CN110866207B

CN110866207B - Data processing method, apparatus and machine readable medium

Info

Publication number: CN110866207B
Application number: CN201810991135.7A
Authority: CN
Inventors: 张祺; 叶毅巧; 张琼; 郜学敏; 叶菁; 钱伊玲
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2018-08-28
Filing date: 2018-08-28
Publication date: 2024-04-09
Anticipated expiration: 2038-08-28
Also published as: CN110866207A

Abstract

The embodiment of the application discloses a data processing method, a device and a machine-readable medium, wherein the method specifically comprises the following steps: determining target information corresponding to a user from information according to first relevant characteristics between the user and the information and first acceptability characteristics of the user for the pushing mode of the information; and sending the target information to the user. According to the method and the device for sending the information, the information can be prevented from being sent to the user with lower acceptance degree of the pushing mode to a certain extent, the disturbance of the target information to the user can be reduced, the information pushing effect can be improved, and the good information pushing effect can be obtained under the condition that a small amount of resources are consumed, so that the utilization rate of the resources can be improved.

Description

Data processing method, apparatus and machine readable medium

Technical Field

The present application relates to the field of computer technology, and in particular, to a data processing method, apparatus, and machine readable medium.

Background

With the development of computer technology, information push technology is one of the key technologies for touching users. The information pushing technology is a technology for reducing information overload by pushing information required by a user on the Internet through a certain technical standard or protocol. The information pushing technology actively pushes information to the user, so that the time spent by the user for searching on the network can be reduced.

In the information pushing technology, because the user can only passively receive information, the user is easily disturbed by uninteresting information, and the information pushing effect is poor. Moreover, the pushed information contains information which is not wanted by the user, so that poor information pushing effect is obtained under the condition of consuming a large amount of resources (network resources and human resources), and the utilization rate of the resources is low.

Disclosure of Invention

In view of the foregoing, an embodiment of the present application proposes a data processing method, apparatus and machine-readable medium to solve the problems of the related art.

To solve the above problems, an embodiment of the present application discloses a data processing method, including:

determining target information corresponding to a user from information according to first relevant characteristics between the user and the information and first acceptability characteristics of the user for the pushing mode of the information;

and sending the target information to the user.

receiving first information;

judging whether the first information is displayed or not according to a third correlation characteristic between a user and the first information and a third acceptability characteristic of the pushing mode of the user on the first information so as to obtain a judging result;

And displaying the first information under the condition that the judgment result is yes.

To solve the above problem, an embodiment of the present application further discloses a data processing apparatus, including:

the target information determining module is used for determining target information corresponding to the user from the information according to first relevant characteristics between the user and the information and first acceptability characteristics of the user on the pushing mode of the information; and

and the target information pushing module is used for sending the target information to the user.

the receiving module is used for receiving the first information;

the judging module is used for judging whether the first information is displayed or not according to a third correlation characteristic between the user and the first information and a third acceptability characteristic of the pushing mode of the user on the first information so as to obtain a judging result; and

and the display module is used for displaying the first information under the condition that the judgment result is yes.

To solve the above problem, an embodiment of the present application further discloses an apparatus, including:

one or more processors; and

One or more machine-readable media having instructions stored thereon, which when executed by the one or more processors, cause the apparatus to perform one or more of the methods described previously.

To address the above issues, an embodiment of the present application also discloses one or more machine readable media having instructions stored thereon that, when executed by one or more processors, cause an apparatus to perform one or more of the methods described previously.

As can be seen from the foregoing, the data processing method, apparatus and machine readable medium according to the embodiments of the present application have at least the following advantages:

the embodiment of the application combines the first related characteristic and the first acceptability characteristic to determine the target information corresponding to the user from the information. Because the first acceptance characteristic of the pushing mode of the information by the user can be used for representing the acceptance degree of the pushing mode by the user, the information can be prevented from being sent to the user with lower acceptance degree of the pushing mode to a certain degree.

And, under the situation that the user has higher acceptance degree for the pushing mode, the first related features can be combined to determine the target information related to the user; the first correlation characteristic between the user and the information can be used for representing the correlation degree between the user and the information, so that the interest degree of the user on the target information can be improved, and the information pushing effect is improved; and the irrelevant target information can be prevented from being sent to the user to a certain extent, so that the disturbance of the target information to the user can be reduced, and the information pushing effect can be improved.

In addition, the method and the device can improve the interest degree of the user on the target information, so that a good information pushing effect can be obtained under the condition of consuming a small amount of resources, and the utilization rate of the resources can be improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief description will be given below of the drawings that are needed in the embodiments or the prior art descriptions, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of an application environment of a data processing method according to an embodiment of the present application;

FIG. 2 is a flowchart illustrating steps of a first embodiment of a data processing method according to the present application;

FIG. 3 is a flowchart illustrating steps of a second embodiment of a data processing method according to the present application;

FIG. 4 is a flow chart of steps of a training method for a model according to an embodiment of the present application;

FIG. 5 is a flow chart of steps of a model-based data processing method according to an embodiment of the present application;

FIG. 6 is a flowchart illustrating steps of a third embodiment of a data processing method of the present application;

FIG. 7 is a flowchart illustrating steps of a fourth embodiment of a data processing method according to the present application;

FIG. 8 is a block diagram of an embodiment of a data processing apparatus of the present application;

FIG. 9 is a block diagram of an embodiment of a data processing apparatus of the present application; and

fig. 10 is a schematic structural diagram of an apparatus according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application are within the scope of the protection of the present application.

The concepts of the present application are susceptible to various modifications and alternative forms, specific embodiments thereof have been shown by way of example in the drawings and will herein be described in detail. It should be understood, however, that the description herein of specific embodiments is not intended to limit the concepts of the present application to the particular forms disclosed, but on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present application.

Reference in the specification to "one embodiment," "an embodiment," "one particular embodiment," etc., means that a particular feature, structure, or characteristic may be included in the described embodiments, but every embodiment may or may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, where a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the purview of one skilled in the art to effect such feature, structure, or characteristic in connection with other ones of the embodiments whether or not explicitly described. In addition, it should be understood that the items in the list included in this form of "at least one of A, B and C" may include the following possible items: (A); (B); (C); (A and B); (A and C); (B and C); or (A, B and C). Likewise, an item listed in this form of "at least one of A, B or C" may mean (A); (B); (C); (A and B); (A and C); (B and C); or (A, B and C).

In some cases, the disclosed embodiments may be implemented as hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried on or stored on one or more transitory or non-transitory machine-readable (e.g., computer-readable) storage media, which may be executed by one or more processors. A machine-readable storage medium may be implemented as a storage device, mechanism, or other physical structure (e.g., volatile or non-volatile memory, a media disc, or other media other physical structure device) for storing or transmitting information in a form readable by a machine.

