concept of the present disclosure will be partially explained in the following description, and some of the other aspects and/or advantages will be apparent through the description or may be learned through the implementation of the overall concept of the present disclosure.

　The following description is provided with reference to the accompanying drawings, to facilitate a thorough understanding of embodiments of the present disclosure that are defined by the claims and equivalents thereof. Various specific details are included to facilitate understanding, but these details are regarded as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, for clarity and conciseness, descriptions for well-known functions and structures are omitted in the following description.

　It should be noted that the terms “first,” “second” and the like in the specification and claims of the present disclosure and the accompanying drawings are used to distinguish similar objects, and not necessarily used to describe a specific order or an order of priority. It should be understood that the data used in this way may be interchanged in an appropriate situation, such that the embodiments of the present disclosure that are described herein can be implemented in an order other than that illustrated or described herein. The implementations described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Rather, the implementations are merely examples of the apparatus and method consistent with some aspects of the present disclosure and claimed in the claims.

　According to a current information interception strategy, junk information may be intercepted, but the definition of a junk message is not exactly the same for each real and specific user. For example, in some specific periods (e.g., a shopping festival such as “Double 11” and “6·18”), a user may purchase a commodity that the user often browses but is not willing to purchase. During the shopping festival, there is a large large margin of preference. Businesses generally offer a lot of preferential information, and send a coupon use method to the user for reference. At this time, the user may prefer to be able to obtain these relevant preferential information and purchase a long-desired commodity at a more favorable price. At this time, the user does not consider the promotion information as junk information any more, but considers the promotion information as a notification of commodity preferential information, but the information is still intercepted as junk information. Therefore, the definition of the junk information should vary from person to person and time to time, and the blind interception cannot satisfy the personalized requirement of the user.

　However, according to the present disclosure, a personalized information interception can be performed for requirements of different users in different periods. That is, the requirements of the different users for information are effectively acquired. Accordingly, the information is effectively filtered and intercepted, to customize a personalized information interception strategy for a different user to realize that the user acquires required information and the useless junk information is intercepted.

　Reference will now be made in detail to the exemplary embodiments of the present disclosure, and examples of the embodiments are illustrated in the accompanying drawings. Here, like reference numerals denote like parts throughout. Hereinafter, according to various embodiments of the present disclosure, the apparatus and method of the present disclosure will be described with reference to the accompanying drawings.

　Fig. 1 is a flowchart illustrating a method for processing information according to an exemplary embodiment of the present disclosure. According to an embodiment of the present disclosure, a junk information interception function of the present disclosure may be independently implemented by a third party application or a manufacturer. That is, the method for processing information in the present disclosure is added to an interception rule, and thus, a determination is completed when an electronic device (e.g., a mobile phone) receives information from external device. Alternatively, the electronic device may reacquire the information intercepted/filtered out by the third party application or the manufacturer, that is, acquire the previously intercepted information from the information intercepted by the third party application. Then, the junk information interception function of the present disclosure is performed in the electronic device.

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

　Referring to Fig. 1, in step S101, information received from external device is acquired. For example, the electronic device may externally receive a large amount of notification information such as information of a preferential activity of a certain commodity. Alternatively, the electronic device obtains information to be processed from the information filtered out by the third party application.

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

　As an example, when receiving a piece of information on a commodity promotion activity, the electronic device may analyze the text contents of the information to obtain the object in the information, for example, at least one of: which kind of commodity, which purchase platform, which brand or which category. The analysis method may include, but not limited to, a semantic analysis method.

　In step S103, whether the object meets a user requirement based on historical data of a shopping related behavior of a user is determined.

　According to an embodiment of the present disclosure, the electronic device may determine whether the object in the information meets a user requirement. Whether the object in the information meets the user requirement may be determined based on historical data of a shopping related behavior of the user.

　The user requirement may include at least one of a purchase intention of the user or a purchase habit of the user. However, the present disclosure is not limited thereto.

　In step S104, the electronic device may provide the information to the user if the object meets the user requirement otherwise, intercept the information. whether to intercept the received information for a user is determined based on the obtained object. 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 for the user, that is, the information is intercepted.

　For example, the information sent by the electronic device to the user may contain related promotional and preferential information of a commodity for which the user has the purchase intention. A method of how to intercept the information received by the electronic device for the user will be described below in detail with reference to Fig. 2.

　Referring to Fig. 2, in step S201, an electronic device determines whether new information to be processed is present. For example, the electronic device proceeds to perform step S202 after receiving the new information, otherwise, the electronic device waits to receive the new information. As another example, the electronic device acquires information to be processed from information intercepted by a third party application, and proceeds to perform step S202, otherwise, the electronic device waits to receive the new information.

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

　In step S203, whether the object satisfies a purchase intention of a user is determined. According to an embodiment of the present disclosure, the electronic device may determine whether the object included in the information satisfies the user intention based on historical data of a shopping related behavior of the user. The shopping related behavior may include a potential shopping behavior and a factual shopping behavior. For example, an artificial intelligence model is trained using historical data related to the potential shopping behavior, and whether the object in the information satisfies the purchase intention of the user is determined based on the trained artificial intelligence model.

