CN115018557A

CN115018557A - Data object processing method and device and server

Info

Publication number: CN115018557A
Application number: CN202210767802.XA
Authority: CN
Inventors: 吴庭玮; 朱道彬; 闫冬梅; 汪婕
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2022-07-01
Filing date: 2022-07-01
Publication date: 2022-09-06

Abstract

The specification provides a data object processing method, a data object processing device and a server. Based on the method, when detecting that the failure rate of the data object of the target user in the current time period is greater than or equal to a preset failure rate threshold value, the server can generate a first questionnaire aiming at the type preference of the data object of the target user; pushing a first questionnaire to the target user to obtain first text data fed back by the target user aiming at the first questionnaire; performing semantic recognition on the first text data to obtain a corresponding first semantic recognition result; screening out a target transaction characteristic type combination matched with the type preference of the current data object of the target user according to the first semantic recognition result; and determining a target data object matched with the target user from the plurality of data objects to be pushed according to the target transaction characteristic type combination of the target user, and pushing the target data object to the target user. Thereby, a better pushing effect can be obtained.

Description

Data object processing method and device and server

Technical Field

The specification belongs to the technical field of artificial intelligence, and particularly relates to a data object processing method, a data object processing device and a server.

Background

In some business scenarios, data objects related to business activities, such as coupons, are often required to be pushed to users, so as to promote related businesses and attract users to participate in business activities, thereby increasing the rate of successful business.

However, when the data objects are pushed to the users based on the existing method, different users are often not distinguished, the same data objects are pushed uniformly, and the pushing has no pertinence, so that the pushing effect is poor, and meanwhile, the interaction experience of the users is also influenced. For example, users are often pushed a large number of coupons for merchandise that the user does not have any interest in.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The specification provides a data object processing method, a data object processing device and a server, which can accurately determine a target data object suitable for a current target user so as to carry out targeted push on the target user, obtain a better push effect and effectively improve the interaction experience of the user.

The specification provides a data object processing method, which is applied to a server and comprises the following steps:

acquiring the failure rate of the data object of the target user in the current time period;

under the condition that the failure rate of the data object of the target user in the current time period is determined to be larger than or equal to a preset failure rate threshold value, generating a first questionnaire aiming at the type preference of the target user about the data object;

pushing a first questionnaire to a target terminal held by a target user, and receiving first text data fed back by the target user aiming at the first questionnaire;

calling a preset semantic recognition model to process the first text data to obtain a first semantic recognition result;

according to the first semantic recognition result, screening transaction characteristic types matched with the type preference of the current data object of the target user for combination to obtain a target transaction characteristic type combination for the target user;

determining a target data object matched with a target user from a plurality of data objects to be pushed according to the target transaction characteristic type combination of the target user;

and pushing the target data object to a target terminal.

In one embodiment, determining a target data object matched with a target user from a plurality of data objects to be pushed according to a target transaction feature type combination of the target user includes:

acquiring transaction behavior data of a target user in a current time period;

extracting a target transaction characteristic data combination of the target user in the current time period from the transaction behavior data of the target user in the current time period according to the target transaction characteristic category combination;

and determining a target data object matched with the target user from the plurality of data objects to be pushed according to the target transaction characteristic data combination of the target user in the current time period.

In one embodiment, determining a target data object matched with a target user from a plurality of data objects to be pushed according to a target transaction characteristic data combination of the target user in a current time period includes:

screening a target type preference prediction model matched with the target transaction characteristic type combination from a preset model set; the preset model set stores a plurality of preset type preference prediction models; the preset type preference prediction model corresponds to one or more transaction characteristic category combinations respectively;

calling a target type preference prediction model to process a target transaction characteristic data combination of a target user in the current time period so as to determine the current preference type of the target user;

and screening out data objects which accord with the current preference type of the target user from the plurality of data objects to be pushed as target data objects.

In one embodiment, after invoking the target type preference prediction model to process the target transaction characteristic data combination of the target user in the current time period to determine the current preference type of the target user, the method further comprises:

screening out a data object which is in accordance with the current preference type of a target user from a plurality of data objects to be pushed to serve as a target test object;

and pushing the target test object to the target user according to the first pushing rule.

In one embodiment, after pushing the target test object to the target user according to the first pushing rule, the method further comprises:

acquiring operation data of a target user for a target test object;

determining a pushing effect parameter of a target test object according to the operation data of the target user aiming at the target test object;

and determining whether the first pushing rule is matched with the target user or not according to the pushing effect parameter of the target test object.

In one embodiment, in the case that it is determined that the first push rule does not match the target user, the method further comprises:

generating a second questionnaire regarding push rule preferences of the data object for the target user;

pushing a second questionnaire to the target user, and receiving second text data fed back by the target user aiming at the second questionnaire;

calling a preset semantic recognition model to process the second text data to obtain a second semantic recognition result;

and determining a target pushing rule matched with the target user from a plurality of preset pushing rules according to the second semantic recognition result.

In one embodiment, determining a target push rule matching the target user from a plurality of preset push rules according to the second semantic recognition result includes:

combining the second semantic recognition result and the target transaction characteristic data to obtain combined data;

and according to the combined data, determining a target pushing rule matched with the target user from a plurality of preset pushing rules.

In one embodiment, pushing the target data object to a target user includes:

and pushing the target data object to a target user in a corresponding pushing mode according to the target pushing rule.

In one embodiment, the data object comprises a coupon.

In one embodiment, after pushing the target data object to a target user, the method further comprises:

adding a state record related to the target data object in a target push record table; recording the valid period information of the target data object; the target push record table corresponds to a user identifier of a target user;

correspondingly, the method further comprises the following steps:

receiving a transaction data processing request sent by a target user through a target terminal;

detecting whether the transaction data processing request carries a data object;

and under the condition that the transaction data processing request is determined to carry the data object, updating a state record related to the data object in the target push record table.

