CN114329231A - Object feature processing method and device, electronic equipment and storage medium - Google Patents
Object feature processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114329231A CN114329231A CN202111679571.9A CN202111679571A CN114329231A CN 114329231 A CN114329231 A CN 114329231A CN 202111679571 A CN202111679571 A CN 202111679571A CN 114329231 A CN114329231 A CN 114329231A
- Authority
- CN
- China
- Prior art keywords
- data
- similar
- target
- sample
- nodes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides an object feature processing method and device, electronic equipment and a storage medium, and relates to the field of data processing, in particular to the technical field of artificial intelligence. The specific implementation scheme is as follows: acquiring object data of a target object, wherein the object data comprises behavior data of the target object and attribute data of the target object, and the activity of the target object is lower than the average activity in a preset object range; based on the object data, an object feature vector of the target object is predicted.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to a method and an apparatus for processing object features, an electronic device, and a storage medium.
Background
In the related art, when resource recommendation is performed on a user object, the following method is generally adopted: obtaining the operation history (for example, searching and clicking) of the user on the resources to obtain the vector representation of the user, then finding out similar users through the vector representation of the user and the vector representation of other users, predicting the preference of the current user according to the resource use conditions of the similar users, and recommending the related resources. However, when the method is used for resource recommendation, the current user needs to have rich operation history, otherwise the vector representation corresponding to the user object is not comprehensive, so that similar users found according to the vector representation are not accurate, the accuracy of resources recommended to the user is low, and the recommendation effect is poor.
Disclosure of Invention
The present disclosure provides a method, apparatus, device, and storage medium for object feature processing.
According to an aspect of the present disclosure, there is provided an object feature processing method, including: acquiring object data of a target object, wherein the object data comprises behavior data of the target object and attribute data of the target object, and the activity of the target object is lower than the average activity in a preset object range; based on the object data, an object feature vector of the target object is predicted.
Optionally, the method further includes: determining a target similar object similar to the target object based on the object feature vector and the similar feature vectors of the similar objects; determining resource content to be pushed based on the behavior data of the target similar object; and pushing the resource content to the target object.
Optionally, determining the target similar object similar to the target object based on the object feature vector and the similar feature vectors of the similar objects includes: acquiring Euclidean distance between the object feature vector and similar feature vectors of similar objects; and selecting the similar objects of which the Euclidean distance is smaller than a preset distance threshold value as the target similar objects.
Optionally, predicting an object feature vector of the target object based on the object data, comprising: and predicting the object characteristic vector of the target object by adopting a meta-learning network model based on the object data, wherein the meta-learning network model is obtained by training based on a plurality of groups of sample object data, the plurality of groups of sample object data comprise the object data of the sample object and the characteristic vector of the sample object, and the activity of the sample object is higher than the average activity.
Optionally, the method further includes: constructing an object resource map, wherein the object resource map is generated based on the wandering routes of a plurality of objects, and the object resource map comprises: the system comprises a plurality of object nodes and resource nodes which have one or more layers of incidence relations with the object nodes; screening a head node and a long tail node aiming at an object from an object resource graph, wherein the number of neighbor nodes of the head node is greater than or equal to a preset threshold value, and the number of neighbor nodes of the long tail node is less than the preset threshold value; and taking objects corresponding to part or all of the head nodes as sample objects.
Optionally, the object data of the sample object comprises: behavior data of the sample object and attribute data of the sample object.
According to another aspect of the present disclosure, there is provided an object feature processing apparatus including: the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring object data of a target object, the object data comprises behavior data of the target object and attribute data of the target object, and the activity of the target object is lower than the average activity in a preset object range; a prediction module to predict an object feature vector of the target object based on the object data.
Optionally, the apparatus further comprises: the first determination module is used for determining a target similar object similar to the target object based on the object feature vector and similar feature vectors of the similar objects; the second determination module is used for determining resource content to be pushed based on the behavior data of the target similar object; and the pushing module is used for pushing the resource content to the target object.