　As an example, the historical data related to the potential shopping behavior may include data collected when the user performs at least one of: starting or running a shopping application in the electronic device, opening a link concerning a commodity, browsing the commodity, whether the commodity is added to a shopping cart, or whether the commodity is added to a favorites list. By monitoring application programs or progresses of the electronic device, the electronic device determines whether the user starts a shopping application program or progress. The shopping application program or progress may include, but not limited to, a shopping application, a shopping applet, a shopping quick application, opening of a link containing a commodity introduction, opening of a link containing a commodity evaluation, opening of a webpage link containing a commodity group purchase link, etc., searching for a commodity name in a browser, and the like. For example, when the user starts the shopping application, the electronic device may confirm that the user has a potential shopping related behavior.

　According to an embodiment of the present disclosure, the historical data of the shopping related behavior may include data when the user browses a commodity (hereinafter, which may be referred to as browsing data), the data being collected and become statistical when it is detected that the user has the potential shopping behavior. When it is monitored that the user has the above potential shopping related behavior, the electronic device begins to collect relevant data when the user browses or purchases the commodity. If the electronic device does not monitor that the user has the potential shopping related behavior, the electronic device continues the monitoring.

　As an example, when it is monitored that the user starts the shopping application, the electronic device begins to collect behavior data when the user browses/purchases the commodity, the behavior data including, but not limited to, starting a backend aid tool, and performing a control analysis and a content capture on a page currently displayed by the shopping application, and capturing content.

　Data when the user browses the commodity may include an attribute of the commodity and the behavior data when the user browses the commodity. The behavior data when the user browses the commodity may include at least one of whether the commodity is added to the shopping cart, whether the commodity is added to the favorites list, or whether the commodity is purchased.

　As an example, when it is monitored that the currently displayed page is a commodity detail page, the electronic device begins to acquire HTML commodity description information contained in the page, analyze text contents of the information to acquire an attribute of a commodity viewed by the user such as a brand and a category, and monitor whether the user performs operations of adding the commodity to the shopping cart, adding the commodity to the favorites list, and purchasing the commodity.

　In addition, when the data when the user browses the commodity is collected, a number of times that the commodity is browsed, a browsing time length, and a browsing date may become statistical. For example, when the user browses the commodity, the electronic device performs timing to obtain the time length that the user spends to browse the commodity, increases the number of times that the user browses the commodity by 1 at the same time, and records the browsing date at which the commodity is browsed.

　As an example, cycle time T may be set, for example, the cycle time T is set to 1 day. Each piece of browsing data records only a number of times that the user browses a corresponding commodity within the cycle time T, a cumulative browsing time length, a browsing date, and a related operation (e.g., whether the commodity is added to the shopping cart, whether the commodity is added to the favorites list, and whether the commodity is purchased). If the user has the behavior of adding the corresponding commodity to the shopping cart within the cycle time T, “whether the commodity is added to the shopping cart” in the browsing data related to the corresponding commodity is marked as “Yes.” Conversely, “whether the commodity is added to the shopping cart” is marked as “No.” If the user has the behavior of adding the corresponding commodity to the favorites list within the cycle time T, “whether the commodity is added to the favorites list” in the browsing data related to the corresponding commodity is marked as “Yes.” Conversely, “whether the commodity is added to the favorites list” is marked as “No.” If the user has the behavior of purchasing the corresponding commodity within the cycle time T, “whether the commodity is purchased” in the browsing data related to the corresponding commodity is marked as “Yes.” Conversely, “whether the commodity is purchased” is marked as “No.”

　An identifier of the commodity may be determined by the attribute of the commodity. If the brands, the categories and the purchase platforms of the two commodities are the same, it is considered that the two commodities are the same commodity. In the situation of the same commodity, the browsing behavior of the user within the cycle time T may correspond to only one piece of browsing data.

　According to an embodiment of the present disclosure, after the historical data of the shopping related behavior of the user is obtained, the artificial intelligence (AI) model may be trained using the historical data of the shopping related behavior of the user, and whether the user has the purchase intention for the object included in the information may be determined 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 in the present disclosure may be, but not limited to, a binary classification model.

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

　The general model may be used before an amount of data (e.g., the browsing data) collected by the electronic device satisfies a predetermined value. The user model or both the user model and the general model may be used after the amount of the data collected by the electronic device satisfies the predetermined value. For example, the general model may be applied in an earlier stage to solve a “cold start problem.” This is because that the data of the single user collected by the electronic device in the earlier stage is very few, the AI model trained using a small amount of data cannot accurately determine the purchase intention of the user, and the general model is the model trained by collecting the data of the large number of users and meets the usage habits of most people. Therefore, the general model may be used in the earlier stage. In the middle and later stage, the user model may be trained using personal data to obtain a more precise AI model.

　Alternatively, the general model may be used in the earlier stage (e.g., the electronic device does not collect enough 100 pieces of browsing data), and the user model may be used in the middle and later stage (e.g., the electronic device collects enough 100 pieces of browsing data).

　Alternatively, the general model may be used in the earlier stage, and an integrated model may be used in the middle and later stage. That is, the general model and the user model are used in combination to determine whether the user has the purchase intention for the commodity included in the information. In the situation where the integrated model is used, 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 exemplary only, and the present disclosure is not limited thereto.

　The general model may use a model suitable for processing a large scale of data, for example, a neural network, and a gradient boosting decision tree (GBDT). The user model may use a model suitable for processing a medium and small scale of data, for example, a support vector machine (SVM). However, the above example models are exemplary only, and the present disclosure is not limited thereto.