The present specification also provides a data object processing method, which is applied to a target terminal held by a target user, and the method includes:

receiving a first questionnaire which is pushed by a server and aims at the type preference of a target user on a data object; and presenting the first questionnaire to the target user;

acquiring first text data fed back by a target user aiming at a first questionnaire; sending the first text data to a server; the server screens out transaction characteristic types matched with the type preference of the current data object of the target user according to the first text data and combines the transaction characteristic types to obtain a target transaction characteristic type combination for the target user; the server also determines a target data object matched with the target user from the data objects to be pushed according to the target transaction characteristic type combination of the target user;

receiving a target data object pushed by a server; and presenting the target data object to the target user.

The present specification also provides a data object processing apparatus, applied to a server, including:

the acquisition module is used for acquiring the failure rate of the data object in the current time period of the target user;

the generating module is used for generating a first questionnaire aiming at type preference of the data object of the target user under the condition that the failure rate of the data object of the target user in the current time period is determined to be greater than or equal to a preset failure rate threshold value;

the first processing module is used for pushing a first questionnaire to a target terminal held by a target user and receiving first text data fed back by the target user aiming at the first questionnaire;

the second processing module is used for calling a preset semantic recognition model to process the first text data to obtain a first semantic recognition result;

the third processing module is used for screening out transaction characteristic types matched with the type preference of the current data object of the target user according to the first semantic recognition result and combining the transaction characteristic types to obtain a target transaction characteristic type combination for the target user;

the determining module is used for determining a target data object matched with the target user from the data objects to be pushed according to the target transaction characteristic type combination of the target user;

and the pushing module is used for pushing the target data object to a target terminal.

This specification also provides a data object processing apparatus, which is applied to a target terminal held by a target user, and includes:

the receiving module is used for receiving a first questionnaire which is pushed by the server and aims at the type preference of the target user and is about the data object; and presenting the first questionnaire to the target user;

the sending module is used for acquiring first text data fed back by a target user aiming at the first questionnaire; sending the first text data to a server; the server screens out transaction characteristic types matched with the type preference of the current data object of the target user according to the first text data and combines the transaction characteristic types to obtain a target transaction characteristic type combination for the target user; the server also determines a target data object matched with the target user from the data objects to be pushed according to the target transaction characteristic type combination of the target user;

the display module is used for receiving the target data object pushed by the server; and presenting the target data object to the target user.

The present specification also provides a server comprising a processor and a memory for storing processor-executable instructions that, when executed by the processor, implement the steps associated with the method of processing the data object.

The present specification also provides a computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the relevant steps of the method of processing the data object.

Based on the data object processing method, the data object processing device and the server provided by the specification, when the server detects that the failure rate of the data object of the target user in the current time period is greater than or equal to a preset failure rate threshold value, a first questionnaire about type preference of the data object for the target user can be generated firstly; pushing a first questionnaire to the target user to acquire first text data fed back by the target user aiming at the first questionnaire; performing semantic recognition on the first text data to obtain a corresponding first semantic recognition result; screening out a target transaction characteristic type combination matched with the type preference of the current data object of the target user according to the first semantic recognition result; and determining a target data object matched with the target user from the plurality of data objects to be pushed according to the target transaction characteristic type combination of the target user, and pushing the target data object to the target user. Therefore, the target data object suitable for the current target user can be accurately determined, the target user can be pushed in a targeted manner, a good pushing effect is obtained, and meanwhile, the interaction experience of the user can be effectively improved.

Drawings

In order to more clearly illustrate the embodiments of the present description, the drawings needed for the embodiments will be briefly described below, the drawings in the following description are only some of the embodiments described in the present description, and other drawings may be obtained by those skilled in the art without inventive efforts.

FIG. 1 is a flow diagram illustrating a method for processing data objects according to one embodiment of the present disclosure;

FIG. 2 is a diagram illustrating an embodiment of a method for processing a data object according to an embodiment of the present disclosure;

FIG. 3 is a diagram illustrating an embodiment of a method for processing a data object according to an embodiment of the present disclosure;

FIG. 4 is a diagram illustrating an embodiment of a method for processing a data object according to an embodiment of the present disclosure;

FIG. 5 is a flow chart illustrating a method for processing data objects according to another embodiment of the present disclosure;

FIG. 6 is a schematic structural component diagram of a server provided in an embodiment of the present description;

FIG. 7 is a schematic diagram illustrating an exemplary architecture of a device for processing data objects according to an embodiment of the present disclosure;

fig. 8 is a schematic structural component diagram of a data object processing apparatus according to another embodiment of the present specification.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step should fall within the scope of protection of the present specification.

Referring to fig. 1, an embodiment of the present disclosure provides a method for processing a data object. The method is particularly applied to the server side. In specific implementation, the method may include the following:

s101: acquiring the failure rate of the data object of the target user in the current time period;

s102: under the condition that the failure rate of the data object of the target user in the current time period is determined to be larger than or equal to a preset failure rate threshold value, generating a first questionnaire aiming at the type preference of the target user about the data object;

s103: pushing a first questionnaire to a target terminal held by a target user, and receiving first text data fed back by the target user aiming at the first questionnaire;

s104: calling a preset semantic recognition model to process the first text data to obtain a first semantic recognition result;

s105: screening out transaction characteristic types matched with the type preference of the current data object of the target user according to the first semantic recognition result, and combining the transaction characteristic types to obtain a target transaction characteristic type combination for the target user;

s106: determining a target data object matched with a target user from a plurality of data objects to be pushed according to the target transaction characteristic type combination of the target user;

s107: and pushing the target data object to a target terminal.

Based on the above embodiment, when detecting that the failure rate of the data object pushed to the target user in the current time period is high and the pushing effect is poor, the server may first automatically trigger to generate a first questionnaire about the type preference of the data object for the target user; pushing the first questionnaire to the target user to acquire first text data fed back by the target user; then according to the first text data, re-screening and combining target transaction characteristic category combinations which are used for predicting data objects which are suitable for predicting the current target users to be interested in; and then, according to the target transaction characteristic type combination, determining a target data object matched with the current target user to push the target user. Therefore, the determined target data object to be pushed to the target user is more targeted, the target user can be attracted better, and a relatively good pushing effect is obtained; meanwhile, the phenomenon that the user feels disliked due to the fact that the data object which is not interested by the target user is pushed blindly can be avoided, and the user can obtain better interactive experience.