Optionally, the first determining module includes: the acquisition unit is used for acquiring Euclidean distance between the characteristic vector of the object and the similar characteristic vector of the similar object; and the selecting unit is used for selecting the similar objects of which the Euclidean distance is smaller than a preset distance threshold value from the similar objects as the target similar objects.
Optionally, the prediction module includes: the prediction unit is used for predicting the object characteristic vector of the target object by adopting a meta-learning network model based on the object data, wherein the meta-learning network model is obtained by training based on a plurality of groups of sample object data, the plurality of groups of sample object data comprise the object data of the sample object and the characteristic vector of the sample object, and the activity of the sample object is higher than the average activity.
Optionally, the prediction module further includes: a building unit, configured to build an object resource map, where the object resource map is generated based on a migration route of a plurality of objects, and the object resource map includes: the system comprises a plurality of object nodes and resource nodes which have one or more layers of incidence relations with the object nodes; the screening unit is used for screening a head node and a long tail node aiming at the object from the object resource graph, wherein the number of neighbor nodes of the head node is greater than or equal to a preset threshold value, and the number of neighbor nodes of the long tail node is less than the preset threshold value; and the processing unit is used for taking objects corresponding to part or all of the head nodes as sample objects.
Optionally, the object data of the sample object comprises: behavior data of the sample object and attribute data of the sample object.
According to still another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform any of the above-described methods.
According to yet another aspect of the disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform any of the above-described methods.
According to yet another aspect of the present disclosure, there is provided a computer program product comprising: a computer program which, when executed by a processor, implements any of the above-described methods.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
fig. 1 is a flowchart of an object feature processing method provided according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of an object feature processing method provided in accordance with an alternative embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a head node u first order neighbor;
FIG. 4 is a schematic diagram of a regression model structure;
fig. 5 is a block diagram of an object feature processing apparatus provided in accordance with an embodiment of the present disclosure;
fig. 6 is a block diagram of an electronic device for implementing an object feature processing method according to an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Description of the terms
Meta-Learning (Meta-Learning), the ability to learn how to learn, rather than Learning a particular task. Through meta learning, when an algorithm faces a new task, the algorithm can quickly learn by using a small amount of data only with learning capacity (namely priori knowledge).
u2u, User to User, emphasizes users and users establishing connections and associations on social platforms.
A User-based Collaborative Filtering, UCF for short, an algorithm for recommending based on a group of users with the same interest generally requires three steps, including: information that may represent the user's interest is collected, nearest neighbor searches are performed, and recommendation results are generated.
Topk, top k objects arranged in a set of orderings.
Dropout randomly leads some neurons not to participate in the current training when a large neural network is trained, so as to avoid overfitting caused by excessive noise of model learning, namely after the model is trained to a certain degree, the testing error obtained on the training set is far larger than that obtained on the testing set.
A fully-connected (FC) network architecture, a most basic neural network or deep neural network layer, where each node of the fully-connected layer is connected to all nodes of the previous layer.
In an embodiment of the present disclosure, an object feature processing method is provided, and fig. 1 is a flowchart of the object feature processing method provided according to the embodiment of the present disclosure, as shown in fig. 1, the flowchart includes the following steps:
step S102, object data of a target object are obtained, wherein the object data comprise behavior data of the target object and attribute data of the target object, and the activity of the target object is lower than the average activity in a preset object range;
in step S104, an object feature vector of the target object is predicted based on the object data.
Through the steps, the behavior data and the attribute data of the target object are obtained, and the characteristics of the target object with low liveness can be obtained more comprehensively. Moreover, when the target object is predicted, the adopted object data not only comprises the behavior data of the object, but also comprises the attribute data of the object, so that the vector representation of the low-activity object (the object with the activity lower than the average activity in the preset object range) can be more comprehensive, the low-activity object can be recommended more accurately, and the problems of inaccurate recommendation and poor recommendation effect of the low-activity object are solved.
As an alternative embodiment, after obtaining the prediction result of the object feature vector of the target object, various operations may be performed, for example, the following operations may be performed: determining a target similar object similar to the target object based on the object feature vector and the similar feature vectors of the similar objects; determining resource content to be pushed based on the behavior data of the target similar object; and pushing the resource content to the target object. By the method, the high-activity users similar to the low-activity users are obtained by utilizing the similarity of the feature vectors, and then the low-activity users are recommended according to the behavior data of the high-activity users, so that the accurate recommendation of the low-activity users can be realized, and the use interest of the users is improved.