　According to an embodiment of the present disclosure, the artificial intelligence model is trained by: generating characteristic data based on a category, a number of times and a time length when the user browses the commodity, and generating tag data based on at least one of whether the commodity is added to the favorites list or whether the commodity is added to the shopping cart. Here, if the commodity is not added to the favorites list and not added to the shopping cart within predetermined time, a tag is set to not satisfying the user requirement, otherwise, the tag is set to satisfying the user requirement. Then, the artificial intelligence model is trained using the characteristic data and the tag data.

　As an example, characteristic data (e.g., a purchase platform, a category and a brand of a commodity, a category of a browsed commodity, a number of browsing times and a browsing time length) and tag data (e.g., whether a commodity is added to a shopping cart, whether a commodity is added to a favorites list, and whether a commodity is purchased) of a large number of users may be used as training data to train a parameter of the general model. Characteristic data and tag data of a single user may only be used as training data to train the parameter of the user model.

　The general model may be trained at a server side connected with the electronic device. The user model may be trained in the electronic device (e.g., a mobile phone). For example, the user model may be set to be trained when a mobile terminal is charged, which avoids the consumption of much power of the mobile terminal due to the training.

　The general model may be downloaded to the electronic device for use. When the general model is updated, the electronic device may download a new general model from the server side to implement the update of the general model. Alternatively, the general model may also be directly used at the server side to predict the purchase intention of the user, and then the electronic device completes the task of predicting the purchase intention of the user by accessing a server interface.

　The user model may be trained and used in the electronic device. In addition, the information collected in the electronic device may be sent to the server, for the server to implement the training for the user model.

　According to another embodiment, when the received information includes the brand, the category, and the purchase platform of the commodity, the electronic device may retrieve an element matching the attribute (object) of the commodity in a first object set (also referred to as a purchase intention database), and utilize the element to determine the purchase intention of the user for the commodity. Specifically, whether the object in the information is matched with an element in the first object set is determined. If the object matches the element in the first object set, it is determined that the object satisfies the purchase intention of the user, otherwise, it is determined that the object does not satisfy the purchase intention of the user.

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

　As an example, the first object set (purchase intention database) may be obtained using the above AI model. Specifically, the above artificial intelligence model is run using data of a recent shopping related behavior within a preset time period, to obtain the purchase intention database satisfying the purchase intention of the user. By using the AI model to determine whether the user has the purchase intention for the browsed commodity, a purchase intention set/purchase intention database may be obtained. Each element in the set respectively represents a purchase intention of a current user for a certain commodity. For example, the each element may include the purchase platform, the brand and the category of the commodity and the purchase intention of the user for the commodity.

　In the present disclosure, the AI model may only predict a commodity for which the purchase intention of the user is not clear. The commodity for which the purchase intention of the user is not clear refers to that the determinations on “whether the commodity is added to the shopping cart,” “whether the commodity is added to the favorites list” and “whether the commodity is purchased” in the browsing data of the corresponding commodity are “No.” That is, when the user browses a certain commodity, a behavior such as adding the commodity to the shopping cart, adding the commodity to the favorites list or purchasing the commodity does not occur, the purchase intention of the user for the commodity cannot be determined. For example, if the value of “whether the commodity is purchased” in the browsing data of the certain commodity is “Yes,” the prediction on the purchase intention for the commodity is not performed. If at least one of the values of “whether the commodity is added to the shopping cart,” and “whether the commodity is added to the favorites list” in the browsing data of the certain commodity is “Yes,” it is determined that the user has a purchase intention for the commodity. The electronic device may use the commodity as an element in a purchase intention set and add the commodity to the purchase intention set.

　Alternatively, expiration time D may be set. In the purchase intention set, an element containing information of a certain commodity and a purchase intention has the expiration time D, and within the expiration time D, the user does not browse the corresponding commodity in the element any more. That is, the expiration time D is between the date at which the user browses the commodity for the last time and the current time, and thus it may be determined that the user has lost the purchase intention for the commodity. At this time, the electronic device may remove the element containing the information of the commodity and the purchase intention from the purchase intention set, and such a design is more in line with the current requirement of the user.

　As an example, when the purchase platform (e.g., Dangdang), the brand (e.g., lily) and the category (e.g., clothing) of a corresponding commodity are extracted according to the received new information, the electronic device may search the element matching the attribute of the corresponding commodity in the purchase intention set. If an element related to the commodity is present in the purchase intention set, the new information is processed according to the value of the purchase intention of the commodity in the purchase intention set. For example, if the purchase intention of the user for the commodity in the purchase intention set is “Yes,” step S205 is performed, and the new information is normally provided to the user. If the purchase intention of the user for the commodity in the purchase intention set is “No,” a determination needs to be performed according to a purchase habit of the user that will be described below. If the commodity does not exist in the purchase intention set, the electronic device determines that the purchase intention of the user for the commodity is “No,” and thus may intercept the information for the user.

　When the new information required to be processed does not include three attributes (a commodity platform, a commodity brand, and a commodity category), for example, includes only one or two attributes in the three attributes. The one or two attributes may be used as a search keyword to search an element of a commodity containing the two attributes of the corresponding commodity from the purchase intention set predicted using the AI model, and a determination is performed on the search result. For example, it is assumed that there are N commodities meeting the two commodity attributes at the same time in the purchase intention set. If the purchase intentions for (N+1)/2 commodities are “Yes,” the purchase intention of the user for the commodity contained in the information may be determined as “Yes,” step S205 is performed, and the electronic device may provide the information to the user normally; otherwise, the purchase intention of the user for the commodity contained in the information may be determined as “No,” and a further determination is required to be performed based on the purchase habit of the user that will be described below.