In some embodiments, referring to fig. 2, the above-mentioned data object processing method may be specifically applied to the server side.

The server may specifically include a background server applied to a side of a network transaction platform (e.g., an XX electronic shopping website, etc.), and capable of implementing functions such as data transmission and data processing. Specifically, the server may be, for example, an electronic device having data operation, storage functions, and network interaction functions. Alternatively, the server may be a software program running in the electronic device and providing support for data processing, storage and network interaction. In the present embodiment, the number of servers is not particularly limited. The server may specifically be one server, or may also be several servers, or a server cluster formed by several servers.

Under normal conditions, in the current time period, the server can determine a data object suitable for the target user according to the existing strategy and push the data object to the target user.

Meanwhile, the server may also apply the data object processing method provided in this specification to periodically detect whether the failure rate of the data object pushed to the target user in a period of time is greater than or equal to a preset failure rate threshold.

Specifically, when detecting that the failure rate of the data object in the current time period of the target user is greater than or equal to a preset failure rate threshold value, the server may determine that the pushing effect of the data object pushed to the target user based on the existing policy in the current time period is poor, and at this time, may trigger to construct a new policy for the current target user; then based on the new strategy, the target data object suitable for the target user is determined again; the target data object may then be pushed to the target user based on the new policy.

Specifically, when a new strategy for a current target user is constructed, a server generates a first questionnaire about type preference of a data object for the target user; and then the first questionnaire is sent to the target terminal.

The target terminal may present the first questionnaire to the target user, and collect first text data provided when the target user replies to the first questionnaire. The target terminal may transmit the first text data to the server.

Then, the server can obtain a corresponding first semantic recognition result through semantic recognition according to the first text data; then, according to the first semantic recognition result, recombining to generate a target transaction characteristic type combination suitable for the current target user; determining a target data object matched with the current target user from a plurality of data objects to be pushed according to the target transaction characteristic type combination; and pushing the target data object to the target terminal.

And the target terminal displays the target data object to a target user.

Because the type of the target data object displayed by the target terminal is in accordance with the type preference of the current data object of the target user, the target user is more likely to generate interest in the pushed target data object and is also more likely to trigger or target the data object, thereby obtaining better pushing effect.

The target terminal may specifically include a front-end device that is applied to a target user side and can implement functions such as data acquisition and data transmission. Specifically, the target terminal may be, for example, an electronic device such as a desktop computer, a tablet computer, a notebook computer, and a mobile phone. Alternatively, the target terminal may be a software application capable of running in the electronic device. For example, it may be XX electronic shopping website APP running on mobile phone.

In some embodiments, the data object may be a coupon. Of course, the above list of coupons is only illustrative. In specific implementation, according to a specific service scenario and a processing requirement, the data object may further include other data objects that need to be pushed, such as introduction information of a commodity, a promotion link of a new service, and the like.

Based on the above embodiments, the processing method of the data object provided in the embodiments of the present specification may be applied to push various data objects such as coupons, so as to meet diversified business scene requirements.

In some embodiments, a target push record corresponding to the user identifier of the target user may be specifically configured on the server side. The target push record may specifically include a status record of a data object pushed to the target user, and push time, validity period information, and other related information of the data object.

The user identifier of the target user may be specifically understood as identification information that can be used to indicate the target user. Specifically, for example, the user name, the user number, the registered mobile phone number, and the like of the target user are provided.

Of course, it should be noted that the user id of the target user listed above is only an exemplary illustration. In specific implementation, the user identifier of the target user may further include other suitable identification information according to specific situations and processing requirements. The present specification is not limited to these.

It should be noted that, in this specification, the information data related to the user is obtained and used on the premise that the user knows and agrees. Moreover, the acquisition, storage, use, processing and the like of the information data all conform to relevant regulations of national laws and regulations.

In specific implementation, each time the server pushes a data object to the target user, a state record about the data object may be added to the target push record table. Specifically, the status field in the status record of the data object may also be set to "pushed". At the same time, the push time (e.g., 2022.05.01) of the data object, as well as expiration information (e.g., 30 days) may also be recorded in the target push record table.

Meanwhile, the server can judge whether the target user uses the data object by detecting whether the transaction data carries the data object according to the transaction data initiated by the target user.

Specifically, when the server detects that one transaction data initiated by the target user carries one pushed data object, the server may update a state record of the data object in the target push record. For example, the status field in the status record for the data object may be modified to "used".

In addition, the server can also detect a target pushing record table regularly, and determine whether the data object fails due to the fact that the user does not use the data object after exceeding the validity period according to the pushing time, the validity period information and the state record of the data object. Upon detecting a failure of a data object, the server may modify a status field in a status record of the data object to "failed".

In some embodiments, in specific implementation, the server may count, according to the target push record table, a ratio of a number of data objects whose status fields in the status record are "invalidated" to a total number of data objects in the current time period, as a failure rate of the data objects in the current time period.

Then, the server may compare the failure rate of the data object of the target user in the current time period with a preset failure rate threshold, and when it is determined that the failure rate of the data object of the target user in the current time period is greater than or equal to the preset failure rate threshold, it may be determined that the existing policy is no longer suitable for the current target user, and a new policy for the current target user needs to be determined. The preset failure rate threshold value can be flexibly set according to specific conditions and pushing requirements.

In some embodiments, referring to fig. 3, the generating of the first questionnaire regarding the type preference of the promotion data for the target user may be implemented by the following steps:

s1: acquiring attribute data of a target user and transaction behavior data of a current time period;

s2: and screening matched problems from a preset first-class question bank and combining the problems according to the attribute data of the target user and the transaction behavior data of the current time period to obtain a first questionnaire.

