CN111695922A

CN111695922A - Potential user determination method and device, storage medium and electronic equipment

Info

Publication number: CN111695922A
Application number: CN201910199069.4A
Authority: CN
Inventors: 钟雨; 崔波; 杜睿桓
Original assignee: Beijing Wodong Tianjun Information Technology Co Ltd
Current assignee: Beijing Wodong Tianjun Information Technology Co Ltd
Priority date: 2019-03-15
Filing date: 2019-03-15
Publication date: 2020-09-22

Abstract

The invention discloses a potential user determination method and device, a storage medium and electronic equipment, and relates to the technical field of computers. The potential user determination method comprises the following steps: determining a plurality of article information according to the article interaction behavior of a target user, respectively converting each article information into an article vector, and constructing a first article sequence consisting of a plurality of article vectors; inputting the first item sequence into a trained intention item prediction model to determine a second item sequence; determining a target article based on the second article sequence, and determining an article acquisition characteristic of the target user in combination with information of the target article; inputting the item acquisition characteristics into a trained probability model to determine the target item acquisition probability of the target user, and determining whether the target user is a potential user for acquiring the target item according to the target item acquisition probability. The present disclosure may improve the accuracy of identifying potential users.

Description

Potential user determination method and device, storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a potential user determination method, a potential user determination apparatus, a storage medium, and an electronic device.

Background

In the field of electronic commerce, personalized recommendation and accurate user behavior guidance can be positioned to a target consumer group, products or services are directly displayed for a user, and time for searching the products or services is saved for the user. However, personalized recommendation often depends on active access of users, the recommendation form is single, the targeted population is wide, and it is difficult for an e-commerce platform to actively determine potential users who may acquire products.

At present, the more common method for determining potential users includes: the method comprises a Lookalike model based on seed population expansion, a method based on user labels and an unsupervised method based on text analysis. However, these methods have a problem of low accuracy of potential user identification.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

The present disclosure is directed to a potential user determination method, a potential user determination device, a storage medium, and an electronic apparatus, which overcome, at least to some extent, the problem of low accuracy of potential user identification in the related art.

According to an aspect of the present disclosure, there is provided a potential user determination method, including: determining a plurality of article information according to the article interaction behavior of a target user, respectively converting each article information into an article vector, and constructing a first article sequence consisting of a plurality of article vectors; inputting the first item sequence into a trained intention item prediction model to determine a second item sequence; determining a target article based on the second article sequence, and determining an article acquisition characteristic of the target user in combination with information of the target article; inputting the item acquisition characteristics into a trained probability model to determine the target item acquisition probability of the target user, and determining whether the target user is a potential user for acquiring the target item according to the target item acquisition probability.

In an exemplary embodiment of the present disclosure, converting each of the item information into an item vector, respectively, includes: performing word segmentation processing on the article information to obtain word segmentation results; inputting each word segmentation result into a trained first conversion model to determine a word segmentation vector corresponding to each word segmentation result; and integrating the word segmentation vectors to determine an article vector corresponding to the article information.

In an exemplary embodiment of the present disclosure, converting each of the item information into an item vector, respectively, includes: determining the browsing times of the articles corresponding to the article information to determine the browsing sequence of the articles; and inputting the browsing sequence into a trained second conversion model to determine an article vector corresponding to each article information.

In an exemplary embodiment of the present disclosure, the potential user determination method includes: determining a plurality of first users; determining a sample input sequence according to a plurality of item information determined by the item interaction behaviors of the first users, and determining a sample output sequence according to the intention item information of the first users; and taking the sample input sequence as the input of an intention commodity prediction model, and taking the sample output sequence as the output of the intention commodity prediction model so as to train the intention commodity prediction model.

In an exemplary embodiment of the present disclosure, determining the target item based on the second item sequence comprises: and taking the object contained in the second object sequence as a target object.

In an exemplary embodiment of the present disclosure, determining the target item based on the second item sequence comprises: determining the items contained in the second item sequence as first candidate items; determining an item similar to the first candidate item as a second candidate item; determining the set of first candidate items and the second candidate items as target items.

In one exemplary embodiment of the present disclosure, determining an item similar to the first candidate item as a second candidate item includes: calculating the similarity between the first candidate article and each other article in the article set; and taking the article with the similarity larger than a preset similarity threshold value in the article set as a second candidate article.

In an exemplary embodiment of the present disclosure, determining the item acquisition characteristic of the target user in combination with the information of the target item includes: determining a first characteristic of the target user according to the article interaction behavior of the target user in a first preset time period; determining a second feature of the target user based on a user representation of the target user; extracting basic information from the information of the target object, and determining a first characteristic of the target object according to the basic information; extracting dynamic information from the information of the target object, and determining a second characteristic of the target object according to the dynamic information; and combining the first characteristic and the second characteristic of the target user and the first characteristic and the second characteristic of the target item to determine the item acquisition characteristic of the target user.

In an exemplary embodiment of the present disclosure, the potential user determination method further includes: determining a plurality of second users; respectively determining the article acquisition characteristics of the second users; determining user information of the existing intention behaviors in a second preset time period; determining a training sample of a probability model based on the item acquisition features of the second users and the user information of the intentional behaviors existing in the second preset time period; and training the probability model by using the training sample of the probability model.

In an exemplary embodiment of the disclosure, the determining the item acquisition characteristics of each second user respectively includes: determining a first characteristic of the second user according to the item interaction behavior of the second user within a third preset time period; determining a second characteristic of the second user based on a user representation of the second user; extracting basic information from information of a predetermined article, and determining a first characteristic of the predetermined article according to the basic information; extracting dynamic information from the information of the predetermined article, and determining a second characteristic of the predetermined article according to the dynamic information; combining the first and second characteristics of the second user and the first and second characteristics of the predetermined item to determine an item acquisition characteristic of the second user.

In an exemplary embodiment of the present disclosure, determining whether the target user is a potential user for acquiring the target item according to the target item acquisition probability includes: judging whether the target article acquisition probability is greater than a preset probability threshold value or not; and if the target item acquisition probability is greater than the preset probability threshold, determining the target user as a potential user for acquiring the target item.

In an exemplary embodiment of the present disclosure, after determining that the target user is a potential user for obtaining the target item, the user determination method further includes: if the target user has an intention achievement behavior aiming at the target object within a fourth preset time period, pushing first preferential information to the target user; and if the target user does not have the intention reaching behavior aiming at the target item within the fourth preset time period, pushing second preferential information to the target user.