　For example, the purchase platform (LIFEASE) and the category (mask) of the corresponding commodity are extracted according to the information to be processed, but the brand of the commodity is not included in the information. At this time, elements including all 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 value corresponding to each retrieved set element may be analyzed. It is assumed that it is retrieved that 25 commodities in the purchase intention set have the same platform and the same category as the commodity corresponding to the information, and the purchase intentions for 18 commodities are “Yes,” where 18>(25+1)/2. At this time, the electronic device may determine that the purchase intention of the user for the commodity contained in the information is “Yes,” step S205 is performed, and the received information may be normally provided to the user; otherwise, step S204 is performed, and whether to send the information to the user may be determined according to the habit of the user that will be described below.

　According to another embodiment of the present disclosure, the parameter of the AI model may be updated based on data collected when the user browses and purchases the commodity within a predetermined time period. When the potential shopping behavior of the user occurs, the electronic device may periodically collect the data when the user browses and purchases the commodity, and periodically train the AI model using the collected browsing data or the purchase data as training data, such that the AI model is more in line with the current shopping intention and habit of the user to more accurately perform the prediction.

　If the object included in the information satisfies the shopping intention of the user, step S205 is performed, and the information received by the electronic device is provided to the user. If the object included in the information does not satisfy the shopping intention of the user, step S204 is performed.

　In step S204, whether the object in the information meets a purchase habit of the user is determined. The electronic device may determine whether the object in the information meets a shopping habit of the user by comparing the commodity attribute included in the historical data of the shopping related behavior of the user with the object in the information. Specifically, a second object set (hereinafter, which may be referred to as a commodity purchase database) in relation to the purchase habit of the user may be determined based on the historical data related to the factual shopping behavior. Whether the object in the information is matched with an element in the second object set is determined. If the object matches the element in the second object set, it is determined that the object meets the purchase habit of the user; otherwise, it is determined that the object does not meet the purchase habit of the user.

　According to an embodiment of the present disclosure, the historical data of the shopping related behavior may include purchase data collected and become statistical when it is detected that the user purchases the commodity. For example, the historical data related to the factual shopping behavior includes data collected when the user purchases the commodity within the predetermined time period. For example, the electronic device may analyze whether there is a control such as “Submit Order” or “Buy Now” in a page currently browsed by the user, through an aid tool. When it is monitored that the user clicks on the control such as “Buy Now,” it is considered that the user is performing the behavior of purchasing a commodity. At this point, the electronic device may acquire the HTML commodity description information contained in the page, analyze text contents of the information to obtain the brand, the category, the purchase platform and the purchase time of the commodity, and mark “whether the commodity is purchased” in the purchase data of the commodity as “Yes.” If “whether the commodity is purchased” in the purchase data corresponding to the commodity is already marked as “Yes,” the electronic device may only update the purchase date in the purchase data of the commodity, and add the latest purchase date to the purchase date in the purchase data of the commodity.

　According to an embodiment of the present disclosure, the purchase data may include purchase time at which the user purchases the commodity within a predetermined cycle period and an attribute of the commodity. For example, each piece of purchase data may include commodity information and data of the behavior of purchasing the commodity, the commodity information including the platform of the commodity, the category to which the commodity belongs and the brand of the commodity, and the data of the behavior of purchasing the commodity including a marked value of “whether to purchase the commodity” and a set of dates at which the commodity is purchased.

　A cycle period M may be preset, for example, the cycle period M is set to one year, that is, the period of the purchase data of the user is one year. The purchase date at which the user purchases the corresponding commodity in the cycle period M is marked on the time axis. If the user purchases the same commodity a plurality of times, the purchase dates of the commodity are cyclically marked on the time axis. For example, when the purchase date of the user is recorded, the month and the day may only be recorded, and the year is not recorded.

　For example, it is assumed that there is a commodity P, the brand of the commodity P is A, the category of the commodity P is B, the purchase platform of the commodity P is JD, and the data of the purchase behavior of the user for the commodity is shown in Fig. 5. In Fig. 5, when the purchase date of the commodity is projected on the time coordinate axis, it can be visually seen that the distribution of the dates at which the commodity is purchased in the cycle period of one year, thereby determining that the commodity belongs to the commodity required to be purchased a plurality of times, which indicates that the commodity may be a consumable commodity. In addition, the time at which the user purchases the commodity is generally concentrated in March, June and November. The above example is exemplary only, and the present disclosure is not limited thereto.

　According to an embodiment of the present disclosure, the commodity purchase database may be formed based on the purchase data of the user. In the present disclosure, the purchase habit of the user may be determined from the commodity purchase database.

　As an example, purchase data of all commodities having the same category and the same purchase platform in the purchase data may be selected, and the purchase dates of the selected corresponding commodities are all projected on a time axis of which the time length is a predetermined cycle period (e.g., one year), thereby determining which time periods the user may purchase the commodity of the corresponding category on the corresponding purchase platform.

　Alternatively, purchase data of all commodities having 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 of which the time length is a predetermined cycle period (e.g., one year), thereby determining which time periods the user may purchase the commodity of the corresponding category on the corresponding purchase platform.

　Alternatively, purchase data of all commodities having 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 of which the time length is a predetermined cycle period (e.g., one year), thereby determining which time periods the user may purchase the commodity of the corresponding category on the corresponding purchase platform.