The attribute data of the target user may specifically include at least one of the following: age of the target user, occupation of the target user, gender of the target user, member information of the target user, and the like.

The transaction behavior data of the target user may specifically include at least one of the following: an online transaction record for the target user, an offline transaction record for the target user, a transfer record for the target user, and so forth.

In specific implementation, the attribute data of the target user can be obtained by searching the user database of the target user in the system; and acquiring the transaction behavior data of the current time period by inquiring the historical transaction record of the current time period of the target user.

The preset first question bank may specifically store a plurality of preset questions for directly or indirectly reflecting the user's preference of the type of the data object.

In some embodiments, the server may push the first questionnaire to the target terminal. Correspondingly, the target terminal receives and displays the first questionnaire to the target user; at the same time, the target user may also be prompted to reply to the first questionnaire.

The target terminal can collect information input by the target user when the target user answers the first questionnaire, and generate first text data for the first questionnaire according to the information.

Based on the above embodiment, the server may automatically generate the first questionnaire for the target user, which is capable of accurately surveying the first questionnaire reflecting the type preference of the target user for the data object.

In some embodiments, the preset semantic recognition model may be specifically understood as a model capable of predicting habit preferences of a user through semantic recognition and logical inference based on input text data.

The habit preferences may specifically include one or more of the following: preference of habit to the type of goods (for example, habit like buying snacks, habit like buying cosmetics, etc.), preference of habit to coupon preferential rules (for example, habit like coupon rule full of a specified amount of money for rebate coupon, or habit like coupon rule free of the last good after reaching a specified number of pieces, etc.), preference of habit to the channel of realization of the preferential event (for example, habit like coupon of online channel, or habit like coupon of offline channel, etc.), preference of habit to the payment channel (for example, habit like bank card payment, or habit like electronic account transfer payment, etc.), and the like.

Of course, it should be noted that the above listed preference is only an exemplary illustration. In specific implementation, the habit preferences may also include other suitable habit preferences related to transaction behaviors according to specific application scenarios and processing requirements. The present specification is not limited to these.

Specifically, the preset semantic recognition model may be obtained as follows: constructing an initial model by using NLP (Natural Language Processing) technology; and obtaining and training the initial model by using the first sample text data of the sample user aiming at the first questionnaire to obtain the preset semantic recognition model.

In some embodiments, referring to fig. 3, in a specific implementation, the server may screen out, according to the first semantic recognition result, a transaction feature type related to the current habit preference of the target user from a preset transaction feature type set, and combine the transaction feature type as a transaction feature type matched with the type preference of the current data object of the target user to obtain a target transaction feature type combination for the current target user.

The preset transaction characteristic type set comprises a plurality of preset transaction characteristic types. The plurality of preset transaction characteristic types included in the preset transaction characteristic type set may be specifically types of transaction characteristics that are selected by sorting and learning a large amount of historical transaction data and historical pushing records in advance and that may affect the pushing effect of the data object.

In some embodiments, referring to fig. 3, when the target data object matching the target user is determined from the multiple data objects to be pushed according to the target transaction feature category combination of the target user, the specific implementation may include the following:

s1: acquiring transaction behavior data of a target user in a current time period;

s2: extracting a target transaction characteristic data combination of the target user in the current time period from the transaction behavior data of the target user in the current time period according to the target transaction characteristic category combination;

s3: and determining a target data object matched with the target user from the plurality of data objects to be pushed according to the target transaction characteristic data combination of the target user in the current time period.

Based on the embodiment, the server can perform characteristic processing such as characteristic engineering on the transaction behavior data of the target user in the current time period in a targeted manner according to the target transaction characteristic type combination so as to accurately extract and obtain the required effective transaction characteristic data of the target user in the current time period for combination, thereby obtaining the target transaction characteristic data combination with better effect and stronger pertinence; and further, the target data object matched with the target user can be accurately determined according to the target transaction characteristic data combination. On one hand, the extraction and the use of the full amount of transaction characteristic data can be avoided, the data processing amount is effectively reduced, and the overall processing efficiency is improved; on the other hand, covering and misleading of effective transaction characteristic data caused by using other invalid transaction characteristic data can be avoided, and therefore the target data object matched with the target user can be determined more accurately.

The transaction characteristic data may specifically include at least one of the following: a trade time characteristic, a trade object characteristic, a trade resource value characteristic, a trade channel characteristic, a trade location characteristic, and the like. Of course, the above listed transaction characteristic data is only an illustrative illustration. In particular implementations, other types of transaction features may also be included, depending on the particular transaction scenario. The present specification is not limited to these.

In some embodiments, the determining, according to the target transaction characteristic data combination of the target user in the current time period, a target data object matched with the target user from the plurality of data objects to be pushed may include the following steps:

s1: screening a target type preference prediction model matched with the target transaction characteristic type combination from a preset model set; the preset model set stores a plurality of preset type preference prediction models; the preset type preference prediction model corresponds to one or more transaction characteristic category combinations respectively;

s2: calling a target type preference prediction model to process a target transaction characteristic data combination of a target user in the current time period so as to determine the current preference type of the target user;

s3: and screening out data objects which accord with the current preference type of the target user from the plurality of data objects to be pushed as target data objects.

Based on the embodiment, the data objects which accord with the current preference type of the target user (namely are suitable for the current target user) can be efficiently and accurately screened from the plurality of data objects to be pushed by utilizing the combination of the target transaction characteristic types, and the data objects are used as the target data objects to be pushed to the target user.

In some embodiments, before the specific implementation, the server may train to obtain a plurality of preset type preference prediction models corresponding to a plurality of transaction feature type combinations by using the sample data, so as to construct and obtain the preset model set.

The preset type preference prediction model can output the type of the corresponding data object as the preference type of the user based on the input transaction characteristic data combination corresponding to the model. The preference types may correspond to one or more types of data objects.

In some embodiments, after invoking the target-type preference prediction model to process the target transaction characteristic data combination of the target user in the current time period to determine the current preference type of the target user, the method may further include, when implemented, the following:

s1: screening out a data object which is in accordance with the current preference type of a target user from a plurality of data objects to be pushed to serve as a target test object;

s2: and pushing the target test object to the target user according to the first pushing rule.