As an alternative embodiment, when determining a target similar object similar to the target object based on the object feature vector and the similar feature vectors of the similar objects, various manners may be adopted, for example, the following manner may be adopted: acquiring Euclidean distance between the object feature vector and similar feature vectors of similar objects; and selecting the similar objects of which the Euclidean distance is smaller than a preset distance threshold value as the target similar objects. By obtaining the Euclidean distance between the characteristic vectors and screening out the users with the Euclidean distance smaller than the preset threshold value as the similar users of the target user, the similarity between the users can be quantitatively and accurately determined through the Euclidean distance between the characteristic vectors, therefore, the users with high activity similar to the users with low activity can be accurately found, the users with low activity are recommended according to the behavior data of the similar users with high activity, the recommendation accuracy is improved, and the recommendation effect is optimized. It should be noted that, the representation of the similarity between users by using the euclidean distance is only an optional implementation, and other ways of representing the similarity between users, such as cosine distance values, may also be used in other embodiments of the present application.
As an alternative embodiment, when predicting the object feature vector of the target object based on the object data, various prediction modes may be adopted, for example, the prediction mode may be implemented based on an artificial intelligence network model. For example, the object feature vector of the target object may be predicted by using a meta-learning network model based on the object data, where the meta-learning network model is trained based on a plurality of sets of sample object data, the plurality of sets of sample object data include the object data of the sample object and the feature vector of the sample object, and the activity of the sample object is higher than the average activity. The meta-learning network model is obtained by training the object data of the sample objects with the activity higher than the average activity and the feature vectors of the sample objects, so that the model can learn various richer features more efficiently, and the feature vectors of the users with low activity are predicted by utilizing the model, so that the obtained result is more accurate.
As an alternative embodiment, there may be a plurality of ways in determining the sample object, for example, the following ways may be used: constructing an object resource map, wherein the object resource map is generated based on the wandering routes of a plurality of objects, and the object resource map comprises: the system comprises a plurality of object nodes and resource nodes which have one or more layers of incidence relations with the object nodes; screening a head node and a long tail node aiming at an object from an object resource graph, wherein the number of neighbor nodes of the head node is greater than or equal to a preset threshold value, and the number of neighbor nodes of the long tail node is less than the preset threshold value; and taking objects corresponding to part or all of the head nodes as sample objects. By determining the sample objects in the manner, the sample objects can be ensured to be all users with higher liveness, more behavior data can be provided for the subsequent model learning process, so that the high efficiency and high accuracy of model learning are ensured, and the accuracy of the prediction result of the feature vector of the user with low liveness is further improved. In addition, the richness of the characteristics corresponding to each object can be systematically and comprehensively depicted in a mode of constructing the object resource graph. And screening out a head node and a long tail node aiming at the object based on the object resource graph, wherein the number of the neighbor nodes of the head node is greater than or equal to a preset threshold value, and the number of the neighbor nodes of the long tail node is less than the preset threshold value. Based on the determination mode for the head node and the long tail node of the object, the characteristics of the user can be determined quantitatively and standardly to a certain extent, so that the sample for training the meta-learning network model is relatively accurate and efficient.
As an alternative embodiment, the object data of the sample object may include various data, for example, may include: behavior data of the sample object, such as data of clicking, collecting, forwarding and commenting on resources by a user; attribute data of the sample object, such as data of gender, age, education level, and consumption level of the user. Through the data, the interest preference and the attribute characteristics of the user can be reflected in multiple directions, so that the prediction model is trained efficiently and comprehensively by utilizing the data, the prediction result of the model is more accurate, the high-activity user similar to the low-activity user can be found conveniently, the recommendation is completed, the recommendation accuracy for the low-activity user is greatly improved, and the recommendation effect is also improved.
Based on the above embodiments and alternative embodiments, an alternative implementation is provided, which is described below.