According to one aspect of the present disclosure, a potential user determination device is provided that includes an item sequence construction module, an intended item prediction module, an acquisition characteristic determination module, and a potential user determination module.

Specifically, the article sequence construction module is configured to determine a plurality of article information according to an article interaction behavior of a target user, convert each article information into an article vector, and construct a first article sequence composed of the plurality of article vectors; the intention item prediction module is used for inputting the first item sequence into a trained intention item prediction model so as to determine a second item sequence; the acquisition characteristic determining module is used for determining a target article based on the second article sequence and determining the article acquisition characteristic of the target user by combining the information of the target article; the potential user determining module is used for inputting the item acquisition characteristics into a trained probability model so as to determine the target item acquisition probability of the target user, and determining whether the target user is a potential user for acquiring the target item according to the target item acquisition probability.

In an exemplary embodiment of the present disclosure, the article sequence building module includes a first conversion unit.

Specifically, the first conversion unit is configured to perform: performing word segmentation processing on the article information to obtain word segmentation results; inputting each word segmentation result into a trained first conversion model to determine a word segmentation vector corresponding to each word segmentation result; and integrating the word segmentation vectors to determine an article vector corresponding to the article information.

In an exemplary embodiment of the present disclosure, the item sequence building module includes a second conversion unit.

Specifically, the second conversion unit is configured to perform: determining the browsing times of the articles corresponding to the article information to determine the browsing sequence of the articles; and inputting the browsing sequence into a trained second conversion model to determine an article vector corresponding to each article information.

In an example embodiment of the present disclosure, the potential user determination device further includes a first model training module.

In particular, the first model training module is configured to perform: determining a plurality of first users; determining a sample input sequence according to a plurality of item information determined by the item interaction behaviors of the first users, and determining a sample output sequence according to the intention item information of the first users; and taking the sample input sequence as the input of an intention commodity prediction model, and taking the sample output sequence as the output of the intention commodity prediction model so as to train the intention commodity prediction model.

In an exemplary embodiment of the present disclosure, the acquisition characteristic determination module includes a first target item determination unit.

Specifically, the first target item determining unit is configured to take the item included in the second item sequence as the target item.

In an exemplary embodiment of the present disclosure, the acquisition characteristic determination module includes a second target item determination unit.

Specifically, the second target item determination unit is configured to perform: determining the items contained in the second item sequence as first candidate items; determining an item similar to the first candidate item as a second candidate item; determining the set of first candidate items and the second candidate items as target items.

In an exemplary embodiment of the present disclosure, the second target item determination unit includes a similarity degree subunit and an item determination subunit.

Specifically, the similarity calculation subunit is configured to calculate similarities between the first candidate item and each of the other items in the item set; the article determining subunit is used for determining the article with the similarity larger than a preset similarity threshold in the article set as a second candidate article.

In an exemplary embodiment of the present disclosure, the acquisition feature determination module includes a first acquisition feature determination unit.

Specifically, the first acquired feature determination unit is configured to perform: determining a first characteristic of the target user according to the article interaction behavior of the target user in a first preset time period; determining a second feature of the target user based on a user representation of the target user; extracting basic information from the information of the target object, and determining a first characteristic of the target object according to the basic information; extracting dynamic information from the information of the target object, and determining a second characteristic of the target object according to the dynamic information; and combining the first characteristic and the second characteristic of the target user and the first characteristic and the second characteristic of the target item to determine the item acquisition characteristic of the target user.

In an exemplary embodiment of the disclosure, the potential user determination device further comprises a second model training module.

In particular, the second model training module is configured to perform: determining a plurality of second users; respectively determining the article acquisition characteristics of the second users; determining user information of the existing intention behaviors in a second preset time period; determining a training sample of a probability model based on the item acquisition features of the second users and the user information of the intentional behaviors existing in the second preset time period; and training the probability model by using the training sample of the probability model.

In an exemplary embodiment of the present disclosure, the second model training module includes a second acquired feature determination unit.

Specifically, the second acquired feature determining unit is configured to perform: determining a first characteristic of the second user according to the item interaction behavior of the second user within a third preset time period; determining a second characteristic of the second user based on a user representation of the second user; extracting basic information from information of a predetermined article, and determining a first characteristic of the predetermined article according to the basic information; extracting dynamic information from the information of the predetermined article, and determining a second characteristic of the predetermined article according to the dynamic information; combining the first and second characteristics of the second user and the first and second characteristics of the predetermined item to determine an item acquisition characteristic of the second user.

In an exemplary embodiment of the disclosure, the potential user determination module includes a potential user determination unit.

In particular, the potential user determination unit is configured to perform: judging whether the target article acquisition probability is greater than a preset probability threshold value or not; and if the target item acquisition probability is greater than the preset probability threshold, determining the target user as a potential user for acquiring the target item.

In an exemplary embodiment of the disclosure, the potential user determination device further includes a preference information pushing module.

Specifically, the preference information pushing module is configured to execute: if the target user has an intention achievement behavior aiming at the target object within a fourth preset time period, pushing first preferential information to the target user; and if the target user does not have the intention reaching behavior aiming at the target item within the fourth preset time period, pushing second preferential information to the target user.

According to an aspect of the present disclosure, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the potential user determination method according to any one of the above embodiments.

According to an aspect of the present disclosure, there is provided an electronic device including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the potential user determination method of any of the above embodiments via execution of the executable instructions.