Based on the embodiment, a corresponding target test object can be determined according to the current preference type of the target user; and further testing whether the target user is matched with the current pushing rule by using the target test object.

The first push rule may be a default push rule, or may be a push rule for a target user based on an existing policy.

In some embodiments, after the target test object is pushed to the target user according to the first pushing rule, when the method is implemented, the following may be further included:

s1: acquiring operation data of a target user aiming at a target test object;

s2: determining a pushing effect parameter of a target test object according to the operation data of the target user aiming at the target test object;

s3: and determining whether the first pushing rule is matched with the target user or not according to the pushing effect parameter of the target test object.

Based on the embodiment, the target user can be tested by using the target test object which accords with the current preference type of the target user, so that the influence of the preference type of the data object on the operation of the target user is eliminated, and whether the currently used first push rule is matched with the target user or not and is suitable for the current target user or not is accurately judged.

The operation data may be specifically understood as an operation of a target user for a target test object, and specifically may include: positive operations (e.g., operations to accept a target test object, operations to use a target test object, etc.) and negative operations (e.g., operations to ignore a target test object, operations to delete a target test object, etc.).

The server can acquire the operation data of a target user aiming at a target test object through the target terminal; and determining the pushing effect parameter of the target test object according to the operation data.

Specifically, the server may count whether a ratio of the number of positive operations to the number of negative operations is greater than a specified ratio. And under the condition that the ratio is determined to be larger than the specified ratio, judging that the first pushing rule is matched with the target user, and then subsequently, continuing to push the data object to the target user according to the first pushing rule. On the contrary, when the ratio is determined to be less than or equal to the specified ratio, it may be determined that the first push rule is not matched with the target user, and then a new push rule that is determined to be suitable for the current target user may be triggered.

In some embodiments, in the case that it is determined that the first push rule does not match the target user, referring to fig. 4, when the method is implemented, the following may be further included:

s1: generating a second questionnaire regarding push rule preferences for the data object for the target user;

s2: pushing a second questionnaire to the target user, and receiving second text data fed back by the target user aiming at the second questionnaire;

s3: calling a preset semantic recognition model to process the second text data to obtain a second semantic recognition result;

s4: and determining a target pushing rule matched with the target user from a plurality of preset pushing rules according to the second semantic recognition result.

Based on the embodiment, the target push rule suitable for the current target user can be accurately determined by pushing the second questionnaire about the push rule preference of the data object to the target user to acquire and according to the second text data fed back by the target user.

In some embodiments, the preset push rules may be obtained by clustering a large number of push records in advance. The preset push rules may specifically include one or more of the following: the push time rule of the data object, the push channel rule of the data object, the push mode rule of the data object, the push trigger place rule of the data object, and the like.

In some embodiments, when the second questionnaire is specifically generated, matched questions may be screened from a preset second-type question bank and combined according to attribute data of the target user and transaction behavior data of the current time period, so as to obtain the second questionnaire. The preset second-type question bank may specifically store a plurality of preset questions for directly or indirectly reflecting the push rule preference of the user with respect to the data object.

In some embodiments, the server may push and present the second questionnaire to the target user through the target terminal. Further, the server may obtain, through the target terminal, second text data fed back by the target user for the second questionnaire. Then, the server can call a preset semantic recognition model to obtain a corresponding second semantic recognition result by processing the second text data.

In some embodiments, the determining, according to the second semantic recognition result, a target push rule matching the target user from a plurality of preset push rules may include, in specific implementation, the following: combining the second semantic recognition result and the target transaction characteristic data to obtain combined data; and according to the combined data, determining a target pushing rule matched with the target user from a plurality of preset pushing rules.

Based on the above embodiment, the data of two different dimensions, namely the second semantic recognition result obtained by recognition based on the second questionnaire and the target transaction characteristic data combination obtained by extracting the transaction behavior data based on the current time period of the target user, can be simultaneously utilized to accurately determine the preset push rule matched with the current target user from the multiple preset push rules as the target push rule.

In some embodiments, the pushing the target data object to the target user may include, in specific implementation: and pushing the target data object to a target user in a corresponding pushing mode according to the target pushing rule.

Based on the embodiment, the target data object which meets the current preference of the target user can be screened out firstly; and then, the target data object is pushed to the target user in a proper pushing mode by a target pushing rule according with the current preference of the target user, so that the target user is more willing to accept and use the target data object, relatively better interactive experience is obtained, and relatively better pushing effect is obtained.

In some embodiments, after the target data object is pushed to the target user, when the method is implemented, the following may be further included: adding a state record related to the target data object in the target push record table; recording the valid period information of the target data object; and the target push record table corresponds to the user identification of the target user.

Correspondingly, when the method is implemented, the following contents can be included:

s1: receiving a transaction data processing request sent by a target user through a target terminal;

s2: detecting whether the transaction data processing request carries a data object;

s3: and under the condition that the transaction data processing request is determined to carry the data object, updating a state record related to the data object in the target push record table.

Based on the embodiment, the server can accurately and timely record and update the state of the data object, so that whether the existing strategy is suitable for the current user or not can be detected and judged in real time or regularly by inquiring the push record table of the user, acquiring the failure rate of the data object in the current time period of the user, and whether the transaction feature type combination and the push rule for predicting the data object need to be determined again for the current user or not can be detected and judged.

In some embodiments, when the target terminal performs specific transaction data processing in response to a target user operation, it may first detect whether an associated data object related to the transaction data exists in data objects currently received by the target terminal. For example, it is checked whether there is a coupon that matches a certain item in the current trade order.

Under the condition that the associated data object is detected to exist, the target terminal can automatically use the associated data object to complete data processing at the target terminal side, and a transaction data processing request at least carrying the data object is obtained; and then the transaction data processing request is sent to a server.

In addition, when detecting that the associated data object exists, the target terminal may also present the associated data object to the target user and ask for prompt information about whether to use the associated data object. And after receiving the instruction for confirming the use of the associated data object initiated by the target user, the target terminal uses the associated data object to complete the data processing at the target terminal side, and obtains a transaction data processing request at least carrying the data object.

After receiving the transaction data processing request, the server may complete corresponding transaction data processing using the data object. For example, the server may complete the underwriting process of the transaction order using the coupon carried in the transaction data processing request.

As can be seen from the above, based on the method for processing a data object provided in the embodiment of the present specification, when detecting that the failure rate of the data object in the current time period of the target user is greater than or equal to the preset failure rate threshold, the server may first generate a first questionnaire about type preference of the data object for the target user; pushing a first questionnaire to the target user to obtain first text data fed back by the target user aiming at the first questionnaire; performing semantic recognition on the first text data to obtain a corresponding first semantic recognition result; screening out a target transaction characteristic type combination matched with the type preference of the current data object of the target user according to the first semantic recognition result; and determining a target data object matched with the target user from the plurality of data objects to be pushed according to the target transaction characteristic type combination of the target user so as to push the target data object to the target user. Therefore, the target data object suitable for the current target user can be accurately determined, the target user can be pushed in a targeted manner, a good pushing effect is obtained, and meanwhile, the interaction experience of the user can be effectively improved.

Referring to fig. 5, an embodiment of the present specification further provides a method for processing a data object. The method is applied to a target terminal side held by a target user, and when the method is implemented, the method can include the following contents:

s501: receiving a first questionnaire which is pushed by a server and aims at the type preference of a target user on a data object; and presenting the first questionnaire to the target user;

s502: acquiring first text data fed back by a target user aiming at a first questionnaire; sending the first text data to a server; the server screens out transaction characteristic types matched with the type preference of the current data object of the target user according to the first text data and combines the transaction characteristic types to obtain a target transaction characteristic type combination for the target user; the server also determines a target data object matched with the target user from the data objects to be pushed according to the target transaction characteristic type combination of the target user;

s503: receiving a target data object pushed by a server; and presenting the target data object to the target user.

In some embodiments, after presenting the target data object to the target user, when the method is implemented, the method may further include: and receiving and responding to the operation data of the target user aiming at the target data object, and carrying out corresponding processing on the target data object.

Specifically, the operation data includes at least one of: accept operations, ignore operations, delete operations, and the like.

Correspondingly, the target terminal may respond to the operation data to perform one of the following processes on the target data object: receiving and storing the target data object; not accepting the target data object; delete the received target data object, and so on.

In some embodiments, after presenting the target data object to the target user, when the method is implemented, the method may further include: receiving and responding to the transaction operation initiated by the target user, and processing the transaction data at the terminal side; detecting whether a target terminal stores a data object related to current transaction data processing or not in the process of processing the transaction data of the terminal; under the condition that the data object related to the current transaction data processing is determined to be stored, automatically using the data object to perform transaction data processing so as to obtain a transaction data processing request at least carrying the data object; and sends the transaction data processing request to a server for further processing.

As can be seen from the above, based on the data object processing method provided in the embodiments of the present specification, a target user may interact with a server through a held target terminal, and the server may accurately determine a target data object suitable for the current target user and push the target user with a targeted data object; meanwhile, the target terminal can also receive and display the target data object which is currently interested by the target user, so that the target user can obtain better interactive experience.

Embodiments of the present specification further provide a server, including a processor and a memory for storing processor-executable instructions, where the processor, when implemented, may perform the following steps according to the instructions: acquiring the failure rate of the data object of the target user in the current time period; under the condition that the failure rate of the data object of the target user in the current time period is determined to be larger than or equal to a preset failure rate threshold value, generating a first questionnaire aiming at the type preference of the target user on the data object; pushing a first questionnaire to a target terminal held by a target user, and receiving first text data fed back by the target user aiming at the first questionnaire; calling a preset semantic recognition model to process the first text data to obtain a first semantic recognition result; screening out transaction characteristic types matched with the type preference of the current data object of the target user according to the first semantic recognition result, and combining the transaction characteristic types to obtain a target transaction characteristic type combination for the target user; determining a target data object matched with a target user from a plurality of data objects to be pushed according to the target transaction characteristic type combination of the target user; and pushing the target data object to a target terminal.

In order to more accurately complete the above instructions, referring to fig. 6, another specific server is provided in the embodiments of the present specification, where the server includes a network communication port 601, a processor 602, and a memory 603, and the above structures are connected by an internal cable, so that the structures may perform specific data interaction.

The network communication port 601 may be specifically configured to acquire failure rate of a data object of a target user in a current time period.

The processor 602 may be specifically configured to generate a first questionnaire regarding type preferences of the data object for the target user when it is determined that a failure rate of the data object for the target user in the current time period is greater than or equal to a preset failure rate threshold; pushing a first questionnaire to a target terminal held by a target user, and receiving first text data fed back by the target user aiming at the first questionnaire; calling a preset semantic recognition model to process the first text data to obtain a first semantic recognition result; according to the first semantic recognition result, screening transaction characteristic types matched with the type preference of the current data object of the target user for combination to obtain a target transaction characteristic type combination for the target user; determining a target data object matched with a target user from a plurality of data objects to be pushed according to the target transaction characteristic type combination of the target user; and pushing the target data object to a target terminal.

The memory 603 may be specifically configured to store a corresponding instruction program.

In this embodiment, the network communication port 601 may be a virtual port bound with different communication protocols, so that different data can be sent or received. For example, the network communication port may be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for mail data communication. In addition, the network communication port can also be a communication interface or a communication chip of an entity. For example, it may be a wireless mobile network communication chip, such as GSM, CDMA, etc.; it can also be a Wifi chip; it may also be a bluetooth chip.

In this embodiment, the processor 602 may be implemented in any suitable manner. For example, the processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, an embedded microcontroller, and so forth. The description is not intended to be limiting.