　When the received information includes the brand, the category, and the purchase platform of the corresponding commodity, the electronic device retrieves an element matching the object in the information in the commodity purchase database, and determines whether the content of the commodity meets the shopping habit of the user by using the element.

　When the received information includes any two objects in the brand, the category, and the purchase platform of the corresponding commodity, the electronic device searches an element matching the any two objects in the commodity purchase database, and determines whether the commodity is the commodity that the user needs to purchase a plurality of times and whether the current time is near the purchase time at which the user ever purchases the corresponding commodity by using the element, to determine whether the contents of the received information meets the shopping habit of the user.

　As an example, if the new information to be processed includes three objects: the platform, the brand and the category of the commodity, the electronic device may directly perform matching on an element in the commodity purchase database of the user. If the commodity belongs to the commodity that the user needs to purchase a plurality of times, that is, the user purchases the commodity a plurality of times, and the time nodes at which the user ever purchases the commodity coincide with the current time by a certain time range, the electronic device determines that the commodity meets the purchase habit of the user. If the new information to be processed does not include all of the three objects (the platform, the brand and the category of the commodity), but includes any two of the three objects, the electronic device performs a search in the commodity purchase database of the user by using the two objects as search keywords, and integrates the purchase date of the commodity in the searched element on the same time axis to determine whether the commodity contained in the information is the commodity that the user purchases a plurality of times and whether the purchase time coincides with the current time by a certain time range. If the above condition is satisfied, the electronic device determines that the commodity meets the purchase habit of the user, and vice versa.

　As an example, the commodity platform (JD), the commodity brand (Adopt a Cow), and the commodity category (milk) may be acquired according to a short message. However, there is no record of the user browsing the commodity recently, and thus, if the purchase intention of the user for the commodity is predicted according to the AI model, the purchase intention for the commodity is “No.” At this time, it is required to determine whether the commodity meets the purchase habit of the user according to the commodity purchase database of the user. For example, the user purchased the commodity six times in the past, the commodity belonging to the commodity that the user purchases a plurality of times, and the user also purchased the commodity at the corresponding time last year. Thus, it may be determined that the commodity meets the purchase habit of the user.

　As another example, only the commodity brand (Pagoda) and the commodity category (Fruit) are acquired according to another short message. At this time, an element including a commodity having the same brand and the same category as this commodity may be extracted from the commodity purchase database of the user. Statistically, if the commodity is a related commodity that the user purchases a plurality of times, and the previous purchase time coincides with the current time by a certain time range, the electronic device may determine that the commodity meets the purchase habit of the user.

　When it is determined that the object included in the information received by the electronic device meets the purchase habit of the user, step S205 is performed, and the electronic device provides the information to the user. When it is determined that the object included in the information received by the electronic device does not meet the purchase habit of the user, step S206 is performed, and the electronic device intercepts the information for the user, which effectively prevents the information that may be junk information, thereby reducing the burden and distress of the user in reading information.

　In the present disclosure, the orders of step S203 and step S204 may be interchanged. That is, it is possible to first determined whether the object included in the information meets the purchase habit of the user, and then determine the purchase intention of the user for the object.

　In addition, according to an embodiment of the present disclosure, a first element set obtained by the AI model and the second object set in relation to the purchase habit of the user may be combined into one set. When the new information is received, the object in the information may be matched with an element in the combined set. If the object is matched with the element, the information is sent to the user, otherwise, the information is intercepted.

　When receiving the new information required to be processed, the electronic device analyzes the text contents of the new information. According to the personalized intelligent information processing strategy of the user, if the new information is the commodity information that the user is interested in, the electronic device sends the new information to the user normally, and displays the new information in the notification information, otherwise, the electronic device intercepts the new information, to avoid the distress to 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 the embodiment of the present disclosure may be implemented by software or hardware (e.g., a chip-on-chip). According to the embodiment of the present disclosure, an example of processing new information in an electronic device is described.

　Referring to Fig. 3, the apparatus 300 may include a receiving module 301, an analyzing module 302 and a determining module 303. Each module in the apparatus 300 may be implemented by one or more modules, and the name of the corresponding module may vary depending on the type of the module. In various embodiments, some modules in the apparatus 300 may be omitted, or additional modules may 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 before the combination may be performed equivalently.

　The receiving module 301 may externally receive information, and the analyzing module 302 may analyze contents of the received information to obtain an object included in the information. In the present disclosure, the object may be, for example, at least one of a commodity, a purchase platform, a category, or a brand. However, the object is not limited thereto, and an other object may also be included.

　The determining module 303 may determine whether to intercept the acquired information, received by the electronic device, for a user based on the obtained object.

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

　According to an embodiment, the shopping related behavior may include a potential shopping behavior and a shopping behavior. The potential shopping behavior may include at least one of whether the user starts a shopping application in the electronic device or whether the user opens a link concerning a commodity. By monitoring application programs or progresses of the electronic device, the electronic device determines whether the user starts a shopping application program or progress. The shopping application program or progress may include, but not limited to, a shopping application, a shopping applet, a shopping quick application, opening of a link containing a commodity introduction, opening of a link containing a commodity evaluation, opening of a webpage link containing a commodity group purchase link, etc., searching for a commodity name in a browser, and the like. The historical data of the shopping related behavior may include data when the user browses a commodity, the data being collected and become statistical when it is detected that the user has the potential shopping behavior. The data when the user browses the commodity may include an attribute of the commodity and the behavior data when the user browses the commodity. The behavior data when the user browses the commodity may include at least one of whether the commodity is added to a shopping cart, whether the commodity is added to a favorites list, or whether the commodity is purchased. In addition, when collecting the data when the user browses the commodity, the determining module 303 may become statistical a number of times that the commodity is browsed, a browsing time length, and a browsing date.