In the drawings, some structural or methodological features may be shown in a particular arrangement and/or ordering. Preferably, however, such specific arrangement and/or ordering is not necessary. Rather, in some embodiments, such features may be arranged in a different manner and/or order than as shown in the drawings. Furthermore, inclusion of a feature in a particular figure that is not necessarily meant to imply that such feature is required in all embodiments and that, in some embodiments, may not be included or may be combined with other features.

The embodiment of the application provides a data processing method, which specifically comprises the following steps: determining target information corresponding to a user from information according to first relevant characteristics between the user and the information and first acceptability characteristics of the user for the pushing mode of the information; and sending the target information to the user.

In the embodiment of the application, the first correlation characteristic between the user and the information can be used for representing the correlation degree between the user and the information. The first related features can enable the target information related to the user to be determined from the information, so that the target information can be matched with the user, and the interest degree of the user on the target information can be improved. Because the embodiment of the application can avoid sending irrelevant target information to the user to a certain extent, the disturbance of the target information to the user can be reduced, and the information pushing effect can be improved.

The first acceptance characteristic of the pushing mode of the information by the user can be used for representing the acceptance degree of the pushing mode by the user, namely, whether the user is willing to accept the pushed information can be reflected to a certain degree. The first acceptability feature can avoid the disturbance of the target information to the user to a certain extent. For example, in the case that the first acceptability feature indicates that the user a has a low acceptability for the push mode, no information may be pushed to the user a; for another example, when the first acceptability feature indicates that the acceptability of the user B for the pushing manner is higher, the target information related to the user B may be determined by combining the first relevant feature, so that the disturbance of the target information on the user may be reduced, and the information pushing effect may be further improved.

In the embodiment of the present application, the types of information may include: news, advertisements, etc., where the advertisements may relate to goods or services. The information sending mode may include: short messages, mail, popup, phone, etc. It will be appreciated that embodiments of the present application are not limited to a particular type and manner of sending information.

The data processing method provided in the embodiment of the present application may be applied to the application environment shown in fig. 1, where as shown in fig. 1, the client 100 and the server 200 are located in a wired or wireless network, and through the wired or wireless network, the client 100 performs data interaction with the server 200.

Optionally, the client 100 may be running on a device, for example, the client 100 may be an APP running on the device, such as a short message APP, an electronic commerce APP, an instant messaging APP, an input method APP, or an APP carried by an operating system, etc., which is not limited in the embodiment of the present application. Alternatively, the apparatus may specifically include, but is not limited to: smart phones, tablet computers, e-book readers, MP3 (dynamic video expert compression standard audio plane 3,Moving Picture Experts Group Audio Layer III) players, MP4 (dynamic video expert compression standard audio plane 4,Moving Picture Experts Group Audio Layer IV) players, laptop portable computers, car computers, desktop computers, set-top boxes, smart televisions, wearable devices, and the like. It will be appreciated that embodiments of the present application are not limited to a particular device.

According to one embodiment, the server 200 may determine, from the information, the target information corresponding to the user according to the first correlation characteristic between the user and the information and the first acceptability characteristic of the pushing manner of the user on the information, and push the target information to the client 100 corresponding to the user, so that the client 100 displays the target information.

According to another embodiment, the client 100 may receive the first information; judging whether the first information is displayed according to a third correlation characteristic between a user and the first information and a third acceptability characteristic of the pushing mode of the user on the first information so as to obtain a judging result, and displaying the first information if the judging result is yes.

In an alternative embodiment of the present application, the client 100 may report the historical behavior data of the user to the server 200.

The reporting manner of the historical behavior data of the user by the client 100 may include: and reporting the collected historical behavior data of the user under the condition that the timing reporting mode, the periodic reporting mode or the network meets preset network conditions (such as a WIFI (wireless fidelity, wireless Fidelity) network or good signal quality).

The historical behavior data of the user may refer to any behavior data generated by the user through the device, and the historical behavior data of the user may include: search behavior data, browsing behavior data, input behavior data, feedback data for historical push information, collection behavior data, save behavior data, attention behavior data, selection behavior data, evaluation behavior data, and the like.

The history push information can reach the history information of the user in a push mode. The feedback data of the user on the historical push information can comprise: whether the user views the historical push information and whether conversion actions are executed after viewing the historical push information, the conversion actions may include: purchasing behavior, registering behavior, collecting behavior, and the like.

The feedback data of the user on the historical push information can represent the acceptance degree of the user on the push mode to a certain extent, so that the feedback data can be used as a determination basis of the first acceptance degree characteristic. Accordingly, the server 200 may determine the first acceptability feature according to the feedback data of the user on the historical push information.

For example, the user a does not view any historical push information, and may consider that the user a has a low acceptance of the push mode, that is, the user a is relatively disliked from the push mode. Or, the user B views all the historical push information, and can consider that the user has higher acceptance of the push mode. For another example, the user C views a part of the historical push information, and may consider that the user has a certain acceptance degree for the push mode.

Of course, the first receptivity feature is determined according to feedback data of the user on the historical push information, but as an alternative embodiment, actually, a person skilled in the art may determine the first receptivity feature in other manners, for example, providing an interface, and receiving the first receptivity feature input by the user through the interface. For example, an input box may be provided through the interface, which may allow for the input of values between 0 and 1. As another example, the following options may be provided through the interface: accepting the option, not accepting the option, or accepting the option of interest for the user option, wherein the first acceptance characteristics corresponding to the accepting the option of interest, not accepting the option, and accepting the option of interest may be: 1. 0, 0.6, etc. It is understood that the first acceptability feature is between 0 and 1, which is just an alternative embodiment, and in fact, the range of values corresponding to the first acceptability feature in the embodiments of the present application is not limited, for example, the range of values corresponding to the first acceptability feature may also be between 0 and 100, etc.

In the embodiment of the application, the user may have a first attribute. Optionally, the first attribute may include at least one of the following attributes: preference attributes and static attributes.

Static properties are relatively stable properties such as the user's age, gender, territory, academic, business, profession, marital, consumption level, identity (e.g., dad, mom, etc.), etc.

With respect to the relative stability of the static attributes described above, preference attributes typically have dynamics, which may change with changing user behavior.

In an alternative embodiment of the present application, the preference attribute may refer to a preference attribute of the user for information. Wherein the preference attribute may vary with a behavior of the user with respect to the information (at least one of a browsing behavior, a searching behavior, a collecting behavior, a saving behavior, a focusing behavior, a selecting behavior, and an evaluating behavior). Examples of preference attributes may include: like games, like music, like to purchase certain types of merchandise, like to purchase certain brands of merchandise, etc.

The above-described historical behavior data of the user may characterize the preference attributes of the user to some extent. Thus, in one embodiment of the present application, server 200 may determine the user's preference attributes based on the user's historical behavioral data.

Alternatively, the server 200 may rely on determining the static attributes of the user. For example, the static attribute may be determined based on registration information of the user on the own platform. Alternatively, the static attribute may be determined based on registration information of the user on the third party platform. The embodiment of the application does not limit the specific determination mode of the static attribute.