In this embodiment, the memory 603 may include multiple layers, and in a digital system, the memory may be any memory as long as binary data can be stored; in an integrated circuit, a circuit without a physical form and with a storage function is also called a memory, such as a RAM, a FIFO and the like; in the system, the storage device in physical form is also called a memory, such as a memory bank, a TF card and the like.

An embodiment of the present specification further provides a target terminal, including a processor and a memory for storing processor-executable instructions, where the processor, when implemented specifically, may perform the following steps according to the instructions: receiving a first questionnaire which is pushed by a server and aims at the type preference of a target user on a data object; and presenting the first questionnaire to the target user; acquiring first text data fed back by a target user aiming at a first questionnaire; sending the first text data to a server; the server screens out transaction characteristic types matched with the type preference of the current data object of the target user according to the first text data and combines the transaction characteristic types to obtain a target transaction characteristic type combination for the target user; the server also determines a target data object matched with the target user from the data objects to be pushed according to the target transaction characteristic type combination of the target user; receiving a target data object pushed by a server; and presenting the target data object to the target user.

The embodiments of the present specification further provide a computer storage medium based on the above data object processing method, where the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the computer program instructions implement: acquiring the failure rate of the data object of the target user in the current time period; under the condition that the failure rate of the data object of the target user in the current time period is determined to be larger than or equal to a preset failure rate threshold value, generating a first questionnaire aiming at the type preference of the target user about the data object; pushing a first questionnaire to a target terminal held by a target user, and receiving first text data fed back by the target user aiming at the first questionnaire; calling a preset semantic recognition model to process the first text data to obtain a first semantic recognition result; according to the first semantic recognition result, screening transaction characteristic types matched with the type preference of the current data object of the target user for combination to obtain a target transaction characteristic type combination for the target user; determining a target data object matched with a target user from a plurality of data objects to be pushed according to the target transaction characteristic type combination of the target user; and pushing the target data object to a target terminal.

The present specification further provides another computer storage medium based on the above data object processing method, where the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the computer storage medium implements: receiving a first questionnaire which is pushed by a server and aims at the type preference of a target user on a data object; and presenting the first questionnaire to the target user; acquiring first text data fed back by a target user aiming at a first questionnaire; sending the first text data to a server; the server screens out transaction characteristic types matched with the type preference of the current data object of the target user according to the first text data and combines the transaction characteristic types to obtain a target transaction characteristic type combination for the target user; the server also determines a target data object matched with the target user from the data objects to be pushed according to the target transaction characteristic type combination of the target user; receiving a target data object pushed by a server; and presenting the target data object to the target user.

In this embodiment, the storage medium includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Cache (Cache), a Hard Disk Drive (HDD), or a Memory Card (Memory Card). The memory may be used to store computer program instructions. The network communication unit may be an interface for performing network connection communication, which is set in accordance with a standard prescribed by a communication protocol.

In this embodiment, the functions and effects specifically realized by the program instructions stored in the computer storage medium can be explained by comparing with other embodiments, and are not described herein again.

Referring to fig. 7, in a software level, an embodiment of the present specification further provides a data object processing apparatus, which may specifically include the following structural modules:

the obtaining module 701 may be specifically configured to obtain a failure rate of a data object of a target user in a current time period;

the generating module 702 may be specifically configured to generate a first questionnaire regarding type preferences of the data object for the target user when it is determined that the failure rate of the data object of the target user in the current time period is greater than or equal to a preset failure rate threshold;

the first processing module 703 may be specifically configured to push a first questionnaire to a target terminal held by a target user, and receive first text data fed back by the target user for the first questionnaire;

the second processing module 704 may be specifically configured to invoke a preset semantic recognition model to process the first text data, so as to obtain a first semantic recognition result;

the third processing module 705 may be specifically configured to screen out, according to the first semantic identification result, a transaction feature type that matches with the type preference of the current data object of the target user, and combine the transaction feature types to obtain a target transaction feature type combination for the target user;

the determining module 706 is specifically configured to determine, according to the target transaction feature type combination of the target user, a target data object matched with the target user from the multiple data objects to be pushed;

the pushing module 707 may be specifically configured to push the target data object to a target terminal.

In some embodiments, when the determining module 706 is implemented, the target data object matching the target user may be determined from the data objects to be pushed according to the target transaction feature type combination of the target user in the following manner: acquiring transaction behavior data of a target user in a current time period; extracting a target transaction characteristic data combination of the target user in the current time period from the transaction behavior data of the target user in the current time period according to the target transaction characteristic category combination; and determining a target data object matched with the target user from the plurality of data objects to be pushed according to the target transaction characteristic data combination of the target user in the current time period.

In some embodiments, when the determining module 706 is implemented, a target data object matching the target user may be determined from the plurality of data objects to be pushed according to the target transaction feature data combination of the target user in the current time period in the following manner: screening a target type preference prediction model matched with the target transaction characteristic type combination from a preset model set; the preset model set stores a plurality of preset type preference prediction models; the preset type preference prediction model corresponds to one or more transaction characteristic category combinations respectively; calling a target type preference prediction model to process a target transaction characteristic data combination of a target user in the current time period so as to determine the current preference type of the target user; and screening out data objects which accord with the current preference type of the target user from the plurality of data objects to be pushed as target data objects.

In some embodiments, after the target transaction characteristic data combination of the target user in the current time period is processed by calling the target type preference prediction model to determine the current preference type of the target user, the device may be further configured to screen a data object conforming to the current preference type of the target user from a plurality of data objects to be pushed to serve as a target test object when being implemented specifically; and pushing the target test object to the target user according to the first pushing rule.

In some embodiments, after the target test object is pushed to the target user according to the first pushing rule, the apparatus may be further configured to obtain operation data of the target user for the target test object when being implemented specifically; determining a pushing effect parameter of a target test object according to the operation data of the target user aiming at the target test object; and determining whether the first pushing rule is matched with the target user or not according to the pushing effect parameter of the target test object.