For users with low activity, the description of the users with low activity is not accurate no matter the vector representation of the users is obtained or the users are characterized according to the population attribute characteristics of the users, so that the method is not suitable for application scenes of a large number of users with low activity; and then lead to the problem that accurate recommendation can not be carried out, and the recommendation effect is poor.
In a user collaborative filtering recall method (for example, a novel is recommended to a user) in the related art, a user click sequence or a vector representation of the user is constructed based on a wandering graph model (i.e., the object resource graph), a cosine distance is calculated as the similarity of the user, similar users are obtained, and resource recall is performed according to a reading list of the similar users. However, the method has a good effect of representing vectors of users with rich behaviors, but has a poor effect of representing vectors of low-activity users with sparse behaviors (the correlation of offline evaluation u2u (User to User, u2u for short) is weak, and no obvious benefit is generated in an experiment when UCF (User-based Collaborative Filtering algorithm, UCF for short) is directly adopted on line for recalling in a vertical dialect recommendation scene, a large number of users with sparse behaviors exist in the vertical dialect recommendation scene (the number of novice resources of motors in the last month of about more than 83 percent of users of the novels is less than 5), so that the Collaborative Filtering recall of users in the related technology cannot meet the resource recall of a large number of low-activity users in the novice scene.
In the implementation process of the method, based on the collaborative filtering recall of the users, a user history reading list is constructed through the clicking preference of the users on the articles or the resources, user vector representation is obtained according to the user history reading list, and the similarity between the users is calculated through the user vectors. Finding a topk nearest neighbor user according to the similarity, predicting articles or resources liked by the current user according to the similarity weight of the adjacent user and the preference of the user on the articles or resources, and calculating to obtain a sorted article list for recommendation. The method is the most basic user recall method, is only suitable for recommendation scenes in which users with abundant behaviors exist, and is not suitable for recommendation scenes in which the behaviors are sparse and more users are recommended.
For another example, for a user with sparse behaviors, a user-item graph model (i.e., the above-mentioned object resource graph) is usually introduced, a vector representation of the user is obtained based on composition migration, and then recommendation of an item or a resource is performed by using the above-mentioned user-based collaborative filtering recall manner. In the practical process, the vector representation is not accurate enough for users with sparse behaviors, so that the user recalls resources with deviation, and the method is also not suitable for novel recommendation scenes.
However, for users with sparse behaviors, clustering recall may also be performed through the demographic characteristics of the users, and the like. However, only the population attribute characteristics of the users are adopted for clustering recall, the user behavior is characterized in a rough manner, and a large number of sparse users can influence the clustering effect.
Based on the above situation, in an alternative embodiment of the present disclosure, an object feature processing scheme is provided. Fig. 2 is a flowchart of an object feature processing method according to an alternative embodiment of the disclosure, where the flowchart includes the following processing as shown in fig. 2:
(1) the method for constructing a user-resource isomorphism map (similar to the above-mentioned object resource map, where users are taken as objects for example) by using the novel reading history, screening users and resources with high node degrees as head nodes, and training a meta-learning network model offline may include the following steps:
constructing a basic model: the method comprises the steps of taking a novel user reading history as a training sample, composing a picture to walk, and obtaining vector representation of users and resources by adopting a word2vec algorithm to be used as a basic model;
screening head nodes: constructing a user-resource isomorphic graph based on the original sample, screening head nodes (the number of neighbors is more than 5 and comprises users and resources), and acquiring head node vectors generated by the model;
acquiring user population attribute characteristics: in order to solve the problem of vector representation of the excessively sparse user, a knowledge distillation idea is adopted, and user population attribute characteristics (gender, age, education degree and consumption level) are introduced;
constructing a meta-learning task: randomly sampling dropout (the number of neighbors of each node is not more than 5) for the first-order neighbors of the head node, as shown in fig. 3, fig. 3 is a schematic diagram of the first-order neighbors of the head node u, constructing a meta-learning task, including constructing a test set with the nodes themselves, constructing a training set with the neighbors of the nodes, and model learning how to characterize the knowledge of the nodes themselves with the neighbors of the nodes (for example, as represented by a 3-layer Fully Connected (FC) network [512,128,32 ]). In the optional embodiment, the feature vectors of the long-tail users are mainly optimized, so that only the head nodes of the users are used in the training set and the test set, and all the neighbor nodes used in the training process are head nodes; summing Euclidean distances between each node type output vector in the test set and the training set and a basic model vector, constructing a training sample as shown in FIG. 4, wherein the training sample comprises 1-order neighbor node aggregation vectors (average pooling) with input characteristics being nodes and user population attribute characteristics, a model fitting target is a vector generated by the model, a loss function can be a model, and FIG. 4 is a structural schematic diagram of a meta-learning network model in an optional embodiment of the disclosure;
updating network parameters: and (3) iterative process meta-learning: in each training, constructing a sub-network based on meta-network parameters, firstly calculating loss of a training node and returning gradient to update sub-network parameters, then calculating test loss by using the updated sub-network, and repeating the process for k times (k is 5); and finally, testing loss and updating parameters of the meta-network by gradient optimization.