In the technical solutions provided by some embodiments of the present disclosure, a first item sequence determined based on an item interaction behavior of a target user is input into an intention item prediction model to obtain a second item sequence representing a possible user's interest, a target item is determined based on the second item sequence, an item acquisition feature of the target user is determined in combination with information of the target item, the item acquisition feature is input into a probability model to obtain a target item acquisition probability of the target user, and whether the target user is a potential user for acquiring the target item is determined according to the target item acquisition probability. On one hand, the method and the device for determining the potential user can accurately determine the potential user by combining with the article interaction behavior of the user, so that the method and the device are helpful for guiding the behavior of the potential user and saving the time for searching articles for the user; on the other hand, the article information is converted into a vector form, so that analysis calculation and processing by using a model are facilitated; on the other hand, the target object is determined by using a second object sequence which is possibly interested by the target user, the object acquisition characteristic is determined according to the target object, and the object acquisition characteristic is input into the probability model to determine whether the target user is a potential user, so that the problem of identification of the potential user can be solved better, a potential user positioning result with better flexibility can be provided by using a probability mode, and the operation effect of the electronic commerce platform is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty. In the drawings:

FIG. 1 schematically illustrates a flow chart of a potential user determination method according to an exemplary embodiment of the present disclosure;

FIG. 2 schematically illustrates a block diagram of a potential user determination device, according to an example embodiment of the present disclosure;

FIG. 3 schematically illustrates a block diagram of an item sequence building module according to an exemplary embodiment of the present disclosure;

FIG. 4 schematically illustrates a block diagram of an item sequence building module according to another exemplary embodiment of the present disclosure;

FIG. 5 schematically illustrates a block diagram of a potential user determination device, according to another example embodiment of the present disclosure;

FIG. 6 schematically illustrates a block diagram of an acquisition characteristic determination module according to an exemplary embodiment of the present disclosure;

FIG. 7 schematically illustrates a block diagram of an acquisition characteristic determination module according to another exemplary embodiment of the present disclosure;

fig. 8 schematically shows a block diagram of a second target item determination unit according to an exemplary embodiment of the present disclosure;

FIG. 9 schematically illustrates a block diagram of an acquisition characteristic determination module, according to another exemplary embodiment of the present disclosure;

FIG. 10 schematically illustrates a block diagram of a potential user determination device, according to yet another example embodiment of the present disclosure;

FIG. 11 schematically illustrates a block diagram of a second model training module, according to an exemplary embodiment of the present disclosure;

FIG. 12 schematically illustrates a block diagram of a potential user determination module, according to an exemplary embodiment of the present disclosure;

FIG. 13 schematically illustrates a block diagram of a potential user determination device, according to yet another example embodiment of the present disclosure;

FIG. 14 shows a schematic diagram of a storage medium according to an example embodiment of the present disclosure; and

fig. 15 schematically shows a block diagram of an electronic device according to an exemplary embodiment of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the steps. For example, some steps may be decomposed, and some steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation. In addition, the terms "first", "second", "third", "fourth", etc. used in the present disclosure are for the purpose of distinction only and should not be construed as a limitation of the present disclosure.

Short messages and emails are good modes for popularizing products on an e-commerce platform, and the products can correspond to various articles and can be popularized to users in a paid or unpaid mode. The short message and the e-mail have the characteristics of low cost and high reaching rate. However, in recent years, the popularization of business of the e-commerce platform is blocked due to misuse of short messages and e-mails, and the effect of guiding user behaviors cannot be realized well.

Currently, a more common determination of potential users may include: the method comprises the following steps of (1) mining similar users through a user portrait and a relationship chain based on a seed crowd extended Lookalike model, specifically based on a seed crowd defined in advance; the method for determining the user based on the user label specifically comprises the steps of determining the label of the user by utilizing the search behavior information of the user, and determining a potential user according to the label of the user; the unsupervised method based on text analysis specifically comprises the steps of generating keyword feature vectors by utilizing user searching and accessing results, extracting the feature vectors of target articles according to texts, and mining potential users by utilizing a neighbor retrieval method. In addition, there are some methods based on human defined metrics and calculation rules.

However, the Lookalike model is wide in oriented population, lacks of user behavior characteristics, is difficult for the e-commerce platform to actively contact potential users which may obtain products thereof, and has low conversion rate; besides the lack of behavior characteristics of users, the method based on the user tags is difficult to deal with aiming at the problem related to sequencing; the unsupervised method based on the text analysis ignores part of the operation behaviors of the user; the manual definition of indexes and calculation rules consumes a large amount of human resources and the method has poor universality. Therefore, it can be seen that the problem of low accuracy of potential user identification is caused by the defects of the existing processing method.

In view of this, the exemplary embodiments of the present disclosure provide a new method and apparatus for determining a potential user, which may improve accuracy of identifying the potential user, and further help to guide user behavior.

It should be noted that the potential user determination method of the exemplary embodiment of the present disclosure may be implemented by a server, that is, the server may implement the steps of the potential user determination method of the present disclosure. For example, the server may be a server used by the e-commerce platform, and in addition, the server may also be a third-party server serving the e-commerce platform, which is not particularly limited in this exemplary embodiment. In this case, the potential user determination device described below may be configured within the server.

Fig. 1 schematically illustrates a flow chart of a potential user determination method of an exemplary embodiment of the present disclosure. Referring to fig. 1, the potential user determination method may include the steps of:

s12, determining a plurality of article information according to the article interaction behavior of the target user, respectively converting each article information into an article vector, and constructing a first article sequence consisting of a plurality of article vectors.

In an exemplary embodiment of the present disclosure, the target user is a user to be determined whether the target user is a potential user, for example, a developer may pre-construct a user white list, and the target user may be any user in the user white list. In addition, the item interaction behavior of the user may include, but is not limited to, a browsing behavior of the user on the item, a behavior of the item being added to the acquisition bar, a behavior of the user paying attention to the item, a pre-acquisition behavior of the user on the item, a collection behavior of the user on the item, and the like. The pre-acquisition behavior may also be referred to as intent behavior, which characterizes the user's interest in acquiring the item.

According to some embodiments of the present disclosure, the server may determine a plurality of item information from one of the above listed item interaction behaviors.

For example, a plurality of item information may be determined based on the browsing behavior. Specifically, first, the server may extract browsing behavior data from a flow table of a data warehouse storing user data, and on one hand, the server may extract browsing behavior data within a period of time (e.g., 30 days); browsing behavior data, on the other hand, may be characterized in the form of triplets, e.g., < user identification, browsing time, item ID >. Next, the server may determine a plurality of item information related to the browsing behavior data, wherein the item information may include an item name, description information of the item, an item ID, item vendor information, and the like.

It is easily understood that, similarly, the server may also determine a plurality of item information according to the behavior data of the item added to the acquisition field, the behavior data of the item concerned by the user, the pre-acquisition behavior data of the item by the user, or the collection behavior data of the item by the user.

In addition, the server may further determine a plurality of item information in combination with a plurality of behavior data in the behavior data, for example, the server may determine a plurality of item information in combination with the user attention behavior data and the user collection behavior data of the item, which should be noted that this is not particularly limited in this exemplary embodiment.