In some embodiments, where it is determined that the first push rule does not match the target user, the apparatus, when embodied, may be further configured to generate a second questionnaire regarding push rule preferences of the data object for the target user; pushing a second questionnaire to the target user, and receiving second text data fed back by the target user aiming at the second questionnaire; calling a preset semantic recognition model to process the second text data to obtain a second semantic recognition result; and determining a target pushing rule matched with the target user from a plurality of preset pushing rules according to the second semantic recognition result.

In some embodiments, when the apparatus is implemented, a target push rule matching the target user may be determined from the plurality of preset push rules according to the second semantic recognition result in the following manner: combining the second semantic recognition result and the target transaction characteristic data to obtain combined data; and according to the combined data, determining a target pushing rule matched with the target user from a plurality of preset pushing rules.

In some embodiments, when the pushing module 707 is implemented, the target data object may be pushed to the target user in the following manner: and pushing the target data object to a target user in a corresponding pushing mode according to the target pushing rule.

In some embodiments, the data object may specifically include a coupon or the like.

In some embodiments, after the target data object is pushed to the target user, the apparatus, when implemented, may be further configured to add a status record associated with the target data object in the target push record table; recording the valid period information of the target data object; and the target push record table corresponds to the user identification of the target user.

Correspondingly, when the device is implemented, the device can be used for receiving a transaction data processing request sent by a target user through a target terminal; detecting whether the transaction data processing request carries a data object; and under the condition that the transaction data processing request is determined to carry the data object, updating a state record related to the data object in the target push record table.

Referring to fig. 8, in a software layer, an embodiment of the present specification further provides a data object processing apparatus, which may specifically include the following structural modules:

a receiving module 801, which may be specifically configured to receive a first questionnaire, which is pushed by a server and is directed to a target user, regarding type preferences of a data object; and presenting the first questionnaire to the target user;

the sending module 802 may be specifically configured to obtain first text data fed back by a target user for a first questionnaire; sending the first text data to a server; the server screens out transaction characteristic types matched with the type preference of the current data object of the target user according to the first text data and combines the transaction characteristic types to obtain a target transaction characteristic type combination for the target user; the server also determines a target data object matched with the target user from the data objects to be pushed according to the target transaction characteristic type combination of the target user;

the presentation module 803 may be specifically configured to receive a target data object pushed by a server; and presenting the target data object to the target user.

It should be noted that, the units, devices, modules, etc. illustrated in the above embodiments may be implemented by a computer chip or an entity, or implemented by a product with certain functions. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. It is to be understood that, in implementing the present specification, functions of each module may be implemented in one or more pieces of software and/or hardware, or a module that implements the same function may be implemented by a combination of a plurality of sub-modules or sub-units, or the like. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

As can be seen from the above, the processing device for data objects provided in the embodiments of the present specification can accurately determine a target data object suitable for a current target user, so as to perform targeted push on the target user, obtain a better pushing effect, and simultaneously, effectively improve the interaction experience of the user.

Although the present specification provides method steps as described in the examples or flowcharts, additional or fewer steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an apparatus or client product in practice executes, it may execute sequentially or in parallel (e.g., in a parallel processor or multithreaded processing environment, or even in a distributed data processing environment) according to the embodiments or methods shown in the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded. The terms first, second, etc. are used to denote names, but not any particular order.

Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may therefore be considered as a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

From the above description of the embodiments, it is clear to those skilled in the art that the present specification can be implemented by software plus necessary general hardware platform. With this understanding, the technical solutions in the present specification may be essentially embodied in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a mobile terminal, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments in the present specification.

The embodiments in the present specification are described in a progressive manner, and the same or similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. The description is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

While the specification has been described with examples, those skilled in the art will appreciate that there are numerous variations and permutations of the specification that do not depart from the spirit of the specification, and it is intended that the appended claims include such variations and modifications that do not depart from the spirit of the specification.

Claims

1. A method for processing a data object, applied to a server, the method comprising:

and pushing the target data object to a target terminal.

2. The method of claim 1, wherein determining a target data object matching the target user from the plurality of data objects to be pushed according to the target transaction feature type combination of the target user comprises:

acquiring transaction behavior data of a target user in a current time period;

3. The method of claim 2, wherein determining a target data object matching the target user from the plurality of data objects to be pushed according to the target transaction characteristic data combination of the target user in the current time period comprises:

4. The method of claim 3, wherein after invoking the target-type preference prediction model to process the target transaction characteristic data combination for the target user's current time period to determine the target user's current preference type, the method further comprises:

5. The method of claim 4, wherein after pushing the target test object to the target user according to the first pushing rule, the method further comprises:

acquiring operation data of a target user aiming at a target test object;

6. The method of claim 5, wherein in the event that the first push rule is determined not to match the target user, the method further comprises:

generating a second questionnaire regarding push rule preferences for the data object for the target user;

7. The method according to claim 6, wherein determining a target push rule matching the target user from a plurality of preset push rules according to the second semantic recognition result comprises:

combining the second semantic recognition result with the target transaction characteristic data to obtain combined data;

8. The method of claim 6, wherein pushing the target data object to a target user comprises:

9. The method of claim 1, wherein the data object comprises a coupon.

10. The method of claim 9, wherein after pushing the target data object to a target user, the method further comprises:

adding a state record related to the target data object in the target push record table; recording the valid period information of the target data object; the target push record table corresponds to a user identifier of a target user;

correspondingly, the method further comprises the following steps:

11. A data object processing method is applied to a target terminal held by a target user, and comprises the following steps:

12. A data object processing apparatus, applied to a server, comprising:

the determining module is used for determining a target data object matched with the target user from a plurality of data objects to be pushed according to the target transaction characteristic type combination of the target user;

13. A data object processing device applied to a target terminal held by a target user includes:

14. A server comprising a processor and a memory for storing processor-executable instructions which, when executed by the processor, implement the steps of the method of any one of claims 1 to 10.

15. A computer-readable storage medium having stored thereon computer instructions which, when executed by a processor, carry out the steps of the method of any one of claims 1 to 10, or 11.