　After obtaining the historical data of the shopping related behavior of the user, the determining module 303 may train an artificial intelligence (AI) model using the historical data of the shopping related behavior of the user, and determine whether the user has the purchase intention for the object included in the information based on the trained AI model. In addition, the AI model may be trained in an other device or a server, 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 determining module 303 may use characteristic data (e.g., a purchase platform, a category and a brand of a commodity) and tag data (e.g., whether a commodity is added to a shopping cart, whether a commodity is added to a favorites list, and whether a commodity is purchased) of a large number of users as training data to train a parameter of the general model. Characteristic data and tag data of a single user may only be used as training data to train the parameter of the user model.

　The determining module 303 may use the general model before an amount of data (e.g., the browsing data) collected by the electronic device satisfies a predetermined value. The determining module 303 may use the user model or both the user model and the general model after the amount of the data collected by the electronic device satisfies the predetermined value. For example, the determining module 303 may use the general model in an earlier stage (e.g., the electronic device does not collect enough 100 pieces of browsing data), and use the user model in the middle and later stage (e.g., the electronic device collects enough 100 pieces of browsing data). Alternatively, the determining module 303 may use the general model in the earlier stage, and an integrated model in the middle and later stage.

　The determining module 303 may use the above AI model to obtain a purchase intention database. By using the AI model to determine whether the user has a purchase intention for a browsed commodity, the determining module 303 may obtain a purchase intention set/purchase intention database, each element in the set respectively representing a purchase intention of a current user for a certain commodity.

　The determining module 303 may set expiration time D. In the purchase intention set, an element containing information of a certain commodity and a purchase intention has the expiration time D, and within the expiration time D, the user does not browse the corresponding commodity in the element any more. That is, the expiration time D is between the date at which the user browses the commodity for the last time and the current time, and thus it may be determined that the user has lost the purchase intention for the commodity. At this time, the electronic device may remove the element containing the information of the commodity and the purchase intention from the purchase intention set, and such a design is more in line with the current requirement of the user.

　The determining module 303 may update the parameter of the AI model based on data collected when the user browses and purchases the commodity within a predetermined time period.

　The determining module 303 may determine whether the object meets a purchase habit of the user according to the obtained object. The determining module 303 may determine whether the object in the information meets a shopping habit of the user by comparing the commodity attribute included in the historical data of the shopping related behavior of the user with the object in the information.

　According to an embodiment of the present disclosure, the historical data of the shopping related behavior may include purchase data collected and become statistical when it is detected that the user purchases the commodity. The purchase data may include purchase time at which the user purchases the commodity within a predetermined cycle period and an attribute of the commodity.

　The determining module 303 may form a commodity purchase database based on the purchase data of the user. The purchase habit of the user may be determined from the commodity purchase database.

　When it is determined that the object (the commodity) included in the information received by the electronic device meets the purchase habit of the user or the user has the purchase intention for the commodity, the determining module may send the information to the user. When it is determined that the object included in the information received by the electronic device does not meet the purchase habit of the user or the user does not have the purchase intention, the determining module 303 intercepts the information for the user, which effectively prevents the information that may be junk information, thereby reducing the burden and distress of the user in reading information.

　As an example, when a mobile phone has new information required to be processed, the analyzing module 302 analyzes the text contents of the new information to extract a keyword (commodity information including a commodity, a commodity platform, a commodity brand, a commodity category, and the like). The determining module 303 precisely matches the commodity information (the commodity platform, the brand and the category) with an element in a set of purchase intentions of the user for the commodity, to determine whether the user has the purchase intention for the commodity. If the new information does not include all of the commodity platform, the commodity brand, and the commodity category, the determining module 303 performs fuzzy matching, and analyzes the search result to determine whether the user has the purchase intention for the commodity in the new information. For example, the new information relates to “Taobao, Brand A,” but does not relate to the category. At this time, the determining module 303 analyzes the purchase intention elements of all commodities matching the platform “Taobao” and the brand “A” in the purchase intention set. If there are N commodities satisfying the platform “Taobao” and the brand “A,” and there are purchase intentions for (N+1)/2 commodities, the determining module 303 determines that the user has the purchase intention for the commodity involved in the new information. Otherwise, the determining module 303 precisely matches the commodity information (the commodity platform, the brand and the category) with the purchase habit of the user for the commodity, to determine whether the user has the purchase intention for the commodity within the current time period. If the new information does not include all of the commodity platform, the commodity brand, and the commodity category, the determining module 303 performs fuzzy matching, and analyzes the search result to determine whether the user has the purchase intention for the commodity in the new information. For example, the new information relates to “Taobao, Category B,” but does not relate to the brand. The purchase habit elements of all commodities matching the platform “Taobao” and the category “B” in a purchase habit set are analyzed. If there are L commodities satisfying the platform “Taobao” and the category “B,” the L commodities are purchased K times in total, and there is a purchase period near a time node, the determining module 303 determines that the user has the purchase intention for the commodity provided in the new information. If it is determined that the user has the purchase intention for the commodity, the determining module 303 determines that the contents of the new information is used for the user, and thus displays the new information to the user normally; otherwise, intercepts the information.

　According to an embodiment of the present disclosure, the apparatus 300 forms an intelligent information processing strategy that is based on the purchase behavior of the user, by monitoring whether the user has the potential shopping behavior, collecting and analyzing the behavior data when the user browses and purchases a commodity on a shopping platform, obtaining whether the user has a potential purchase intention for the commodity through the artificial intelligence model, and extracting a purchase habit of the user through the historical purchase behavior data of the user. According to the present disclosure, it is possible that the new information received in the electronic device of the user is processed, and the information required by the user is pushed to the user. That is, the information is normally displayed in the notification information of the user, and the junk information not required by the user is intercepted.

　In the present disclosure, at least one of the plurality of modules may be implemented by the artificial intelligence (AI) model. The function associated with the AI may be performed by a non-volatile storage device, a volatile storage device, and a processor.

　As an example, the artificial intelligence model may consist of a plurality of neural network layers. Each layer has a plurality of weight values, and a layer operation is performed through a calculation of the previous layer and an operation of the plurality of weight values. Examples of a neural network include, but not limited to, a convolutional neural network (CNN), a deep neural network (DNN), a recursive neural network (RNN), a restricted Boltzmann machine (RBM), a depth belief network (DBN), a bidirectional recurrent depth neural network (BRDNN), a generative adversarial?network (GAN), and a deep Q network.

　A learning algorithm may refer to a method of using a plurality of pieces 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 the learning algorithm include, but not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

　Referring to Fig. 4, the computing apparatus 400 according to the exemplary embodiment of the present disclosure includes a memory 401 storing a computer program, and a processor 402. The computer program, when executed by the processor 402, implements the method for processing information according to the exemplary embodiment of the present disclosure.

　The computing apparatus in the embodiment of the present disclosure may include, but not limited to, an apparatus such as a mobile phone, a notebook computer, a PDA (Personal Digital Assistant), a PAD (tablet computer), and a desktop computer. The computing apparatus shown in Fig. 4 is only one example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.

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

　When executed by the processor 402, the computer program may further implement: determining whether the object meets a user requirement; not intercepting the information if the object meets the user requirement, otherwise, intercepting the information; determining whether the object meets the user requirement based on historical data of a shopping related behavior of a user; training an artificial intelligence model using historical data related to the potential shopping behavior, and determining whether the object meets the user requirement based on the trained artificial intelligence model; running the artificial intelligence model using data of a recent shopping related behavior within a preset time period, to obtain a first object set satisfying the user requirement; determining whether the object is matched with an element in the first object set; determining that the object satisfies the user requirement, if the object matches the element in the first object set, otherwise, determining that the object does not satisfy the user requirement; updating a parameter of the artificial intelligence model based on data collected when the user browses and purchases a commodity within a predetermined time period; determining a second object set in relation to a purchase habit of the user, based on historical data related to the factual shopping behavior; determining whether the object is matched with an element in the second object set; and determining that the object satisfies the user requirement, if the object matches the element in the second object set, otherwise, determining that the object does not satisfy the user requirement.

　For new information required to be processed, the computing apparatus 400 obtains a commodity tag (including a purchase platform, a brand, a category, and the like) by analyzing the text contents of the new information. If it is determined that the user has a purchase intention for the commodity, the computing apparatus 400 sends the information to the user normally, otherwise, intercepts the information.

　Further, as to a determination on whether the user has a purchase intention for a certain commodity, the computing apparatus 400 may determine whether the user has the purchase intention for the certain commodity in consideration of the purchase intention of the user for the commodity that is predicted by the AI model and the purchase habit of the user that is obtained from the historical shopping behavior data of the user, to determine whether to intercept some information. However, the above example is only exemplary, and the intention of the user may also be determined in consideration of an other user requirement.

　The processor 402 may include one or more processors. At this time, the one or more processors may be a general purpose processor (e.g., a central processing unit (CPU) and an application processor (AP)), a processor for graphics only (e.g., a graphics processing unit (GPU), a visual processing unit (VPU)), and/or an AI application specific processor (e.g., a neural processing unit (NPU)).

　The one or more processors control the processing on inputted data according to a predefined operating rule or an AI model stored in a non-volatile memory and a volatile storage device. The predefined operating rule or the artificial intelligence model may be provided through training or learning. Here, the providing through the learning means that a predefined operation rule or an AI model with an expected characteristic is formed by applying a learning algorithm to a plurality of pieces of learning data. The learning may be performed in the device itself performing the AI according to an embodiment, and/or may be implemented by a separate server/device/system.

　According to the intelligent information processing strategy of the present disclosure, some of the information that may be intercepted by the interception function of the electronic device may be displayed normally according to the requirement of the user. In this way, a different interception strategy may be used for a different user, such that the user will not miss the information that the user is interested in, and at the same time will not be distressed by a large amount of junk information.

　As used herein, the term “module” may include a unit implemented in hardware, software or firmware, and may interchangeably be used with other terms, for example, “logic,” “logic block,” “part,” or “circuit.” The module may be an integrated component or a minimum unit or part of the component, adapted to perform one or more functions. For example, according to an embodiment, the module may be implemented in the form of an application specific integrated circuit (ASIC).