Method embodiment one

Referring to fig. 2, a flowchart illustrating steps of a first embodiment of a data processing method of the present application may specifically include the following steps:

step 201, determining target information corresponding to a user from information according to a first correlation characteristic between the user and the information and a first acceptability characteristic of the pushing mode of the user for the information;

step 202, the target information is sent to the user.

Steps 201 to 202 included in the method of the embodiment of the present application may be performed by a server. Of course, the embodiments of the present application do not limit the specific implementation subject corresponding to the method.

In step 201, the information may serve as a source of target information. For convenience of description, the embodiment of the present application uses the information set as a source of the target information, that is, the embodiment of the present application may obtain the target information from the information set.

A first correlation characteristic between the user and the information may be used to characterize a degree of correlation between the user and the information. The first related features can enable the target information related to the user to be determined from the information, so that the target information can be matched with the user, and the interest degree of the user on the target information can be improved.

In an optional embodiment of the present application, the first relevant feature between the user and the information may be obtained according to a first attribute word corresponding to the user and a second attribute word corresponding to the information.

Alternatively, a degree of correlation between the first attribute word and the second attribute word may be determined as the above-described first correlation feature. The process of determining the degree of relatedness between the first and second attributed words may include: and respectively determining a first word vector and a second word vector corresponding to the first attribute word and the second attribute word, determining the similarity between the first word vector and the second word vector, and determining the correlation according to the similarity.

Wherein, the first attribute word corresponding to the user can be used for representing the first attribute of the user. The first attribute word may include:

preference attribute words obtained according to the historical behavior data of the user; and/or

The static attribute words of the user.

The historical behavior data of the user may correspond to a preset time period, the ending time of the preset time period may be the current time, and the time length of the preset time period may be determined by a person skilled in the art according to actual application requirements, for example, the time length may be 6 months, 3 months, 1 month, and the like.

The method for obtaining the preference attribute words according to the historical behavior data of the user in the embodiment of the application can comprise the following steps: statistical methods, pattern recognition methods, and the like. The statistical mode can be used for counting the information keywords corresponding to the historical behavior data of the user so as to obtain the information keywords with higher occurrence frequency as preference attribute words. The mode recognition mode can preset preference attribute categories, and the target preference attribute category corresponding to the historical behavior data is determined through a classification method.

In the embodiment of the present application, preference attribute words may include, but are not limited to: running, music, shuttlecocks, brands of goods, types of goods, etc. It will be appreciated that embodiments of the present application are not limited to specific preference attribute words.

The second attribute word may be used to characterize an attribute of the information. The second attribute word may include:

the attribute words of the commodities corresponding to the information; and/or

And extracting attribute words from the text corresponding to the information.

The information of the embodiment of the application can correspond to commodities. The attribute words possessed by the commodity may include: commodity type words, commodity name words, commodity brand words, and the like. The commodity type can refer to an attribute set which is generalized according to the same attribute of a certain class of commodity, for example, the type of a mobile phone has common attributes such as screen size, ringtone, network system and the like; the book types have common attributes such as publishing agency, author, ISBN (International Standard book number ) number, etc. The commodity type can add more display points on the basis of simple commodities. The commodity type may include three parts of extended attributes, parameters, specifications, etc.

The information of the embodiment of the application may correspond to text. According to the embodiment of the application, the attribute words can be extracted from the text corresponding to the information, and the corresponding extraction process can comprise the following steps: and segmenting the text corresponding to the information, removing stop words from the segmentation result, and extracting attribute words of a preset type. The preset type of attribute words may include: commodity words, brand words, industry words, etc. Commodity words may refer to words related to a commodity. Brand words may include: enterprise brands (e.g., e-commerce brands, etc.). Industry words may characterize an industry.

In one application example of the present application, assume that the text corresponding to the information is "[ AA net ] store celebration is to let go of-full 188-element return 288-element coupon-! 1 Yuan explosion type is robbed every day, paris water 1 Yuan/1 bottle in France-! Snack buy 1 increases by 1-! The address xxx TD unsubscribes from which the attribute words "AA", "paris water", "snack" etc. can be extracted.

Stop Words (Stop Words) may refer to Words that occur frequently in text but have little practical meaning. The stop words may include: the words of the mood aid, adverbs, prepositions, conjunctions, etc. are generally not themselves explicitly meaningful, and only put them into a complete sentence to have a certain effect. Such as the common words "a", "an", "and", "next" and the like.

In an alternative embodiment of the present application, the types of information may include: commodity type and/or text type. The first relevant feature between the information of the commodity type and the user may be relevant feature X11, and the first relevant feature between the information of the text type and the user may be relevant feature X12. Since the determination process of the relevant feature X11 and the relevant feature X12 may be different, for example, the relevant feature X11 and the relevant feature X12 may be provided by different platforms or modules, respectively, the relevant feature X11 or the relevant feature X12 may be optionally adjusted by using the adjustment coefficient a, and the adjustment may reduce the difference caused by different determination processes, so that the normalization may be performed.

Optionally, the process of adjusting the relevant feature X11 or the relevant feature X12 may include: the correlation feature X11 or the correlation feature X12 is multiplied by the adjustment coefficient a. Thus, the first correlation characteristic between the user and the information can be expressed as:

X1＝a1*X11+a2*X12 (1)

in one embodiment of the present application, the correlation feature X11 may correspond to the adjustment coefficient a1, and the correlation feature X12 may correspond to the adjustment coefficient a2.

The adjustment coefficient a1 and the adjustment coefficient a2 may have current values, and initial values of the current values may be manually determined.

Optionally, the adjustment coefficient a2 may be adjusted according to a pushing effect corresponding to the text type information; for example, if the pushing effect corresponding to the text type information is poor, a2 may be reduced.

Optionally, the adjustment coefficient a1 may be adjusted according to a pushing effect corresponding to information of the commodity type; for example, if the pushing effect corresponding to the information of the commodity type is poor, a1 may be reduced.

Optionally, the adjustment coefficient a1 or a2 can be adjusted according to the pushing effect corresponding to the text type and the commodity type information respectively; for example, if the push effect corresponding to the information of the commodity type is lower than the push effect corresponding to the information of the text type, a2 may be increased; or if the pushing effect corresponding to the text type information is lower than the pushing effect corresponding to the commodity type, the a1 can be increased.

The pushing effect corresponding to the information can be determined according to the pushing quantity and the feedback condition corresponding to the information. Feedback conditions may include: view quantity, etc. For example, the pushing effect may be obtained according to a ratio of the number of views to the number of pushes.

It will be appreciated that, those skilled in the art may determine the adjustment coefficient a1 and the adjustment coefficient a2 according to practical application requirements, and the specific determination manners of the adjustment coefficient a1 and the adjustment coefficient a2 are not limited in the embodiments of the present application.