After determining the plurality of item information, the server may convert each item information into an item vector for subsequent analysis processing.

According to some embodiments of the present disclosure, first, the server may perform a word segmentation process on each item information to obtain word segmentation results. Specifically, the existing natural language processing method can be adopted to perform word segmentation on the article information, and the specific implementation mode of word segmentation is not specially limited in the disclosure; next, the server may input each obtained segmentation result into a trained first conversion model to determine a segmentation vector of each segmentation result, and the dimension of the segmentation vector may be 64, for example. The first conversion model can be a Word2vev model, however, the first conversion model can also be a GloVe model, an ELMo model, a BERT model and the like, and the method does not specially limit the type of the first conversion model, the selection of training samples and the training process; subsequently, the server may integrate the analysis vectors output via the first conversion model to determine an item vector to which the item information corresponds.

According to other embodiments of the present disclosure, first, the server may determine the browsing times of the articles corresponding to the information of each article, and determine the browsing sequence of each article based on the browsing times, for example, the browsing sequence may be a sequence in which the articles are arranged from high to low based on the browsing times, or may be a sequence in which the articles are arranged from low to high based on the browsing times, which is not particularly limited in this exemplary embodiment; next, the server may input the determined browsing sequence into a trained second conversion model, and output of the second conversion model is an item vector corresponding to each item information. The second conversion model may be of the same type as the first conversion model and may be a Word2vev model, however, the second conversion model may also be of a different type from the first conversion model and may be a Word2vev model, a GloVe model, an ELMo model, a BERT model, or the like.

In addition, for an item information, the two embodiments can be combined to determine an item vector. For example, when the first embodiment determines that the dimension of the item vector is 64 and the second embodiment determines that the dimension of the item vector is 64, the item information may be represented by combining the two into a 128-dimensional vector.

After converting each item information into an item vector, the server may include a first item sequence comprising a plurality of item vectors. For example, in the case that the item interaction behavior is a browsing behavior, the first item sequence may be a sequence in which items are arranged from high to low in the number of browsing times, or may be a sequence in which items are arranged from low to high in the number of browsing times.

It should be understood that the above-described scheme is a scheme of constructing the first item sequence after converting each item information into an item vector. However, in other embodiments of the present disclosure, the first item sequence may be determined by constructing a sequence of item information and then performing vector conversion on all the item information based on the sequence.

Further, the first conversion model and/or the second conversion model described above may be configured within the server. However, it is easily understood that the first conversion model and/or the second conversion model may also be configured in another server, which is not particularly limited in the exemplary embodiment.

S14, inputting the first item sequence into a trained intention item prediction model to determine a second item sequence.

In an exemplary embodiment of the present disclosure, the intention item prediction model may be a sequence-to-sequence based neural network model (seq2seq neural network model), and the seq2seq neural network model is an end-to-end model capable of performing a prediction process on a sequence. The disclosed exemplary embodiments implement the process of intent item prediction using a seq2seq neural network model, however, it should be understood that the seq2seq neural network model is not limited to the form, and for example, a seq2seq neural network model with attention mechanism may also be employed. In addition, in other embodiments of the present disclosure, other neural network models may also be used to process the first item sequence, which is not particularly limited in this exemplary embodiment. Similar to the first and second conversion models described above, the intended item prediction model may be configured in a server that performs the disclosed exemplary method, however, may be configured in other servers than the server that performs the disclosed exemplary method.

Exemplary embodiments of the present disclosure may also include a process of training an intent-to-commodity prediction model.

First, the server may determine a plurality of first users, specifically, a user having pre-acquisition behavior (intention reaching behavior) for a period of time as the first user based on a flow table of a data warehouse storing user data, however, the first user may also be determined based on the user white list described in step S12, for example, a number of users may be randomly selected from the user white list as the first user, in which case, the number of users in the user white list and the computer processing capability may be integrated to determine the number of first users.

Next, the server may determine a plurality of item information according to the item interaction behavior of each first user, and it should be understood that, for each first user of the plurality of first users, a plurality of item information may be determined according to the item interaction behavior thereof, and the manner of determining the plurality of items corresponding to the first user is the same as the manner of determining the plurality of item information corresponding to the target user in step S12, which is not described herein again. After determining the plurality of item information corresponding to the first user, a sample input sequence may be determined according to the plurality of item information, and similarly, the plurality of item information may be converted into item vectors, respectively, and a sequence composed of the plurality of item vectors is constructed as the sample input sequence. It should be noted that for each first user, there may be a corresponding sample input sequence.

Additionally, the server may obtain intended-item information for each first user from the data repository and determine a sample output sequence based on the intended-item information. Wherein the respective intended items may be sorted based on the number of intended items to generate the sample output sequence. Likewise, for each first user, there may be a corresponding sample output sequence. It should be understood that the sample output sequence is also represented in the form of an item vector.

It should be noted that the server, in determining the sample input sequence and the sample output sequence, is the item information that is extracted over a period of time, which may be, for example, a month, a quarter, a half year, a year, etc. It is easy to understand that the larger the time period span is, the larger the sample data is, and the better the model prediction effect is.

The server may then train the intent-to-commodity prediction model using the sample input sequence as input to the intent-to-commodity prediction model and the sample output sequence as output from the intent-to-commodity prediction model.

Further, after training the intent item prediction model, the method of exemplary embodiments of the present disclosure may further include obtaining samples for validating the intent item prediction model in order to validate the trained intent item prediction model. The process of specifically obtaining the sample of the verification model and the process of verifying the model are similar to the training process, and are not described herein again.

The above describes a scheme for training an intent item prediction model by a server of an exemplary method of the present disclosure. However, according to other embodiments of the present disclosure, the process of training the intent-to-item prediction model may be performed by a server other than the server performing the exemplary method of the present disclosure, and the training method is similar and will not be described herein.

After determining the trained intended goods prediction model, the server may input the first sequence of items constructed in step S12 into the trained intended goods prediction model to determine a second sequence of items. It is readily understood that the second item sequence characterizes the item sequence that may be of interest to the target user determined based on the item interaction behavior of the target user.

And S16, determining a target object based on the second object sequence, and determining the object acquisition characteristics of the target user by combining the information of the target object.

According to some embodiments of the present disclosure, the server may determine the items included in the sequence from the second sequence of items and treat those items as target items.

According to further embodiments of the present disclosure, first, the server may determine the items included in the sequence from the second item sequence and treat these items as first candidate items; next, the server may determine an item similar to the first candidate item as a second candidate item, and determine a set of the first candidate item and the second candidate item as the target item.

Specifically, the process of determining the target item may include:

first, the server may calculate a similarity of the first candidate item to each of the other items in the set of items.

The item set according to the exemplary embodiment of the present disclosure may be an item set composed of all items of an e-commerce platform, or may be an item set composed of all items under a certain category.

The present disclosure may calculate the similarity by the cosine similarity principle. In particular, since the second item sequence is composed of item vectors of a plurality of items, for example, one of the item vectors is denoted as

Expressing all articles in the article set in a vector form, selecting one article to be marked as

Thus, the similarity sim (X, Y) of the two articles can be calculated using the following formula:

thus, the similarity between the first candidate item and each of the other items in the set of items can be calculated.

In addition to cosine similarity, other embodiments of the present disclosure may also calculate similarity between items by using principles such as mahalanobis distance, manhattan distance, euclidean distance, etc., which is not particularly limited in this exemplary embodiment.

Next, the server may use the determined item with the similarity greater than a preset similarity threshold as the second candidate item, for example, the preset similarity threshold may be set to 0.8. It will be readily appreciated that each first candidate item may correspond to a plurality of second candidate items.

The server may then determine a set of the first candidate item and the second candidate item as the target item.

After determining the target item, the server may determine the item acquisition characteristics of the target user in combination with the information of the target item.

In one aspect, the server may determine a first characteristic of the target user based on item interaction behavior of the target user over a first preset time period (e.g., a day, a week, a month, a quarter, etc.). Taking the example that the article interaction behavior is the browsing behavior of the target user on the article, the server may determine the article browsing sequence of the target user, count the browsing times of the target user for each article and the total browsing times of the target user, and take the browsing times of the target user for each article and the total browsing times of the target user as the first characteristic of the target user.

However, it should be understood that the item interaction behavior may be a combination of one or more of a browsing behavior of the target user on the item, a behavior of the item being added to the get bar, a behavior of the target user paying attention to the item, a pre-fetching behavior of the target user on the item, and a collecting behavior of the target user on the item. Similarly, the corresponding determined data is the first feature, for example, the number of times that the target user joins the acquisition field for each item and the total number of times that the target user joins the acquisition field may be used as the first feature of the target user.

In another aspect, the server may determine a second characteristic of the target user based on a user representation of the target user. Specifically, the user profile of each user may be pre-constructed and stored in the user profile table of the data repository. In this case, first, the server may determine enumerated features, such as user account, gender, age group, membership grade, region, item acquisition capability level, etc., from the user image of the target user; these enumerated features may then be one-hot (OneHot) encoded to generate 0/1 features; additionally, the server may extract numerical features from the user representation of the target user, such as a user promotional sensitivity score, a user liveness score, etc.; next, the numerical feature and the enumerated feature subjected to the one-hot encoding may be spliced to obtain a second feature of the target user.

In yet another aspect, the server may extract base information from the information of the target item and determine the first characteristic of the target item based on the base information. Specifically, first, the server may extract enumerated features of the target item, such as item category, brand, color, intended user gender, and the like, from a pre-stored item feature table; these enumerated features may then be one-hot coded to generate a plurality of 0/1 features; in addition, the server may extract numerical characteristics of the target item, such as size, weight, and the like, from the item characteristic table; next, the server may splice the numerical feature of the target item with the enumerated feature subjected to the unique hot encoding to obtain the first feature of the target item.

In yet another aspect, the server may extract dynamic information from the information of the target item and determine the second characteristic of the target item based on the dynamic information. Specifically, first, the server may extract browsed data, data added to the acquisition column, data of interest, collected data, data of intentional behavior, and the like of the target item within a first preset time period from a flow table of the data warehouse; next, the server may determine corresponding values according to the data, for example, the number of times of being browsed, the number of times of being accessed by an independent Visitor (UV), the number of times of being added to the acquisition field, the number of times of being concerned, the number of times of being collected, the number of times of having an intention behavior, and the like; in addition, the server can acquire the emission quantity of the target object in a first preset time period; in addition, similarly, the server may determine a category or a brand corresponding to the target item, and count information such as the total number of times the category or the brand is browsed, the number of times the category or the brand is accessed by an independent visitor, the number of times the category or the brand is added to the acquisition field, the number of times the category or the brand is concerned, the number of times the category or the brand is collected, the number of times the intention behavior exists, and the issue amount. And integrating the information to determine a second characteristic of the target item.

Thus, the first and second characteristics of the target user and the first and second characteristics of the target item described above may be combined to determine the item acquisition characteristic of the target user.

And S18, inputting the article acquisition characteristics into a trained probability model to determine the target article acquisition probability of the target user, and determining whether the target user is a potential user for acquiring the target article according to the target article acquisition probability.

In an exemplary embodiment of the present disclosure, the probability model may be a Gradient Boosting Decision Tree (GBDT), which is an iterative Decision Tree algorithm that may be composed of a plurality of Decision trees, and the conclusions of all the trees are accumulated to finally obtain a predicted result. However, it should be understood that other probabilistic models, such as random forests, XGBoost, etc., may also be employed to implement the probabilistic model described in this disclosure, and the disclosure is not limited to the probabilistic model. Similar to the models described above, the probabilistic model of the exemplary embodiments of the present disclosure may be configured in a server that performs the exemplary method of the present disclosure, however, may be configured in other servers than the server that performs the exemplary method of the present disclosure.

The exemplary embodiments of the present disclosure may also include a process of training a probabilistic model.

First, the server may determine a plurality of second users. Similar to the determination of the plurality of first users in step S14, in particular, the server may determine the second user based on the behavior of the flow table of the data warehouse storing the user data over a period of time, however, the second user may also be determined based on the user white list described in step S12. It is to be understood that the plurality of second users may include the first user described above.

Next, the server may determine the item acquisition characteristics of each second user separately, e.g., the server may determine the item acquisition characteristics of each second user every day.

Specifically, the server determines a first characteristic of the second user according to an article interaction behavior of the second user within a third preset time period; determining a second characteristic of the second user based on the user image of the second user, extracting basic information from the information of the predetermined article, and determining a first characteristic of the predetermined article according to the basic information; extracting dynamic information from the information of the predetermined article, and determining a second characteristic of the predetermined article according to the dynamic information; the first and second characteristics of the second user and the first and second characteristics of the predetermined item are combined to determine an item acquisition characteristic of the second user. The third preset time period may be a day, a week, a month, a quarter, etc., and may be the same as the first preset time period, and the predetermined item may be a randomly determined item. The specific process is similar to the above step S16 of determining the item acquisition characteristic of the target user, and is not described herein again.

In addition, the server may determine the user information of the intentional behavior existing within a second preset time period, where the second preset time period may be a period of time (e.g., 15 days) after determining that the second user item acquires the feature, however, the second preset time period is not particularly limited by the present disclosure.

Then, a training sample of the probabilistic model may be determined based on the item acquisition features of the second users and the user information of the intentional behavior existing within the second preset time period, and the probabilistic model may be trained by using the training sample.

For the process of determining the training sample of the probabilistic model, for example, the server may determine the item acquisition characteristics of each second user 1 month and 1 day, and in a case where the second preset time period is 15 days, determine the user information of the intentional behavior existing from 1 month and 1 day to 1 month and 15 days. If the item acquisition characteristics and the user information with the intentional behaviors are stored in a table mode, the item acquisition characteristics table and the user information table with the intentional behaviors can be associated in a left connection mode, matched data in the item acquisition characteristics table and the user information table with the intentional behaviors are recorded as a positive example, and unmatched data are recorded as a negative example. Next, the same number of positive examples and negative examples can be determined by using the method of negative sampling to obtain training samples of the 1 month and 1 day probabilistic model. Repeating the step of determining the training sample for 1 month and 1 day for 1 month and 2 days to 1 month and 30 days to obtain the training sample of the probability model.

And training the probability model by using the determined training samples. In addition, after the training of the probabilistic model, the method of the exemplary embodiment of the present disclosure may further include obtaining a sample for verifying the probabilistic model, so as to verify the trained probabilistic model. The specific process of obtaining the sample of the verification probability model and the process of verifying the model are similar to the training process, and are not described herein again.

The above describes a scheme for training a probabilistic model by a server of an exemplary method of the present disclosure. However, according to other embodiments of the present disclosure, the process of training the probabilistic model may be performed by other servers except the server performing the exemplary method of the present disclosure, and the training method is similar and will not be described herein again.

After determining the trained probabilistic model, the server may input the item acquisition characteristics of the target user determined in step S16 into the trained probabilistic model to determine the target item acquisition probability of the target user.

In addition, after determining the target item acquisition probability of the target user, the server may determine whether the target user is a potential user for acquiring the target item according to the target item acquisition probability. Specifically, the server may determine whether the target item acquisition probability is greater than a preset probability threshold, for example, the preset probability threshold may be set to 0.5. And if the target item acquisition probability is greater than the preset probability threshold, determining the target user as a potential user for acquiring the target item.

For the determined potential users, the exemplary embodiments of the present disclosure also provide a user behavior guidance strategy. Specifically, if the target user has an intention achievement behavior for the target item within a fourth preset time period (for example, within a current half year), pushing first preferential information to the target user; and if the target user does not have the intention achievement behavior aiming at the target object within the fourth preset time period, pushing second preferential information to the target user.

By judging whether the target user has the intention reaching behavior aiming at the target object within the fourth preset time period or not, the target user can be classified, and different user behavior guiding strategies are carried out. For example, if the target user has an intention reaching behavior for the target item in a fourth preset time period, it may be indicated that the target user is an old user, in which case, the first benefit information, such as doubling of points, issuing coupons, etc., may be pushed to the target user based on a policy for the old user; if the target user does not have the intention to reach the behavior for the target item within the fourth preset time period, indicating that the target user is probably a new user, second preferential information, such as issuing a coupon, can be pushed to the target user based on the strategy for the new user. It is readily understood that the value of the issued coupons may be different for the old user and the new user.

It should be noted that although the various steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that these steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.

Further, a potential user determination device is also provided in the present example embodiment.

Fig. 2 schematically illustrates a block diagram of a potential user determination device of an exemplary embodiment of the present disclosure. Referring to fig. 2, a potential user determination apparatus 2 according to an exemplary embodiment of the present disclosure may include an item sequence construction module 21, an intended item prediction module 23, an acquisition feature determination module 25, and a potential user determination module 27.

Specifically, the article sequence construction module 21 may be configured to determine a plurality of article information according to an article interaction behavior of a target user, convert each article information into an article vector, and construct a first article sequence composed of a plurality of article vectors; intent item prediction module 23 may be configured to input the first item sequence into a trained intent item prediction model to determine a second item sequence; the acquisition characteristic determining module 25 may be configured to determine a target item based on the second item sequence, and determine an item acquisition characteristic of the target user in combination with information of the target item; the potential user determining module 27 may be configured to input the item acquisition characteristics into a trained probability model to determine a target item acquisition probability of the target user, and determine whether the target user is a potential user for acquiring the target item according to the target item acquisition probability.

On the one hand, the potential user can be accurately determined by combining the item interaction behavior of the user, so that the time for searching items is saved for the user; on the other hand, the article information is converted into a vector form, so that analysis and processing by using a model are facilitated; on the other hand, the target object is determined by using a second object sequence which is possibly interested by the target user, the object acquisition characteristic is determined according to the target object, and the object acquisition characteristic is input into the probability model to determine whether the target user is a potential user, so that the problem of identification of the potential user can be solved better, a potential user positioning result with better flexibility can be provided by using a probability mode, and the operation effect of the electronic commerce platform is improved.

According to an exemplary embodiment of the present disclosure, referring to fig. 3, the article sequence building module 21 may include a first conversion unit 301.

In particular, the first conversion unit 301 may be configured to perform: performing word segmentation processing on the article information to obtain word segmentation results; inputting each word segmentation result into a trained first conversion model to determine a word segmentation vector corresponding to each word segmentation result; and integrating the word segmentation vectors to determine an article vector corresponding to the article information.

According to an exemplary embodiment of the present disclosure, referring to fig. 4, the article sequence building module 21 may include a second conversion unit 401.