(2) And (2) utilizing the meta-learning network model obtained by training in the step (1) to predict the long-tail user node vector representation in an off-line manner, wherein the method can adopt the following steps:
screening long-tail user nodes: screening long tail node users from the user-resource same composition (for example, the total number of clicks of a novel resource in 30 days does not exceed 5);
construct meta-test (meta-test) task: obtaining long-tail user node vector representation: constructing a meta-test task in a similar way to a training set, wherein the testing set is a long-tail user node to be predicted, and the training set is a neighbor of the node; the calculation process is similar to that in training, and finally the vector representation of the user node is obtained.
(3) The method for constructing the meta-collaboration (meta-ucf) recall path on line comprises the following steps:
merging the updated long tail node vector with a user vector generated by the original model, and selecting a user with a click history of more than 5 as a core user to construct a u2u similarity matrix;
online add meta-collaboration (metaUCF) recall: and recalling the top fifty most similar users by each user, and recalling the novel resources clicked by the similar users by adopting a voting algorithm.
The implementation mode provides an effective low-activity user vector representation and user recommendation method aiming at the vertical scenes with a large number of low-activity users, and the method combines meta learning and recommendation service scenes to prove the feasibility of transfer learning in the recommendation scenes.
In an embodiment of the present disclosure, an object feature processing apparatus is further provided, and fig. 5 is a block diagram of a structure of the object feature processing apparatus provided according to the embodiment of the present disclosure, and as shown in fig. 5, the apparatus includes: an acquisition module 51 and a prediction module 52, which will be described below.
An obtaining module 51, configured to obtain object data of a target object, where the object data includes behavior data of the target object and attribute data of the target object, and an activity of the target object is lower than an average activity within a predetermined object range; and a prediction module 52, connected to the obtaining module 51, for predicting the object feature vector of the target object based on the object data.
As an alternative embodiment, the apparatus further comprises: the device comprises a first determining module, a second determining module and a pushing module, and the device is explained below.
A first determining module, connected to the predicting module, for determining a target similar object similar to the target object based on the object feature vector and the similar feature vectors of the similar objects; the second determining module is connected to the first determining module and used for determining the resource content to be pushed based on the behavior data of the target similar object; and the pushing module is connected to the second determining module and used for pushing the resource content to the target object.
As an alternative embodiment, the first determining module includes: the acquisition unit is used for acquiring Euclidean distance between the characteristic vector of the object and the similar characteristic vector of the similar object; and the selecting unit is used for selecting the similar objects of which the Euclidean distance is smaller than a preset distance threshold value from the similar objects as the target similar objects.
As an alternative embodiment, the prediction module may include: the prediction unit is used for predicting the object characteristic vector of the target object by adopting a meta-learning network model based on the object data, wherein the meta-learning network model is obtained by training based on a plurality of groups of sample object data, the plurality of groups of sample object data comprise the object data of the sample object and the characteristic vector of the sample object, and the activity of the sample object is higher than the average activity.