According to one embodiment, an interface may be provided and a first receptivity feature for user input is received via the interface.

According to another embodiment, the first acceptability feature may be obtained according to feedback data of the user on the historical push information.

The feedback data of the user on the historical push information can represent the acceptance degree of the user on the push mode to a certain extent, so that the feedback data can be used as a determination basis of the first acceptance degree characteristic.

In one embodiment of the present application, the first acceptability feature AR1 may be determined according to the number of historical push information f1 and the number of historical push information f2 that the user views, and may be expressed as:

AR1＝f2/f1 (2)

wherein, f1 may refer to the total number of the history push information, f2 may be obtained according to the feedback data of the history push information, if the user views one history push information, f2 is added with 1, otherwise, if the user does not view one history push information, f2 is unchanged.

In another embodiment of the present application, the first acceptability feature may be obtained according to feedback data of the user on the historical push information and a second correlation feature between the user and the historical push information. According to the method and the device for determining the first acceptability feature, the feedback data and the second relevant feature are comprehensively considered in the process of determining the first acceptability feature, and accuracy of the first acceptability feature can be improved.

According to the embodiment of the application, under the condition that the second related characteristic is high, the user checks the history push information normally; when the second correlation characteristic is low, if the user views the history push information, the user can be considered to have higher acceptance degree for the pick-up mode; it can be considered that the relationship between the first receptivity feature and the second correlation feature may be a negative relationship, and thus the following manner of determining the first receptivity feature AR1 may be provided:

First according to X _2i And r _i Determining the contribution characteristic of the ith history pushing information on the acceptance degree, namely the contribution characteristic of the ith history pushing information for short; thenSumming the contribution features of all the ith history pushing information to obtain f1 contribution features of the history pushing information; then, AR1 is determined from the contribution features of the f1 pieces of history push information and f1, and for example, a ratio of the contribution features of the f1 pieces of history push information to f1 may be used as AR1.

Wherein i represents the ith history push information in the f1 history push information, X _2i Representing a second correlation characteristic between the ith historical push information and the user, r _i Indicating whether the user views the ith historical push information, if so, r _i =1, otherwise r _i ＝0。

Optionally, in determining the contribution feature of the ith history push information, the second correlation feature may be first inverted, for example, the inverting may include: determining a difference between 1 and the second correlation feature; the inverted second correlation characteristic can then be correlated with r _i Fusing to obtain the contribution characteristic of the ith history pushing information; the above fusion may be addition or multiplication, etc.

Of course, the manner of determining AR1 based on the contribution feature and the formula (2) is merely an alternative embodiment of the manner of determining the first receptivity feature, and in fact, those skilled in the art may use other manners of determining the first receptivity feature according to actual needs, and the embodiment of the present application does not limit the specific manner of determining the first receptivity feature.

It should be noted that, in the embodiment of the present application, the feedback data may correspond to a preset time period, and in order to improve accuracy of the first acceptability feature, a time length of the preset time period may exceed a time length threshold, where the time length threshold may be 1 month, 2 months, and so on. Alternatively, in the case where the time length of the preset time period does not exceed the time length threshold, the first acceptability feature may be assigned, for example, the value assigned to the first acceptability threshold may be a value of 0.5 or the like.

The embodiment of the application does not limit the specific process of determining the target information corresponding to the user from the information in step 201.

According to an embodiment, step 201 may first determine whether the user is willing to accept the pushed information according to the first acceptability feature, if not, no information may be sent to the user, and if so, the target information corresponding to the user may be determined from the information according to the first relevant feature.

Optionally, the determining whether the user is willing to accept the push information may specifically include: and judging whether the first acceptability feature exceeds a first threshold, if so, the user is willing to accept the push information, and if not, the user is unwilling to accept the push information. The first threshold may be a positive number less than 0.5, and the embodiments of the present application are not limited to a specific first threshold.

According to another embodiment, step 201 may fuse the first acceptability feature and the first relevant feature to obtain a fused feature, and determine, according to the fused feature, target information corresponding to the user from the information. Optionally, fusing the first acceptability feature and the first relevant feature may specifically include: the first receptivity feature and the first correlation feature are weighted and averaged, wherein weights w1 and w2 corresponding to the first receptivity feature and the first correlation feature respectively can be determined by a person skilled in the art according to actual application requirements, and the weighted and averaged process can be expressed as follows:

MiX1＝AR1*w1+X1*w2 (3)

the determining, according to the fusion feature, the target information corresponding to the user from the information may specifically include: the information that the fusion characteristic exceeds a second threshold value is used as target information; or ordering the information according to the sequence of the fusion characteristics from large to small, and selecting the information of the N (N is a natural number) digits arranged in front as target information.

In step 202, the sending manner of the target information may include: short messages, mails, popups, telephones, etc., it can be understood that the specific sending mode of the target information is not limited in the embodiments of the present application.

In summary, according to the data processing method of the embodiment of the present application, the first relevant feature and the first receptivity feature are combined, and the target information corresponding to the user is determined from the information. Because the first acceptance characteristic of the pushing mode of the information by the user can be used for representing the acceptance degree of the pushing mode by the user, the information can be prevented from being sent to the user with lower acceptance degree of the pushing mode to a certain degree.

Method embodiment II

Referring to fig. 3, a flowchart illustrating steps of a second embodiment of a data processing method of the present application may specifically include the following steps:

step 301, determining the probability of the user viewing the information according to a first correlation characteristic between the user and the information and a first acceptability characteristic of the pushing mode of the user for the information;

step 302, determining target information corresponding to the user from the information according to the probability;

step 303, sending the target information to the user.

Compared with the first embodiment of the method shown in fig. 2, in this embodiment, the probability of the user viewing the information may be determined according to the first correlation feature and the first acceptability feature, and the target information may be determined from the information according to the probability; therefore, the target information can be enabled to correspond to a higher probability, the probability of checking the target information by a user can be further improved, the information pushing effect is improved, and the interference of the target information to the user can be reduced.

In an optional embodiment of the present application, step 301 may specifically include determining a probability that the user views the information: and determining the probability of the user viewing the information according to the first relevant feature, the first acceptability feature and the mapping relation among the relevant feature, the acceptability feature and the probability.

The mapping relation can be determined by a person skilled in the art according to the actual application requirements. Referring to table 1, an illustration of a mapping relationship according to an embodiment of the present application is shown. Step 301 may look up table 1 based on AR1 and X1 to obtain probability P.

In table 1, the associated feature X may be divided into a plurality of first shift positions and the acceptance feature AR may be divided into a plurality of second shift positions, respectively, and the probability P may be determined according to a combination of the first shift position and the second shift position.

Specifically, the acceptability feature AR may be divided into 3 second gears: AR & gt, 0.8, 0.5-0.8, and AR < 0.5.