Specifically, the second conversion unit 401 may be configured to perform: determining the browsing times of the articles corresponding to the article information to determine the browsing sequence of the articles; and inputting the browsing sequence into a trained second conversion model to determine an article vector corresponding to each article information.

According to an exemplary embodiment of the present disclosure, referring to fig. 5, the potential user determining apparatus 5 may include a first model training module 51 in addition to the item sequence building module 21, the intended item prediction module 23, the acquired feature determining module 25, and the potential user determining module 27, as compared to the potential user determining apparatus 2.

In particular, the first model training module 51 may be configured to perform: determining a plurality of first users; determining a sample input sequence according to a plurality of item information determined by the item interaction behaviors of the first users, and determining a sample output sequence according to the intention item information of the first users; and taking the sample input sequence as the input of an intention commodity prediction model, and taking the sample output sequence as the output of the intention commodity prediction model so as to train the intention commodity prediction model.

According to an exemplary embodiment of the present disclosure, referring to fig. 6, the acquisition characteristic determination module 25 may include a first target item determination unit 601.

Specifically, the first target item determination unit 601 may be configured to take the item included in the second item sequence as the target item.

According to an exemplary embodiment of the present disclosure, referring to fig. 7, the acquisition characteristic determination module 25 may include a second target item determination unit 701.

Specifically, the second target item determination unit 701 may be configured to perform: determining the items contained in the second item sequence as first candidate items; determining an item similar to the first candidate item as a second candidate item; determining the set of first candidate items and the second candidate items as target items.

According to an exemplary embodiment of the present disclosure, referring to fig. 8, the second target item determination unit 701 may include a similarity degree subunit 8001 and an item determination subunit 8003.

Specifically, the similarity calculation subunit 8001 may be configured to calculate similarities between the first candidate item and each of the other items in the item set; item determination subunit 8003 may be configured to use, as the second candidate item, an item in the item set whose similarity is greater than a preset similarity threshold.

According to an exemplary embodiment of the present disclosure, referring to fig. 9, the acquisition feature determination module 25 may include a first acquisition feature determination unit 901.

Specifically, the first acquired feature determining unit 901 may be configured to perform: determining a first characteristic of the target user according to the article interaction behavior of the target user in a first preset time period; determining a second feature of the target user based on a user representation of the target user; extracting basic information from the information of the target object, and determining a first characteristic of the target object according to the basic information; extracting dynamic information from the information of the target object, and determining a second characteristic of the target object according to the dynamic information; and combining the first characteristic and the second characteristic of the target user and the first characteristic and the second characteristic of the target item to determine the item acquisition characteristic of the target user.

According to an exemplary embodiment of the present disclosure, referring to fig. 10, potential user determination device 10 may include a second model training module 101 in addition to item sequence construction module 21, intended item prediction module 23, acquisition feature determination module 25, and potential user determination module 27, as compared to potential user determination device 2.

In particular, the second model training module 101 may be configured to perform: determining a plurality of second users; respectively determining the article acquisition characteristics of the second users; determining user information of the existing intention behaviors in a second preset time period; determining a training sample of a probability model based on the item acquisition features of the second users and the user information of the intentional behaviors existing in the second preset time period; and training the probability model by using the training sample of the probability model.

It should be understood that the second model training module 101 may also be included in the potential user determination device 5, and correspondingly, the first model training module 51 may also be included in the potential user determination device 10.

According to an exemplary embodiment of the present disclosure, referring to fig. 11, the second model training module 101 may include a second acquired feature determination unit 111.

Specifically, the second acquired feature determining unit 111 may be configured to perform: determining a first characteristic of the second user according to the item interaction behavior of the second user within a third preset time period; determining a second characteristic of the second user based on a user representation of the second user; extracting basic information from information of a predetermined article, and determining a first characteristic of the predetermined article according to the basic information; extracting dynamic information from the information of the predetermined article, and determining a second characteristic of the predetermined article according to the dynamic information; combining the first and second characteristics of the second user and the first and second characteristics of the predetermined item to determine an item acquisition characteristic of the second user.

According to an exemplary embodiment of the present disclosure, referring to fig. 12, the potential user determining module 27 may include a potential user determining unit 121.

In particular, the potential user determining unit 121 may be configured to perform: judging whether the target article acquisition probability is greater than a preset probability threshold value or not; and if the target item acquisition probability is greater than the preset probability threshold, determining the target user as a potential user for acquiring the target item.

According to an exemplary embodiment of the present disclosure, referring to fig. 13, the potential user determining apparatus 13 may further include a benefit information pushing module 131 in addition to the item sequence constructing module 21, the intended item predicting module 23, the acquisition characteristic determining module 25, and the potential user determining module 27, compared to the potential user determining apparatus 2.

Specifically, the offer information pushing module 131 is configured to perform: if the target user has an intention achievement behavior aiming at the target object within a fourth preset time period, pushing first preferential information to the target user; and if the target user does not have the intention reaching behavior aiming at the target item within the fourth preset time period, pushing second preferential information to the target user.

It should be noted that the offer information pushing module 131 may also be included in the potential user determination device 5 or the potential user determination device 10.

Since each functional module of the program operation performance analysis apparatus according to the embodiment of the present invention is the same as that in the embodiment of the present invention, it is not described herein again.

In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, aspects of the invention may also be implemented in the form of a program product comprising program code means for causing a terminal device to carry out the steps according to various exemplary embodiments of the invention described in the above section "exemplary methods" of the present description, when said program product is run on the terminal device.

Referring to fig. 14, a program product 1400 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical disk, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.

An electronic device 1500 according to this embodiment of the invention is described below with reference to fig. 15. The electronic device 1500 shown in fig. 15 is only an example and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 15, electronic device 1500 is in the form of a general purpose computing device. Components of electronic device 1500 may include, but are not limited to: the at least one processing unit 1510, the at least one storage unit 1520, a bus 1530 connecting different system components (including the storage unit 1520 and the processing unit 1510), and a display unit 1540.

Wherein the memory unit stores program code that is executable by the processing unit 1510 to cause the processing unit 1510 to perform steps according to various exemplary embodiments of the present invention as described in the above section "exemplary methods" of the present specification. For example, the processing unit 1510 may perform step S12 as shown in fig. 1: determining a plurality of article information according to the article interaction behavior of a target user, respectively converting each article information into an article vector, and constructing a first article sequence consisting of a plurality of article vectors; step S14: inputting the first item sequence into a trained intention item prediction model to determine a second item sequence; step S16: determining a target article based on the second article sequence, and determining an article acquisition characteristic of the target user in combination with information of the target article; step S18: inputting the item acquisition characteristics into a trained probability model to determine the target item acquisition probability of the target user, and determining whether the target user is a potential user for acquiring the target item according to the target item acquisition probability.