As an alternative embodiment, the prediction module may further include: a construction unit, a screening unit and a processing unit, which are described below.
A building unit, configured to build an object resource map, where the object resource map is generated based on a migration route of a plurality of objects, and the object resource map includes: the system comprises a plurality of object nodes and resource nodes which have one or more layers of incidence relations with the object nodes; the screening unit is connected to the building unit and used for screening a head node and a long tail node aiming at the object from the object resource graph, wherein the number of the neighbor nodes of the head node is greater than or equal to a preset threshold value, and the number of the neighbor nodes of the long tail node is less than the preset threshold value; and the processing unit is connected to the screening unit and is used for taking objects corresponding to part or all of the head nodes as sample objects.
As an alternative embodiment, the object data of the sample object includes: behavior data of the sample object and attribute data of the sample object.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 6 illustrates a schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 6, the electronic device (or device 600) includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
A number of components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, or the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 601 executes the respective methods and processes described above, such as the object feature processing method. For example, in some embodiments, the object feature processing method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the object feature processing method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the object feature processing method in any other suitable way (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (15)
1. An object feature processing method, comprising:
acquiring object data of a target object, wherein the object data comprises behavior data of the target object and attribute data of the target object, and the activity of the target object is lower than the average activity in a preset object range;
based on the object data, an object feature vector of the target object is predicted.
2. The method of claim 1, wherein the method further comprises:
determining a target similar object similar to the target object based on the object feature vector and similar feature vectors of similar objects;
determining resource content to be pushed based on the behavior data of the target similar object;
and pushing the resource content to the target object.
3. The method of claim 2, wherein the determining a target similar object similar to the target object based on the object feature vector and similar feature vectors of similar objects comprises:
acquiring Euclidean distance between the object feature vector and similar feature vectors of the similar objects;
and selecting the similar objects of which the Euclidean distance is smaller than a preset distance threshold value as the target similar objects.
4. The method of claim 1, wherein said predicting an object feature vector of the target object based on the object data comprises:
and predicting the object feature vector of the target object by adopting a meta-learning network model based on the object data, wherein the meta-learning network model is obtained by training based on a plurality of groups of sample object data, the plurality of groups of sample object data comprise the object data of the sample object and the feature vector of the sample object, and the activity of the sample object is higher than the average activity.
5. The method of claim 4, wherein the method further comprises:
building an object resource map, wherein the object resource map is generated based on the migration routes of a plurality of objects, and the object resource map comprises: the system comprises a plurality of object nodes and resource nodes which have one or more layers of incidence relations with the object nodes;
screening a head node and a long tail node for an object from the object resource graph, wherein the number of neighbor nodes of the head node is greater than or equal to a predetermined threshold value, and the number of neighbor nodes of the long tail node is less than the predetermined threshold value;
and taking objects corresponding to part or all of the head nodes as the sample objects.
6. The method of any of claims 4 to 5, wherein the object data of the sample object comprises: behavior data of the sample object and attribute data of the sample object.
7. An object feature processing apparatus comprising:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring object data of a target object, the object data comprises behavior data of the target object and attribute data of the target object, and the activity of the target object is lower than the average activity in a preset object range;
a prediction module to predict an object feature vector of the target object based on the object data.
8. The apparatus of claim 7, wherein the apparatus further comprises:
a first determination module, configured to determine a target similar object similar to the target object based on the object feature vector and similar feature vectors of similar objects;
the second determination module is used for determining resource content to be pushed based on the behavior data of the target similar object;
and the pushing module is used for pushing the resource content to the target object.
9. The apparatus of claim 8, wherein the first determining means comprises:
an obtaining unit, configured to obtain a euclidean distance between the object feature vector and a similar feature vector of the similar object;
and the selecting unit is used for selecting the similar objects of which the Euclidean distance is smaller than a preset distance threshold value as the target similar objects.
10. The apparatus of claim 9, wherein the prediction module comprises:
and the prediction unit is used for predicting the object characteristic vector of the target object by adopting a meta-learning network model based on the object data, wherein the meta-learning network model is obtained by training based on a plurality of groups of sample object data, the plurality of groups of sample object data comprise the object data of the sample object and the characteristic vector of the sample object, and the activity of the sample object is higher than the average activity.