In the case where AR > 0.8, the user is considered to have a high acceptance of the push method, and therefore the probability P can be increased based on the relevant feature X. For example, if the correlation feature X is greater than 0.2, a higher value may be assigned for the probability P; alternatively, if X < 0.2, p=0.2.

Under the condition that AR is more than or equal to 0.5 and less than or equal to 0.8, the user can be considered to have low acceptance of the pushing mode, but still can accept the pushing mode, so that the probability P can be determined according to the related characteristics X. For example, if the correlation feature X is greater than 0.5, a higher value may be assigned for the probability P; alternatively, if X < 0.5, a lower value is given to probability P.

When AR < 0.5, the user is considered to have a low acceptance of the push method, and therefore the probability P can be reduced based on the correlation characteristic X.

TABLE 1

It can be understood that the mapping relationships shown in table 1 are merely examples, and those skilled in the art may actually determine the mapping relationships according to actual application requirements, and the embodiments of the present application do not limit specific mapping relationships.

In an alternative embodiment of the present application, the mapping relationship may be characterized by a model; the model may include a plurality of training samples, one of which may include: one history push information received by a user and feedback data of the user for the one history push information. According to the embodiment of the application, the training samples can be determined according to the history pushing information, and different training samples can correspond to different history pushing information.

In one embodiment of the present application, the training process of the model may include: determining training characteristics corresponding to the training samples; the training features may include: a second correlation characteristic X2 between the user and one piece of history push information and a second acceptance characteristic AR2 of the push mode of the user for the information in a history time period corresponding to the one piece of history push information; and training the training samples according to the training characteristics corresponding to the training samples to obtain the model.

The determination of the second correlation characteristic X2 is similar to the determination of the first correlation characteristic X1. One difference is that the second correlation feature X2 may be used to characterize the degree of correlation between the user and a piece of historical push information received, while the first correlation feature X1 may be used to characterize the degree of correlation between the user and a piece of information to be pushed. Therefore, the determination process of the second correlation characteristic X2 is not described herein, and is merely referred to herein.

The second acceptability feature AR2 determination process is similar to the first acceptability feature AR1 determination process, and the determination basis of both may include: and the user feeds back data of the historical push information. One difference is that the feedback data of the first receptivity feature AR1 corresponds to a preset time period, the feedback data of the second receptivity feature AR2 corresponds to a historical time period, and the start time of the preset time period and the historical time period may be the same, but the end time may be different.

Alternatively, the expiration time of the preset period of time may include: the expiration time of the history period may be the latest feedback time of the user for one history push information as a training sample from the latest feedback time of the user for all history push information to the time between the execution times of step 301.

In an application example of the present application, assuming that the user receives f1 (f 1 is a natural number) pieces of history push information in total, the latest feedback time of the user for all f1 pieces of history push information is T1, and the execution time of step 301 is T2, and T2 is later than T1, the ending time of the preset time period corresponding to the first receptivity feature AR1 may be any time between [ T1, T2 ]. And for the j (1.ltoreq.j.ltoreq.f1) th history push information in the f1 history push information, the ending time of the corresponding history period may include: feedback time of the user for the j-th history push information.

It should be noted that, for different history push information in the f1 history push information, the start time of the corresponding history period may be the same, but the end time may be different. Different historical push information corresponds to different termination time, so that different training samples can correspond to different second acceptability features AR2.

In one embodiment of the present application, the second receptivity feature AR2 may be determined for the jth history push information, and may be expressed as:

AR1＝f3/j (4)

j represents the number of history push information received before the user's feedback time for the j-th history push information; f3 may refer to the amount of historical push information the user views before the user's feedback time for the jth historical push information.

The present embodiment may provide the following manner of determining the second acceptability feature AR 2:

first according to X _2i And r _i Determining the contribution characteristic of the ith history pushing information on the acceptance degree, namely the contribution characteristic of the ith history pushing information for short; then, the contribution features of the j i-th history pushing information are summed to obtain the contribution features of the j history pushing information; then, AR2 is determined according to the contribution features of the j pieces of history push information and j, for example, a ratio of the contribution features of the j pieces of history push information to j may be taken as AR2.

Wherein i represents the ith history push information in the j history push information, X _2i Representing a second correlation characteristic between the ith historical push information and the user, r _i Indicating whether the user views the ith historical push information, if so, r _i =1, otherwise r _i ＝0。

In practical applications, the training samples may be trained by a machine learning algorithm to obtain the model. Examples of the machine learning algorithm described above may include: neighbor classification, bayesian, LR (logistic regression ), SVM (support vector machine, support Vector Machine), adaboost (adaptive enhancement), neural networks, hidden markov, etc., it will be appreciated that the embodiments of the present application do not limit the machine learning algorithm to which the model corresponds.

The machine learning method can design and analyze some algorithms which enable a computer to automatically learn, the algorithms can automatically analyze and obtain rules from training data, and the rules are utilized to predict unknown data, so that the machine learning method has better robustness and can obtain higher precision.

In an application example of the present application, it is assumed that the set corresponding to the training sample is { (x) _i ,y _i ) I=1,.. _i For a feature corresponding to a training sample (i-th history push information), y _i Is x _i Corresponding probability, if the ith history push information is checked by the user, y _i =1, or if the ith history push information is notViewed by the user, y _i =0; the output function corresponding to the SVM model trained using the machine learning algorithm may be f (x).

The input of f (x) may be: the feature x, x corresponding to the information to be pushed may include: the output of the first acceptance feature and the first correlation feature, f (x), may be a probability of the user viewing the information. Alternatively, f (x) may be a sign function, although embodiments of the present application specifically provide f (x). f (x) also corresponds to parameters, and the training process described above can be used to determine parameters of the model. It will be appreciated that the parameters of the model may be updated as the training samples are updated.

In step 301, a feature x corresponding to information may be input into a model to obtain a probability that a user output by the model views the information.

Step 302 may specifically include the process of determining, from the information, the target information corresponding to the user according to the probability: judging whether the probability corresponding to one piece of information exceeds a probability threshold value, and if so, taking the piece of information as target information.

The probability threshold may be determined by one skilled in the art according to the actual application requirements. Generally, the larger the probability threshold, the less the target information interferes with the user; the smaller the probability threshold, the greater the amount of target information. It will be appreciated that embodiments of the present application are not limited to a particular probability threshold.

Referring to fig. 4, a flowchart illustrating steps of a training method of a model according to an embodiment of the present application may specifically include the following steps:

step 401, determining information s corresponding to a training sample;

step 402, determining a second receptivity feature AR2 of the pushing mode of the user for the information in the historical time period corresponding to the information s;

step 403, determining a correlation characteristic X21 between the commodity corresponding to the information s and the user;

when the information corresponds to a commodity, step 403 is executed, and when the information does not correspond to a commodity, step 403 may not be executed.

Step 404, determining a relevant feature X22 between the text corresponding to the information s and the user;

step 405, determining a second correlation characteristic X2 between the user and the information s according to the correlation characteristic X21 and the correlation characteristic X22;

step 406, training the training samples according to training features corresponding to the training samples to obtain a model; the model is used for representing the mapping relation among related features, acceptability features and probabilities, and the training features can comprise: a second correlation feature X2 and a second acceptance feature AR2.

Referring to fig. 5, a flowchart illustrating steps of a model-based data processing method according to an embodiment of the present application may specifically include the following steps:

step 501, determining information s to be pushed;

step 502, determining a first acceptability feature AR1 of a pushing mode of the user for the information in a preset time period corresponding to the information s;

step 503, determining a correlation characteristic X11 between the commodity corresponding to the information s and the user;

note that, when the information corresponds to a commodity, step 503 is executed, and when the information does not correspond to a commodity, step 503 may not be executed.

Step 504, determining relevant features X12 between the text corresponding to the information s and the user;

Step 505, determining a first correlation characteristic X1 between the user and the information s according to the correlation characteristic X11 and the correlation characteristic X12;

step 506, inputting the first correlation feature X1 and the first acceptability feature AR1 into a model to obtain the probability of viewing the information s by the user output by the model;

step 507, judging whether the probability of the user checking the information s exceeds a probability threshold, if so, executing step 508, otherwise, executing step 509;

step 508, sending information s to the user;

step 509, not sending information s to said user.

Training the training samples according to training characteristics corresponding to the training samples to obtain a model; the model is used for representing the mapping relation among related features, acceptability features and probabilities, and the training features can comprise: .

In summary, according to the data processing method of the embodiment of the present application, the probability of the user viewing the information may be determined according to the first relevant feature and the first receptivity feature. Determining target information from the information according to the probability; therefore, the target information can be enabled to correspond to a higher probability, the probability of checking the target information by a user can be further improved, the information pushing effect is improved, and the interference of the target information to the user can be reduced.

Method example III

Referring to fig. 6, a flowchart illustrating steps of a third embodiment of a data processing method of the present application may specifically include the following steps:

step 601, receiving first information;

step 602, judging whether to display the first information according to a third correlation characteristic between the user and the first information and a third acceptability characteristic of the pushing mode of the user on the first information so as to obtain a judgment result;

and step 603, displaying the first information when the judgment result is yes.

At least one step included in the method of the embodiment of the present application may be executed by the client, and the embodiment of the present application does not limit the specific execution body corresponding to the step.

In this embodiment of the present application, the received first information may be a push message or a non-push message. For example, the server may obtain target information corresponding to a user through the method described in fig. 2, 3, 4 or 5, and send the target information to a client corresponding to the user; for a client, the target information it receives may be referred to as first information.

A third correlation characteristic between the user and the first information may be used to characterize the degree of correlation between the user and the first information. The third related feature can enable the first information related to the user to be displayed, and the first information unrelated to the user can not be displayed, so that interference of the displayed first information on the user can be reduced.

In an optional embodiment of the present application, the third correlation feature between the user and the first information may be obtained according to the first attribute word corresponding to the user and the third attribute word corresponding to the first information.

Optionally, the third attribute word may specifically include:

the attribute words of the commodities corresponding to the first information; and/or

And extracting attribute words from the text corresponding to the first information.

Alternatively, a degree of correlation between the third attribute word and the second attribute word may be determined as the above-described third correlation feature. The process of determining the correlation between the third attribute word and the second attribute word is similar to the process of determining the correlation between the first attribute word and the second attribute word, and therefore, the description thereof will be omitted herein, and reference is made to the description.

According to one embodiment, an interface may be provided and a third receptivity feature for user input may be received via the interface.

According to another embodiment, the third receptivity feature may be obtained according to feedback data of the user on the historical push information.

In another embodiment of the present application, the third acceptability feature may be obtained according to feedback data of the user on the historical push information and a second correlation feature between the user and the historical push information.

The determination process of the third acceptability feature is similar to the determination process of the first acceptability feature, and therefore, the description thereof will be omitted herein, and the description thereof will be omitted.

The third acceptance characteristic of the pushing mode of the user for the first information can be used for representing the acceptance degree of the user for the pushing mode, namely, whether the user is willing to accept the pushed first information can be reflected to a certain degree.

The third acceptance characteristic can avoid the interference of the displayed first information to the user to a certain extent. For example, if the third acceptability feature indicates that the user a has a low acceptability for the push manner, any first information may not be displayed to the user a; for another example, when the third receptivity feature indicates that the receptivity of the user B to the pushing manner is higher, the third correlation feature may be combined to determine whether to display the first information to the user B, so that the disturbance of the displayed first information to the user B may be reduced, and the information pushing effect may be further improved.

In step 603, the first information may be displayed by popup window, notification, or the like. The notification is a notification with global effect, which is shown at the top of the screen. The notification center may display information of any information source so that the user knows the latest dynamics by looking at the information. In the case that the judgment result is no, the first information may be displayed.

In summary, the third correlation feature between the user and the first information in the data processing method of the embodiment of the application may be used to characterize the degree of correlation between the user and the first information. The third related feature can enable the first information related to the user to be displayed, and the first information unrelated to the user can not be displayed, so that interference of the displayed first information on the user can be reduced.

The third acceptance characteristic of the pushing mode of the user for the first information can be used for representing the acceptance degree of the user for the pushing mode, namely, whether the user is willing to accept the pushed first information can be reflected to a certain degree. The third acceptance characteristic can avoid the interference of the displayed first information to the user to a certain extent.

Method example IV

Referring to fig. 7, a flowchart illustrating steps of a fourth embodiment of a data processing method of the present application may specifically include the following steps:

step 701, receiving first information;

step 702, determining a first probability of the user viewing the first information according to a third correlation characteristic between the user and the first information and a third acceptability characteristic of the pushing mode of the user for the first information;

Step 703, judging whether to display the first information according to the first probability to obtain a judgment result;

step 704, displaying the first information if the judgment result is yes.

Compared with the third embodiment of the method shown in fig. 6, in this embodiment, a first probability of the user checking the first information may be determined according to the third correlation feature and the third receptivity feature, and whether to display the first information may be determined according to the first probability; therefore, the first information corresponding to the higher first probability can be displayed, and the interference of the displayed first information to the user can be reduced.

Optionally, step 703 may include determining whether to display the first information: determining a first probability of the user viewing the first information according to a third correlation characteristic between the user and the first information and a third acceptability characteristic of the pushing mode of the user for the first information; and judging whether to display the first information according to the first probability.

Optionally, the determining the first probability that the user views the information may specifically include: and determining a first probability of the user viewing the information according to the third correlation feature, the third acceptance feature and the mapping relation among the correlation feature, the acceptance feature and the probability.

According to an embodiment, the mapping relationship between the relevant features, the receptivity features and the probabilities may refer to table 1, which is not described herein.