　Various embodiments as set forth herein may be implemented as software including one or more instructions stored in a storage medium and readable by a machine (e.g., a mobile apparatus or an electronic device). For example, a 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 using one or more other components under the control of the processor. This enables the machine to be operated to perform at least one function according to the at least one invoked instruction. The one or more instructions may include a code generated by a complier or a code executable by an interpreter. A machine readable storage medium may be provided in the form of a non-transitory storage medium. Here, the term “non-transitory” simply means that the storage medium is a tangible apparatus, and does not include a signal (e.g., an electromagnetic wave), but this term does not differentiate between a case where data is semi-permanently stored in the storage medium and a case where the data is temporarily stored in the storage medium.

　According to an embodiment, a method according to various embodiments of the present disclosure may be included and provided in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine readable storage medium (e.g., compact disc read only memory (CD-ROM)), or distributed (e.g., downloaded or uploaded) online via an application store (e.g., Play Store™), or between two user apparatuses (e.g., smart phones) directly. If the computer program product is distributed online, at least part of the computer program product may be temporarily generated or at least temporarily stored in the machine readable storage medium such as a memory of a server of the manufacturer, a server of the application store, or a relay server.

　According to various embodiments, each component (e.g., module or program) of the above components may include a single entity or a plurality of entities. According to various embodiments, one or more of the above components may be omitted, or one or more other components may be added. Alternatively or additionally, a plurality of components (e.g., modules or programs) may be integrated into a single component. In this case, according to various embodiments, the integrated component may still perform one or more functions of each of the plurality of components in the same or similar way as that in which the one or more functions are performed by a corresponding one of the plurality of components before the integration. According to various embodiments, operations performed by the module, the program, or an other component may be performed sequentially, in parallel, repeatedly, or heuristically, or one or more of the operations may be executed in a different order, or omitted, or one or more other operations may be added.

　The present disclosure is shown and described with reference to the exemplary embodiments thereof. However, it should be appreciated 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 present disclosure as defined by the claims and their equivalents.

Claims

A method for processing information, comprising:

　acquiring information received from external device;

　analyzing contents of the acquired information to obtain an object included in the information;

　determining whether the object meets a user requirement based on historical data of a shopping related behavior of a user; and

　providing the information to the user if the object meets the user requirement; otherwise, intercepting the information.
The method according to claim 1, wherein the object comprises at least one of a commodity, a brand, a category, or a platform.
The method according to claim 1, wherein the shopping related behavior comprises a potential shopping behavior and a factual shopping behavior.
The method according to claim 3, wherein historical data related to the potential shopping behavior comprises data collected when the user performs at least one of: starting or running a shopping application in an electronic device, opening a link concerning a commodity, browsing the commodity, whether the commodity is added to a shopping cart, or whether the commodity is added to a favorites list.
The method according to claim 3, wherein historical data related to the factual shopping behavior comprises data collected when the user purchases the commodity within a predetermined time period.
The method according to claim 3, wherein the determining whether the object meets the user requirement based on historical data of a shopping related behavior of a user comprises:

　training an artificial intelligence model using the historical data related to the potential shopping behavior, and determining whether the object meets the user requirement based on the trained artificial intelligence model.
The method according to claim 6, wherein the determining whether the object meets the user requirement based on the trained artificial intelligence model comprises:

　running the artificial intelligence model using data of a recent shopping related behavior within a preset time period, to obtain a first object set satisfying the user requirement;

　determining whether the object is matched with an element in the first object set; and

　determining that the object satisfies the user requirement, if the object matches the element in the first object set; otherwise, determining that the object does not satisfy the user requirement.
The method according to claim 6, wherein the artificial intelligence model is trained by:

　generating characteristic data based on a category, a number of times and a time length when the user browses the commodity;

　generating tag data based on at least one of whether the commodity is added to the favorites list or whether the commodity is added to the shopping cart, wherein if the commodity is not added to the favorites list and not added to the shopping cart within predetermined time, a tag is set to not satisfying the user requirement; otherwise, the tag is set to satisfying the user requirement; and

　training the artificial intelligence model using the characteristic data and the tag data.
The method according to claim 3, wherein the determining whether the object meets the user requirement based on historical data of a shopping related behavior of a user comprises:

　determining a second object set in relation to a purchase habit of the user, based on the historical data related to the factual shopping behavior;

　determining whether the object is matched with an element in the second object set; and

　determining that the object satisfies the user requirement, if the object matches the element in the second object set; otherwise, determining that the object does not satisfy the user requirement.
An apparatus for processing information, comprising:

　at least one memory; and at least one processor coupled to the at least one memory and configured to:

　acquire information received from external device,

　analyze contents of the acquired information to obtain an object included in the information,

　determine whether the object meets a user requirement based on historical data of a shopping related behavior of a user, and

provide the information to the user if the object meets the user requirement; otherwise, intercept the information.
The apparatus according to claim 10, wherein the object comprises at least one of a commodity, a brand, a category, or a platform.
The apparatus according to claim 10, wherein the shopping related behavior comprises a potential shopping behavior and a factual shopping behavior.
The apparatus according to claim 11, wherein historical data related to the potential shopping behavior comprises data collected when the user performs at least one of: starting or running a shopping application in an electronic device, opening a link concerning a commodity, browsing the commodity, whether the commodity is added to a shopping cart, or whether the commodity is added to a favorites list.
The apparatus according to claim 11, wherein historical data related to the factual shopping behavior comprises data collected when the user purchases the commodity within a predetermined time period.
A computer readable recording medium, storing a program, wherein the program comprises an instruction for performing the method according to claim 1.