The storage unit 1520 may include readable media in the form of volatile storage units, such as a random access memory unit (RAM)15201 and/or a cache memory unit 15202, and may further include a read only memory unit (ROM) 15203.

Storage unit 1520 may also include a program/utility 15204 having a set (at least one) of program modules 15205, such program modules 15205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 1530 may be any bus representing one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 1500 can also communicate with one or more external devices 1600 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 1500, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 1500 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interface 1550. Also, the electronic device 1500 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 1560. As shown, the network adapter 1560 communicates with the other modules of the electronic device 1500 over the bus 1530. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 1500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

Furthermore, the above-described figures are merely schematic illustrations of processes involved in methods according to exemplary embodiments of the invention, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is to be limited only by the terms of the appended claims.

Claims

1. A method for potential user determination, comprising:

determining a plurality of article information according to the article interaction behavior of a target user, respectively converting each article information into an article vector, and constructing a first article sequence consisting of a plurality of article vectors;

inputting the first item sequence into a trained intention item prediction model to determine a second item sequence;

determining a target article based on the second article sequence, and determining an article acquisition characteristic of the target user in combination with information of the target article;

inputting the item acquisition characteristics into a trained probability model to determine the target item acquisition probability of the target user, and determining whether the target user is a potential user for acquiring the target item according to the target item acquisition probability.

2. The method of claim 1, wherein converting each item information into an item vector comprises:

performing word segmentation processing on the article information to obtain word segmentation results;

inputting each word segmentation result into a trained first conversion model to determine a word segmentation vector corresponding to each word segmentation result;

and integrating the word segmentation vectors to determine an article vector corresponding to the article information.

3. The method of claim 1, wherein converting each item information into an item vector comprises:

determining the browsing times of the articles corresponding to the article information to determine the browsing sequence of the articles;

and inputting the browsing sequence into a trained second conversion model to determine an article vector corresponding to each article information.

4. The method of claim 1, wherein the method of potential user determination comprises:

determining a plurality of first users;

determining a sample input sequence according to a plurality of item information determined by the item interaction behaviors of the first users, and determining a sample output sequence according to the intention item information of the first users;

and taking the sample input sequence as the input of an intention commodity prediction model, and taking the sample output sequence as the output of the intention commodity prediction model so as to train the intention commodity prediction model.

5. The potential user determination method of claim 1, wherein determining a target item based on the second item sequence comprises:

and taking the object contained in the second object sequence as a target object.

6. The potential user determination method of claim 1, wherein determining a target item based on the second item sequence comprises:

determining the items contained in the second item sequence as first candidate items;

determining an item similar to the first candidate item as a second candidate item;

determining the set of first candidate items and the second candidate items as target items.

7. The method of claim 6, wherein determining an item similar to the first candidate item as a second candidate item comprises:

calculating the similarity between the first candidate article and each other article in the article set;

and taking the article with the similarity larger than a preset similarity threshold value in the article set as a second candidate article.

8. The method of claim 1, wherein determining the item acquisition characteristic of the target user in conjunction with the information of the target item comprises:

determining a first characteristic of the target user according to the article interaction behavior of the target user in a first preset time period;

determining a second feature of the target user based on a user representation of the target user;

extracting basic information from the information of the target object, and determining a first characteristic of the target object according to the basic information;

extracting dynamic information from the information of the target object, and determining a second characteristic of the target object according to the dynamic information;

and combining the first characteristic and the second characteristic of the target user and the first characteristic and the second characteristic of the target item to determine the item acquisition characteristic of the target user.

9. The method of claim 1, further comprising:

determining a plurality of second users;

respectively determining the article acquisition characteristics of the second users;

determining user information of the existing intention behaviors in a second preset time period;

determining a training sample of a probability model based on the item acquisition features of the second users and the user information of the intentional behaviors existing in the second preset time period;

and training the probability model by using the training sample of the probability model.

10. The method of claim 9, wherein determining the item acquisition characteristic of each of the second users comprises:

determining a first characteristic of the second user according to the item interaction behavior of the second user within a third preset time period;

determining a second characteristic of the second user based on a user representation of the second user;

extracting basic information from information of a predetermined article, and determining a first characteristic of the predetermined article according to the basic information;

extracting dynamic information from the information of the predetermined article, and determining a second characteristic of the predetermined article according to the dynamic information;

combining the first and second characteristics of the second user and the first and second characteristics of the predetermined item to determine an item acquisition characteristic of the second user.

11. The method of claim 1, wherein determining whether the target user is a potential user for obtaining the target item according to the target item obtaining probability comprises:

judging whether the target article acquisition probability is greater than a preset probability threshold value or not;

and if the target item acquisition probability is greater than the preset probability threshold, determining the target user as a potential user for acquiring the target item.

12. The method of claim 11, wherein after determining that the target user is a potential user for obtaining the target item, the method further comprises:

if the target user has an intention achievement behavior aiming at the target object within a fourth preset time period, pushing first preferential information to the target user;

and if the target user does not have the intention reaching behavior aiming at the target item within the fourth preset time period, pushing second preferential information to the target user.

13. A potential user determination device, comprising:

the system comprises an article sequence construction module, an article sequence construction module and an article sequence management module, wherein the article sequence construction module is used for determining a plurality of article information according to article interaction behaviors of a target user, respectively converting each article information into an article vector, and constructing a first article sequence consisting of a plurality of article vectors;

the intention item prediction module is used for inputting the first item sequence into a trained intention item prediction model so as to determine a second item sequence;

the acquisition characteristic determining module is used for determining a target article based on the second article sequence and determining the article acquisition characteristic of the target user by combining the information of the target article;

and the potential user determining module is used for inputting the item acquisition characteristics into a trained probability model so as to determine the target item acquisition probability of the target user, and determining whether the target user is a potential user for acquiring the target item according to the target item acquisition probability.

14. A storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the potential user determination method of any one of claims 1 to 12.

15. An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the potential user determination method of any of claims 1-12 via execution of the executable instructions.