According to another embodiment, the mapping relationship may be characterized by a model; the model includes a plurality of training samples, one of which may include: one history push information received by a user and feedback data of the user for the one history push information. The training process and the using process of the model can refer to fig. 4 and fig. 5, and are not described herein in detail, but can refer to each other.

In summary, according to the data processing method of the embodiment of the present application, a first probability of a user checking first information may be determined according to a third correlation feature and a third receptivity feature, and whether to display the first information is determined according to the first probability; therefore, the first information corresponding to the higher first probability can be displayed, and the interference of the displayed first information to the user can be reduced.

It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some blocks may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are all preferred embodiments and that the acts referred to are not necessarily required by the embodiments of the present application.

The embodiment of the application also provides a data processing device.

With reference to fig. 8, a block diagram of an embodiment of a data processing apparatus of the present application is shown, and may specifically include the following modules:

the target information determining module 801 is configured to determine target information corresponding to a user from information according to a first correlation characteristic between the user and the information and a first receptivity characteristic of the user to a pushing manner of the information; and

and a target information pushing module 802, configured to send the target information to the user.

Optionally, the first acceptability feature may be obtained according to feedback data of the user on the historical push information.

Alternatively, the first acceptability feature may be derived from feedback data of the user on the historical push information and a second correlation feature between the user and the historical push information.

Optionally, the target information determining module 801 may include:

the probability determining module is used for determining the probability of the user to view the information according to the first correlation characteristic between the user and the information and the first acceptability characteristic of the pushing mode of the user to the information; and

And the information determining module is used for determining target information corresponding to the user from the information according to the probability.

Optionally, the probability determining module may include:

and the mapping determining module is used for determining the probability of the user viewing the information according to the first relevant feature, the first acceptability feature and the mapping relation among the relevant feature, the acceptability feature and the probability.

Alternatively, the mapping relationship may be characterized by a model; the model may include a plurality of training samples, one of which may include: one history push information received by a user and feedback data of the user for the one history push information.

Optionally, the apparatus may further include:

the training feature determining module is used for determining training features corresponding to the training samples; the training features may include: a second correlation characteristic between the user and one piece of history push information and a second acceptance characteristic of the push mode of the user for the information in a history time period corresponding to the one piece of history push information;

and the training module is used for training the training samples according to the training characteristics corresponding to the training samples so as to obtain the model.

Optionally, the first correlation characteristic between the user and the information is obtained according to a first attribute word corresponding to the user and a second attribute word corresponding to the information.

Optionally, the first attribute word corresponding to the user may include:

The static attribute words of the user.

Optionally, the second attribute word may include:

the attribute words of the commodities corresponding to the information; and/or

And extracting attribute words from the text corresponding to the information.

In summary, the data processing apparatus according to the embodiment of the present application determines, from the information, the target information corresponding to the user in combination with the first relevant feature and the first receptivity feature. Because the first acceptance characteristic of the pushing mode of the information by the user can be used for representing the acceptance degree of the pushing mode by the user, the information can be prevented from being sent to the user with lower acceptance degree of the pushing mode to a certain degree.

With reference to fig. 9, a block diagram of an embodiment of a data processing apparatus of the present application is shown, which may specifically include the following modules:

a receiving module 901, configured to receive first information;

the judging module 902 is configured to judge whether to display the first information according to a third correlation characteristic between the user and the first information and a third receptivity characteristic of the pushing manner of the user on the first information, so as to obtain a judging result; and

the display module 903 is configured to display the first information if the determination result is yes.

Optionally, the third acceptability feature is obtained according to feedback data of the user on the historical push information.

Optionally, the third acceptability feature is obtained according to feedback data of the user on the historical push information and a second correlation feature between the user and the historical push information.

Optionally, the determining module 902 may include:

The first probability determining module is used for determining a first probability of the user viewing the first information according to a third correlation characteristic between the user and the first information and a third acceptability characteristic of the pushing mode of the user for the first information;

and the probability judging module is used for judging whether the first information is displayed or not according to the first probability.

Optionally, the first probability determining module may specifically include:

and the mapping probability determining module is used for determining the first probability of the user viewing the information according to the third related feature, the third receptivity feature, the related feature, the mapping relation among the receptivity feature and the probability.

Alternatively, the mapping relationship may be characterized by a model; the model may include a plurality of training samples, one of which may include: one history push information received by a user and feedback data of the user for the one history push information. The training process and the using process of the model can refer to fig. 4 and fig. 5, and are not described herein in detail, but can refer to each other.

Optionally, the third attribute word may specifically include:

For the device embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and similar references are made to each other.

Embodiments of the present application may be implemented as a system or apparatus configured as desired using any suitable hardware and/or software. Fig. 10 schematically illustrates an example apparatus 1100 that may be used to implement various embodiments described herein.

For one embodiment, fig. 10 illustrates an exemplary apparatus 1100, the apparatus 1100 may include: one or more processors 1102, a system control module (chipset) 1104 coupled to at least one of the processors 1102, a system memory 1106 coupled to the system control module 1104, a non-volatile memory (NVM)/storage 1108 coupled to the system control module 1104, one or more input/output devices 1110 coupled to the system control module 1104, and a network interface 1112 coupled to the system control module 1106. The system memory 1106 may include: instructions 1162, the instructions 1162 being executable by the one or more processors 1102.

The processor 1102 may include one or more single-core or multi-core processors, and the processor 1102 may include any combination of general-purpose or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). In some embodiments, the apparatus 1100 can function as a server, a target device, a wireless device, etc., as described in embodiments of the present application.

In some embodiments, the apparatus 1100 may include one or more machine-readable media (e.g., system memory 1106 or NVM/storage 1108) having instructions and one or more processors 1102, in combination with the one or more machine-readable media, configured to execute the instructions to implement the modules included in the foregoing apparatus to perform the actions described in the embodiments of the present application.

The system control module 1104 of an embodiment may include any suitable interface controller for providing any suitable interface to at least one of the processors 1102 and/or any suitable device or component in communication with the system control module 1104.

The system control module 1104 for one embodiment may include one or more memory controllers to provide interfaces to the system memory 1106. The memory controller may be a hardware module, a software module, and/or a firmware module.

The system memory 1106 for one embodiment may be used for loading and storing data and/or instructions 1162. For one embodiment, the system memory 1106 may include any suitable volatile memory, such as, for example, a suitable DRAM (dynamic random Access memory). In some embodiments, system memory 1106 may comprise: double data rate type four synchronous dynamic random access memory (DDR 4 SDRAM).

The system control module 1104 for one embodiment may include one or more input/output controllers to provide interfaces to the NVM/storage 1108 and the input/output device(s) 1110.

NVM/storage 1108 of one embodiment may be used to store data and/or instructions 1182. NVM/storage 1108 may include any suitable nonvolatile memory (e.g., flash memory, etc.) and/or may include any suitable nonvolatile storage device(s), such as one or more Hard Disk Drives (HDDs), one or more Compact Disc (CD) drives, and/or one or more Digital Versatile Disc (DVD) drives, etc.

NVM/storage 1108 may include storage resources that are physically part of the device on which device 1100 is installed or which may be accessed by the device without being part of the device. For example, NVM/storage 1108 may be accessed over a network via network interface 1112 and/or through input/output devices 1110.

Input/output device(s) 1110 for one embodiment may provide an interface for apparatus 1100 to communicate with any other suitable device, input/output device 1110 may include a communication component, an audio component, a sensor component, and the like.

The network interface 1112 of an embodiment may provide an interface for the device 1100 to communicate over one or more networks and/or with any other suitable device, and the device 1100 may communicate wirelessly with one or more components of a wireless network in accordance with any of one or more wireless network standards and/or protocols, such as accessing a wireless network based on a communication standard, such as WiFi,2G, or 3G, or a combination thereof.

For one embodiment, at least one of the processors 1102 may be packaged together with logic of one or more controllers (e.g., memory controllers) of the system control module 1104. For one embodiment, at least one of the processors 1102 may be packaged together with logic of one or more controllers of the system control module 1104 to form a System In Package (SiP). For one embodiment, at least one of the processors 1102 may be integrated on the same new product as the logic of one or more controllers of the system control module 1104. For one embodiment, at least one of the processors 1102 may be integrated on the same chip as logic of one or more controllers of the system control module 1104 to form a system on a chip (SoC).

In various embodiments, apparatus 1100 may include, but is not limited to: a desktop computing device or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet, a netbook, etc.), among others. In various embodiments, device 1100 may have more or fewer components and/or different architectures. For example, in some embodiments, the apparatus 1100 may include one or more cameras, keyboards, liquid Crystal Display (LCD) screens (including touch screen displays), non-volatile memory ports, multiple antennas, graphics chips, application Specific Integrated Circuits (ASICs), and speakers.

Wherein if the display comprises a touch panel, the display screen may be implemented as a touch screen display to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation.

The embodiment of the application also provides a non-volatile readable storage medium, where one or more modules (programs) are stored, where the one or more modules are applied to an apparatus, and the apparatus may be caused to execute instructions (instructions) of each method in the embodiment of the application.

In one example, an apparatus is provided, comprising: one or more processors; and instructions in one or more machine-readable media stored thereon, which when executed by the one or more processors, cause the apparatus to perform a method as in an embodiment of the present application, the method may comprise: the method shown in fig. 2 or fig. 3 or fig. 4 or fig. 5 or fig. 6 or fig. 7.

One or more machine-readable media are also provided in one example, having instructions stored thereon that, when executed by one or more processors, cause an apparatus to perform a method as in an embodiment of the present application, the method may comprise: the method shown in fig. 2 or fig. 3 or fig. 4 or fig. 5 or fig. 6 or fig. 7.

The foregoing has outlined a data processing method, a data processing device and a device in detail, wherein specific examples are provided herein to illustrate the principles and embodiments of the present application, and the above examples are only for the purpose of aiding in the understanding of the method and core ideas of the present application; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

Claims

1. A method of data processing, comprising:

transmitting the target information to the user;

the first acceptance characteristic is used for representing the acceptance degree of a user on a pushing mode, and is the ratio of the number of historical pushing information checked by the user to the number of the historical pushing information; or the first acceptability feature is the ratio of the contribution feature of the history push information to the number of the history push information; wherein the contribution characteristic is determined according to a second correlation characteristic between a user and the history push information;

the determining the target information corresponding to the user comprises the following steps:

and judging whether the first acceptability feature exceeds a first threshold value, if not, not sending target information to the user, and if so, determining target information corresponding to the user from the information according to the first relevant feature.

2. The method of claim 1, wherein the determining the target information corresponding to the user further comprises:

Determining the probability of the user to view the information according to the first correlation characteristic between the user and the information and the first acceptability characteristic of the pushing mode of the user to the information;

and determining target information corresponding to the user from the information according to the probability.

3. The method of claim 2, wherein the determining the probability that the user views the information comprises:

and determining the probability of the user viewing the information according to the first relevant feature, the first acceptability feature and the mapping relation among the relevant feature, the acceptability feature and the probability.

4. A method according to claim 3, characterized in that the mapping relationship is characterized by a model; the model includes a plurality of training samples, one of the training samples including: one history push information received by a user and feedback data of the user for the one history push information.

5. The method according to claim 4, wherein the method further comprises:

determining training characteristics corresponding to the training samples; the training features include: a second correlation characteristic between the user and one piece of history push information and a second acceptance characteristic of the push mode of the user for the information in a history time period corresponding to the one piece of history push information;

Training the training samples according to training characteristics corresponding to the training samples to obtain the model.

6. The method of claim 1, wherein the first correlation characteristic between the user and the information is obtained from a first attribute word corresponding to the user and a second attribute word corresponding to the information.

7. The method of claim 6, wherein the first attribute word corresponding to the user comprises:

The static attribute words of the user.

8. The method of claim 6, wherein the second attribute word comprises:

the attribute words of the commodities corresponding to the information; and/or

And extracting attribute words from the text corresponding to the information.

9. A method of data processing, comprising:

receiving first information;

if the judgment result is yes, displaying the first information;

The third acceptance characteristic is used for representing the acceptance degree of the user on the pushing mode, and is the ratio of the number of the historical pushing information checked by the user to the number of the historical pushing information; or the third acceptance characteristic is the ratio of the contribution characteristic of the history push information to the number of the history push information; wherein the contribution characteristic is determined according to a second correlation characteristic between a user and the history push information;

the judging whether to display the first information includes: judging whether the third acceptability feature exceeds a first threshold, and if not, not displaying the first information.

10. The method of claim 9, wherein the determining whether to present the first information comprises:

determining a first probability of the user viewing the first information according to a third correlation characteristic between the user and the first information and a third acceptability characteristic of the pushing mode of the user for the first information;

and judging whether to display the first information according to the first probability.

11. A data processing apparatus, comprising:

The target information pushing module is used for sending the target information to the user;

12. The apparatus of claim 11, wherein the target information determination module comprises:

13. A data processing apparatus, comprising:

the receiving module is used for receiving the first information;

the display module is used for displaying the first information under the condition that the judging result is yes;

14. The apparatus of claim 13, wherein the determining module comprises:

15. An apparatus, comprising:

one or more processors; and

one or more machine readable media having instructions stored thereon, which when executed by the one or more processors, cause the apparatus to perform the method of one or more of claims 1-8.

16. One or more machine readable media having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform the method of one or more of claims 1-8.

17. An apparatus, comprising:

one or more processors; and

one or more machine readable media having instructions stored thereon, which when executed by the one or more processors, cause the apparatus to perform the method of one or more of claims 9-10.

18. One or more machine readable media having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform the method of one or more of claims 9-10.