11. The apparatus of claim 10, wherein the prediction module further comprises:
a building unit, configured to build an object resource map, where the object resource map is generated based on a migration route of a plurality of objects, and the object resource map includes: the system comprises a plurality of object nodes and resource nodes which have one or more layers of incidence relations with the object nodes;
the screening unit is used for screening a head node and a long tail node for an object from the object resource map, wherein the number of neighbor nodes of the head node is greater than or equal to a preset threshold value, and the number of neighbor nodes of the long tail node is less than the preset threshold value;
and the processing unit is used for taking objects corresponding to part or all of the head nodes as the sample objects.
12. The apparatus of any of claims 10 to 11, wherein the object data of the sample object comprises: behavior data of the sample object and attribute data of the sample object.
13. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.
14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1 to 6.
15. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111679571.9A CN114329231A (en) | 2021-12-31 | 2021-12-31 | Object feature processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111679571.9A CN114329231A (en) | 2021-12-31 | 2021-12-31 | Object feature processing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114329231A true CN114329231A (en) | 2022-04-12 |
Family
ID=81023756
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111679571.9A Pending CN114329231A (en) | 2021-12-31 | 2021-12-31 | Object feature processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114329231A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117132367A (en) * | 2023-10-20 | 2023-11-28 | 腾讯科技（深圳）有限公司 | Service processing method, device, computer equipment, storage medium and program product |
-
2021
- 2021-12-31 CN CN202111679571.9A patent/CN114329231A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117132367A (en) * | 2023-10-20 | 2023-11-28 | 腾讯科技（深圳）有限公司 | Service processing method, device, computer equipment, storage medium and program product |
| CN117132367B (en) * | 2023-10-20 | 2024-02-06 | 腾讯科技（深圳）有限公司 | Service processing method, device, computer equipment, storage medium and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ding et al. | Time-aware cloud service recommendation using similarity-enhanced collaborative filtering and ARIMA model | |
| CN112765477B (en) | Information processing method and device, information recommendation method and device, electronic equipment and storage medium | |
| CN111708876B (en) | Method and device for generating information | |
| CN111723292B (en) | Recommendation method, system, electronic equipment and storage medium based on graph neural network | |
| CN111651671B (en) | User object recommendation method, device, computer equipment and storage medium | |
| CN111259222A (en) | Article recommendation method, system, electronic device and storage medium | |
| CN112000763B (en) | Method, device, equipment and medium for determining competition relationship of interest points | |
| CN111814056A (en) | Supplier recommendation method based on information processing and related equipment | |
| CN110555172A (en) | user relationship mining method and device, electronic equipment and storage medium | |
| CN112989146A (en) | Method, apparatus, device, medium, and program product for recommending resources to a target user | |
| CN113569162A (en) | Data processing method, device, equipment and storage medium | |
| CN114329231A (en) | Object feature processing method and device, electronic equipment and storage medium | |
| JP7454630B2 (en) | Training method and device for label recommendation model, label acquisition method and device | |
| CN115329078B (en) | Text data processing method, device, equipment and storage medium | |
| CN115618079A (en) | Session recommendation method, device, electronic equipment and storage medium | |
| CN112905885B (en) | Method, apparatus, device, medium and program product for recommending resources to user | |
| CN113961797A (en) | Resource recommendation method and device, electronic equipment and readable storage medium | |
| CN115858911A (en) | Information recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN112818241A (en) | Content promotion method and device, computer equipment and storage medium | |
| CN113094584A (en) | Method and device for determining recommended learning resources | |
| CN113220983A (en) | Deep learning-based item selection method and device | |
| CN114637921B (en) | Item recommendation method, device and equipment based on modeling accidental uncertainty | |
| CN112749335B (en) | Lifecycle state prediction method, lifecycle state prediction apparatus, computer device, and storage medium | |
| CN115687778A (en) | Resource recommendation method, device, equipment and storage medium | |
| CN113987345A (en) | Data processing method, device, equipment, storage medium and program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |