CN115269996A - Data matching processing method and device - Google Patents
Data matching processing method and device Download PDFInfo
- Publication number
- CN115269996A CN115269996A CN202210991556.6A CN202210991556A CN115269996A CN 115269996 A CN115269996 A CN 115269996A CN 202210991556 A CN202210991556 A CN 202210991556A CN 115269996 A CN115269996 A CN 115269996A
- Authority
- CN
- China
- Prior art keywords
- data
- vector
- text
- preference data
- dimension
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a data matching processing method and device, and relates to the technical field of big data, wherein the method comprises the following steps: acquiring preference data of a target user, wherein the preference data comprises: preference data of text dimensions and preference data of image dimensions; uniformly converting the preference data of the text dimensionality and the preference data of the image dimensionality into target vectors; and inputting the target vector into a pre-established matching model to obtain a pushing result, wherein the pre-established matching model is obtained on the basis of joint training of text dimension data and image dimension data in historical data in a target platform. According to the scheme, the matching processing is carried out in the text dimension preference data and the image dimension preference data in the target user preference data in a centralized manner, so that the problem of low accuracy existing in the matching processing only through the text data can be solved, the matching success rate is effectively improved, and the technical effects of improving the clicking and purchasing rate of the user are achieved.
Description
Technical Field
The present application relates to the field of big data technologies, and in particular, to a data matching processing method and apparatus.
Background
The search matching is a service with wide requirements in electronic commerce, a user matches the needed commodities by inputting keywords, and the e-commerce platform can recommend the commodities which are more in line with the requirements of the platform and the user to the user in a search result according to historical behavior data, commodity quality, user preference, marketing requirements of the platform and the like of the user.
However, an effective solution is not proposed at present for how to effectively improve the accuracy of the matching result and the fitness between the matching result and the user requirement so as to improve the conversion rate of the article.
This section is intended to provide a background or context to the embodiments of the application that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
Disclosure of Invention
The embodiment of the application provides a data matching processing method and device, so that the accuracy of a matching result is improved, and the conversion rate of an article is improved.
The embodiment of the application also provides a data matching processing method and a device, wherein:
a data matching processing method obtains preference data of a target user, wherein the preference data comprises: preference data for text dimensions and preference data for image dimensions;
uniformly converting the preference data of the text dimension and the preference data of the image dimension into a target vector;
and inputting the target vector into a pre-established matching model to obtain a pushing result, wherein the pre-established matching model is obtained on the basis of joint training of text dimension data and image dimension data in historical data in a target platform.
In one embodiment, the matching model is built as follows:
acquiring a log file of the target platform;
calling historical behavior data from the log file;
acquiring a plurality of pieces of text dimension data and image dimension data from the historical behavior data;
carrying out segmentation, tiling and coding processing on each piece of text dimension data and image dimension data to obtain training data;
and training through the training data to obtain the matching model.
In one embodiment, the segmenting, tiling and encoding each piece of text dimension data and image dimension data to obtain a training data vector includes:
dividing a piece of image dimension data into a plurality of blocks, converting the plurality of blocks into a first vector, and adding index codes to the position of each block in the first vector;
dividing a piece of text dimension data into a plurality of segments, converting the plurality of segments into a second vector, and adding index codes to the position of each segment in the second vector;
and serially arranging the first vector and the second vector to serve as the training data.
In one embodiment, uniformly converting the preference data of the text dimension and the preference data of the image dimension into a target vector includes:
dividing the preference data of the image dimension into a plurality of blocks, converting the plurality of blocks into a third vector, and adding index codes to the positions of the blocks in the third vector;
dividing the preference data of the text dimension into a plurality of sections, converting the plurality of sections into a fourth vector, and adding index codes to the position of each section in the fourth vector;
and serially arranging the third vector and the fourth vector to be used as the target vector.
In one embodiment the target user's preference data comprises at least one of: the data corresponding to the click behavior of the target user, the data corresponding to the purchase behavior of the target user and the data corresponding to the behavior of which the viewing time of the target user exceeds a preset threshold value.
In one embodiment, inputting the target vector into a pre-established matching model to obtain a push result, including:
acquiring a search word input by a target user;
inputting the target vector and the search word into the pre-established matching model to obtain a search matching result;
and pushing the search matching result to the target user.
In one embodiment, a pre-established matching model is provided with a classification network layer, by which the output of a plurality of neurons is mapped to 0 and 1 based classification results.
A data match processing apparatus, comprising:
an obtaining module, configured to obtain preference data of a target user, where the preference data includes: preference data of text dimensions and preference data of image dimensions;
the conversion module is used for uniformly converting the preference data of the text dimension and the preference data of the image dimension into a target vector;
and the matching module is used for inputting the target vector into a pre-established matching model to obtain a pushing result, wherein the pre-established matching model is obtained on the basis of combined training of text dimensional data and image dimensional data in historical data in a target platform.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above method when executing the computer program.
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the above-mentioned method.
In the embodiment of the application, the preference data of the text dimensionality and the preference data of the image dimensionality in the preference data of the target user are subjected to matching processing in a concentrated mode, and compared with a scheme of performing matching processing only through the text data in the prior art, the method and the device can solve the problem that the accuracy is low when matching processing is performed only through the text data, achieve the technical effects of effectively improving the matching success rate and improving the click and purchase rate of the user.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
FIG. 1 is a flowchart of a method according to an embodiment of a data matching method provided herein;
FIG. 2 is a logic diagram of the data matching method provided herein;
fig. 3 is a block diagram of a hardware structure of an electronic device of a data matching processing method provided in the present application;
fig. 4 is a block diagram of an embodiment of a data matching processing apparatus provided in the present application.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present application are provided to explain the present application and should not be interpreted as limiting the present application.
Considering that the existing search matching is mostly closed loop formed by realizing algorithm and data, the algorithm and the data are continuously improved by methods such as A/B test and the like, so that the conversion rate of the articles obtained by search matching is continuously improved. Search matching based on plain text data can result in a large amount of details of user experience being lost due to loss of image dimensionality, and therefore the fitness of the final search recommendation result to the user is poor.
For example, data in non-image dimensions (i.e., data in text dimensions) may not fully express user preferences, such as: a user who is very disliked of the green picture sees that the picture in the recommended good is green, and the good may be subconsciously rejected. Although some can be expressed by adding non-image data, if the expression of similar words "the user dislikes yellow in green clothes" is encountered, the expression cannot be accurately expressed and controlled, the expression of the image is relatively stronger, and the data of the non-image dimension cannot completely express the surrounding environment information, such as: the overall page color system, etc.
In this example, a data matching processing method is provided, in which image data and text data (i.e., non-image data) are uniformly modeled, and image dimension data is added in comparison with an existing search matching method, so that more potential information of a user can be mined, and accuracy of search matching can be improved.
Fig. 1 is a flowchart of a method according to an embodiment of a data matching processing method provided in the present application. Although the present application provides method operational steps or apparatus configurations as illustrated in the following examples or figures, more or fewer operational steps or modular units may be included in the methods or apparatus based on conventional or non-inventive efforts. In the step or structure in which the necessary cause and effect relationship does not logically exist, the execution sequence of the steps or the module structure of the apparatus is not limited to the execution sequence or the module structure described in the embodiment of the present application and shown in the drawings. When the described method or module structure is applied in an actual device or end product, the method or module structure according to the embodiments or shown in the drawings can be executed sequentially or executed in parallel (for example, in a parallel processor or multi-thread processing environment, or even in a distributed processing environment).
Specifically, as shown in fig. 1, the data matching processing method may include the following steps:
step 101: acquiring preference data of a target user, wherein the preference data comprises: preference data for text dimensions and preference data for image dimensions;
wherein the target user's preference data may include, but is not limited to, at least one of: the data corresponding to the clicking behavior of the target user, the data corresponding to the purchasing behavior of the target user and the data corresponding to the behavior of which the viewing time of the target user exceeds a preset threshold value. The preference data of the text dimension can be description data of a user in a text form, description data of historical shopping behaviors of the user, the preference data of the image dimension can be commodity images or page images, and the plurality of images can be videos. For example, if a user clicks a certain product many times, an introduction video or a main image of the product may be acquired as the preference data of the image dimension.
Step 102: uniformly converting the preference data of the text dimension and the preference data of the image dimension into a target vector;
step 103: and inputting the target vector into a pre-established matching model to obtain a pushing result, wherein the pre-established matching model is obtained on the basis of joint training of text dimension data and image dimension data in historical data in a target platform.
The matching model can be established according to the following steps:
s1: acquiring a log file of the target platform;
that is, the target platform may be, for example: and processing the log file of the e-commerce platform to acquire each historical behavior data as basic data.
S2: calling historical behavior data from the log file;
the historical behavior data may include, but is not limited to: commodity data, user behavior data, user purchase history data, operation set target, and the like, which can be used to determine the possibility of purchase of the user.
S3: acquiring a plurality of pieces of text dimension data and image dimension data from the historical behavior data;
s4: segmenting, tiling and coding each piece of text dimensional data and image dimensional data to obtain training data;
s5: and training through the training data to obtain the matching model.
Specifically, each piece of text dimension data and image dimension data are subjected to segmentation, tiling and encoding processing to obtain a training data vector, wherein the training data vector can be obtained by dividing one piece of image dimension data into a plurality of blocks, converting the plurality of blocks into a first vector, and adding index encoding to the position of each block in the first vector; dividing a piece of text dimension data into a plurality of segments, converting the plurality of segments into a second vector, and adding index codes to the position of each segment in the second vector; and serially arranging the first vector and the second vector to serve as the training data.
For example, the image may be divided into 9 parts, and then the 9 parts of the image are converted into vectors, and then the vectors are added with position index codes 0,1,2,3 \8230, and \82308, or the text data may be converted into vectors, and then the vectors are added with position index codes, and then the text data and the vectors are arranged in series with the vectors of the image parts and input into the neural network structure.
For the preference data of the user, the preference data may also be uniformly converted into a target vector, specifically, the preference data of the image dimension may be divided into a plurality of blocks, the plurality of blocks are converted into a third vector, and an index code is added to a position of each block in the third vector; dividing the preference data of the text dimension into a plurality of segments, converting the plurality of segments into a fourth vector, and adding index codes to the position of each segment in the fourth vector; and serially arranging the third vector and the fourth vector to be used as the target vector.
The data matching processing method can be applied to data matching, for example, a user opens a target website or a target e-commerce platform to recommend a product to the user, and the product is determined to be displayed on a homepage, or applied to search, for example, the user inputs a search word in a search box of the e-commerce platform to match a search result.
That is, the inputting of the target vector into a matching model established in advance to obtain the pushing result may include: acquiring a search word input by a target user; inputting the target vector and the search word into the pre-established matching model to obtain a search matching result; and pushing the search matching result to the target user.
A classification network layer may be provided in the pre-established matching model, through which the outputs of the plurality of neurons are mapped to 0 and 1-based classification results. That is, the favorite data of the user may be used as input, passed through a plurality of neurons, and then mapped to the classification network layer, so as to obtain a probability value between 0 and 1, and based on the probability value, it is determined whether the user has interest in the current item, that is, it is determined whether the item needs to be pushed, or the probability value of each item is obtained, and several items ranked on TOPN are selected as pushed items.
When matching is actually performed, one of the following algorithms may be used: collaborative filtering, content recommendation, similarity recommendation, deep learning algorithms, and the like.
The above method is described below with reference to a specific embodiment, however, it should be noted that the specific embodiment is only for better describing the present application and is not to be construed as a limitation of the present application.
In this example, a data matching method is provided, which can perform unified modeling on image data (single image data or video data composed of multiple images) and text data as shown in fig. 2, so as to improve the completeness of the data, thereby implementing a search method for high-quality search matching.
Namely, aiming at the problems that the search engine is established based on non-image data, image information data are omitted, and data information related between the image data and characters is omitted, the image and non-image information are modeled in a unified mode and are optimized in an iterative mode, and therefore a better intelligent search engine can be generated. For example, an intelligent search engine can be formed by uniformly constructing user data, platform merchant data, commodity display pictures, commodity characters, whole page pictures and user behavior videos (or continuous images).
Specifically, a picture may be divided into 9 parts, the 9 parts of the picture are converted into a vector, a position index code 0,1,2,3.. 9 is added to the vector, and then the vector is input into the neural network structure. Or converting the characters of the non-picture part into vectors, adding position index codes to the vectors, then arranging the vectors in series with the vectors of the picture part, and inputting the vectors into the neural network structure.
The modeling can be divided into two steps:
s1: establishing a basic model:
1) Establishing data, constructing a piece of data with images and characters, and segmenting, tiling and coding the images and the characters according to the processing mode to obtain vectors; a large amount of the above data is constructed and stored by row.
2) And training a model, and performing model training through the constructed data.
S2: training a personalized recommendation model:
the user preference is established, specifically, the user preference can be established through data clicked or handed over by the user, the data clicked or handed over by the user can also be images and characters, and the images and the characters in the data clicked or handed over by the user are also converted into vectors, so that search matching is realized.
When the basic model is established, the model parameters can be initialized for the basic model, and then training can be performed through data with marks at the downstream.
On the basis of the basic network model, a classification network layer can be added for outputting whether a certain piece of data is liked by the user, for example, if the user likes, 1 is output, and if the user dislikes, 0 is output. Specifically, the classification layer may be implemented based on probability, and maps the output of a plurality of neurons into a (0, 1) interval, thereby implementing 0 and 1 classification to determine whether the user likes.
The method embodiments provided in the above embodiments of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Taking the electronic device as an example, fig. 3 is a block diagram of a hardware structure of the electronic device of the data matching processing method provided in the present application. As shown in fig. 3, the electronic device 10 may comprise one or more (only one shown in the figure) processors 02 (the processors 02 may comprise, but are not limited to, a processing means such as a microprocessor MCU or a programmable logic device FPGA), a memory 04 for storing data, and a transmission module 06 for communication functions. It will be understood by those skilled in the art that the structure shown in fig. 3 is only an illustration and is not intended to limit the structure of the electronic device. For example, the electronic device 10 may also include more or fewer components than shown in FIG. 3, or have a different configuration than shown in FIG. 3.
The memory 04 may be configured to store software programs and modules of application software, such as program instructions/modules corresponding to the data matching processing method in the embodiment of the present application, and the processor 02 executes various functional applications and data processing by operating the software programs and modules stored in the memory 04, that is, implements the short message sending method of the application program. The memory 04 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 04 may further include memory located remotely from the processor 02, which may be connected to the electronic device 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission module 06 is used for receiving or transmitting data via a network. Specific examples of such networks may include wireless networks provided by communication providers of the electronic device 10. In one example, the transmission module 06 includes a Network adapter (NIC) that can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission module 06 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In the software aspect, the data matching processing apparatus may be as shown in fig. 4, and include:
an obtaining module 401, configured to obtain preference data of a target user, where the preference data includes: preference data for text dimensions and preference data for image dimensions;
a conversion module 402, configured to uniformly convert the preference data of the text dimension and the preference data of the image dimension into a target vector;
a matching module 403, configured to input the target vector into a pre-established matching model to obtain a pushing result, where the pre-established matching model is obtained by performing joint training on text dimension data and image dimension data in historical data in a target platform.
In one embodiment, the matching model may be built as follows:
s1: acquiring a log file of the target platform;
s2: calling historical behavior data from the log file;
s3: acquiring a plurality of pieces of text dimension data and image dimension data from the historical behavior data;
s4: carrying out segmentation, tiling and coding processing on each piece of text dimension data and image dimension data to obtain training data;
s5: and training through the training data to obtain the matching model.
The segmenting, tiling and encoding processing is performed on each piece of text dimension data and image dimension data to obtain a training data vector, which may include: dividing a piece of image dimension data into a plurality of blocks, converting the plurality of blocks into a first vector, and adding index codes to the position of each block in the first vector; dividing a piece of text dimension data into a plurality of segments, converting the plurality of segments into a second vector, and adding index codes to the position of each segment in the second vector; and serially arranging the first vector and the second vector to serve as the training data.
The conversion module 402 may specifically divide the preference data of the image dimension into a plurality of blocks, convert the plurality of blocks into a third vector, and add an index code to a position of each block in the third vector; dividing the preference data of the text dimension into a plurality of segments, converting the plurality of segments into a fourth vector, and adding index codes to the position of each segment in the fourth vector; and serially arranging the third vector and the fourth vector to be used as the target vector.
In one embodiment, the preference data of the target user may include, but is not limited to, at least one of the following: the data corresponding to the click behavior of the target user, the data corresponding to the purchase behavior of the target user and the data corresponding to the behavior of which the viewing time of the target user exceeds a preset threshold value.
In an embodiment, the matching module 403 may be specifically configured to obtain a search term input by a target user; inputting the target vector and the search word into the pre-established matching model to obtain a search matching result; and pushing the search matching result to the target user.
In one embodiment, a classification network layer may be provided in the pre-established matching model, through which the outputs of the plurality of neurons are mapped to 0 and 1 based classification results.
An embodiment of the present application further provides a specific implementation manner of an electronic device, which is capable of implementing all steps in the data matching processing method in the foregoing embodiment, where the electronic device specifically includes the following contents: a processor (processor), a memory (memory), a communication Interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the processor is configured to invoke the computer program in the memory, and when executing the computer program, the processor implements all the steps in the data matching processing method in the foregoing embodiment, for example, when executing the computer program, the processor implements the following steps:
step 1: acquiring preference data of a target user, wherein the preference data comprises: preference data for text dimensions and preference data for image dimensions;
step 2: uniformly converting the preference data of the text dimension and the preference data of the image dimension into a target vector;
and 3, step 3: and inputting the target vector into a pre-established matching model to obtain a pushing result, wherein the pre-established matching model is obtained on the basis of joint training of text dimension data and image dimension data in historical data in a target platform.
From the above description, the embodiment of the application performs matching processing in the text dimension preference data and the image dimension preference data in the target user preference data, so that the problem of low accuracy in matching processing only through text data can be solved, the matching success rate is effectively improved, and the technical effects of improving the click rate and the purchase rate of users are achieved.
An embodiment of the present application further provides a computer-readable storage medium capable of implementing all the steps in the data matching processing method in the foregoing embodiment, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements all the steps in the data matching processing method in the foregoing embodiment, for example, when the processor executes the computer program, the processor implements the following steps:
step 1: acquiring preference data of a target user, wherein the preference data comprises: preference data of text dimensions and preference data of image dimensions;
step 2: uniformly converting the preference data of the text dimension and the preference data of the image dimension into a target vector;
and 3, step 3: and inputting the target vector into a pre-established matching model to obtain a pushing result, wherein the pre-established matching model is obtained on the basis of combined training of text dimensional data and image dimensional data in historical data in a target platform.
From the above description, the embodiment of the application performs matching processing in the text dimension preference data and the image dimension preference data in the target user preference data, so that the problem of low accuracy in matching processing only through text data can be solved, the matching success rate is effectively improved, and the technical effects of improving the click rate and the purchase rate of users are achieved.
According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Although the present application provides method steps as described in an embodiment or flowchart, additional or fewer steps may be included based on conventional or non-inventive efforts. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of sequences, and does not represent a unique order of performance. When an actual apparatus or client product executes, it may execute sequentially or in parallel (e.g., in the context of parallel processors or multi-threaded processing) according to the embodiments or methods shown in the figures.
The systems, apparatuses, modules or units described in the above embodiments may be specifically implemented by a computer chip or an entity, or implemented by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a vehicle-mounted human-computer interaction device, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
Although embodiments of the present description provide method steps as described in embodiments or flowcharts, more or fewer steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When implemented in an actual device or end product, can be executed sequentially or in parallel according to the methods shown in the embodiments or figures (e.g., parallel processor or multi-thread processing environments, even distributed data processing environments). The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded.
For convenience of description, the above devices are described as being divided into various modules by functions, which are described separately. Of course, in implementing the embodiments of the present description, the functions of each module may be implemented in one or more software and/or hardware, or a module implementing the same function may be implemented by a combination of multiple sub-modules or sub-units, and the like. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Those skilled in the art will also appreciate that, in addition to implementing the controller in purely computer readable program code means, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may therefore be considered as a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The embodiments of this specification may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The described embodiments may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
All the embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment. In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of an embodiment of the specification. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.
The above description is only an example of the embodiments of the present disclosure, and is not intended to limit the embodiments of the present disclosure. Various modifications and variations to the embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of the embodiments of the present invention should be included in the scope of the claims of the embodiments of the present invention.
Claims (10)
1. A data matching processing method is characterized by comprising the following steps:
acquiring preference data of a target user, wherein the preference data comprises: preference data for text dimensions and preference data for image dimensions;
uniformly converting the preference data of the text dimension and the preference data of the image dimension into a target vector;
and inputting the target vector into a pre-established matching model to obtain a pushing result, wherein the pre-established matching model is obtained on the basis of joint training of text dimension data and image dimension data in historical data in a target platform.
2. The method of claim 1, wherein the matching model is established as follows:
acquiring a log file of the target platform;
calling historical behavior data from the log file;
acquiring a plurality of pieces of text dimension data and image dimension data from the historical behavior data;
carrying out segmentation, tiling and coding processing on each piece of text dimension data and image dimension data to obtain training data;
and training through the training data to obtain the matching model.
3. The method of claim 2, wherein the segmenting, tiling, and encoding each piece of text dimension data and image dimension data to obtain a training data vector comprises:
dividing a piece of image dimension data into a plurality of blocks, converting the plurality of blocks into a first vector, and adding index codes to the positions of the blocks in the first vector;
dividing a piece of text dimension data into a plurality of segments, converting the plurality of segments into a second vector, and adding index codes to the position of each segment in the second vector;
and serially arranging the first vector and the second vector to serve as the training data.
4. The method of claim 1, wherein uniformly converting the text dimension preference data and the image dimension preference data into a target vector comprises:
dividing the preference data of the image dimension into a plurality of blocks, converting the plurality of blocks into a third vector, and adding index codes to the positions of the blocks in the third vector;
dividing the preference data of the text dimension into a plurality of sections, converting the plurality of sections into a fourth vector, and adding index codes to the position of each section in the fourth vector;
and serially arranging the third vector and the fourth vector to be used as the target vector.
5. The method of claim 1, wherein the target user's preference data comprises at least one of: the data corresponding to the click behavior of the target user, the data corresponding to the purchase behavior of the target user and the data corresponding to the behavior of which the viewing time of the target user exceeds a preset threshold value.
6. The method of claim 1, wherein inputting the target vector into a pre-established matching model to obtain a push result comprises:
acquiring a search word input by a target user;
inputting the target vector and the search word into the pre-established matching model to obtain a search matching result;
and pushing the search matching result to the target user.
7. The method of claim 1, wherein a pre-established matching model is provided with a classification network layer through which the output of the plurality of neurons is mapped to 0 and 1 based classification results.
8. A data matching processing apparatus, comprising:
an obtaining module, configured to obtain preference data of a target user, where the preference data includes: preference data for text dimensions and preference data for image dimensions;
the conversion module is used for uniformly converting the preference data of the text dimension and the preference data of the image dimension into a target vector;
and the matching module is used for inputting the target vector into a pre-established matching model to obtain a pushing result, wherein the pre-established matching model is obtained on the basis of the combined training of text dimension data and image dimension data in historical data in a target platform.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210991556.6A CN115269996A (en) | 2022-08-18 | 2022-08-18 | Data matching processing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210991556.6A CN115269996A (en) | 2022-08-18 | 2022-08-18 | Data matching processing method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115269996A true CN115269996A (en) | 2022-11-01 |
Family
ID=83752967
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210991556.6A Pending CN115269996A (en) | 2022-08-18 | 2022-08-18 | Data matching processing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115269996A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117764206A (en) * | 2024-02-21 | 2024-03-26 | 卓世智星(天津)科技有限公司 | Multi-model integration method and system |
-
2022
- 2022-08-18 CN CN202210991556.6A patent/CN115269996A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117764206A (en) * | 2024-02-21 | 2024-03-26 | 卓世智星(天津)科技有限公司 | Multi-model integration method and system |
CN117764206B (en) * | 2024-02-21 | 2024-05-07 | 卓世智星(天津)科技有限公司 | Multi-model integration method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110162701B (en) | Content pushing method, device, computer equipment and storage medium | |
CN109002488B (en) | Recommendation model training method and device based on meta-path context | |
CN104751354B (en) | A kind of advertisement crowd screening technique | |
CN110046301B (en) | Object recommendation method and device | |
CN112035743A (en) | Data recommendation method and device, computer equipment and storage medium | |
CN112989169B (en) | Target object identification method, information recommendation method, device, equipment and medium | |
CN111695960A (en) | Object recommendation system, method, electronic device and storage medium | |
US11720622B2 (en) | Machine learning multiple features of depicted item | |
CN113379449B (en) | Multimedia resource recall method and device, electronic equipment and storage medium | |
CN113254711A (en) | Interactive image display method and device, computer equipment and storage medium | |
CN115631012A (en) | Target recommendation method and device | |
CN115269996A (en) | Data matching processing method and device | |
CN115238191A (en) | Object recommendation method and device | |
CN114417161B (en) | Virtual article time sequence recommendation method, device, medium and equipment based on special-purpose map | |
Truong et al. | Exploring cross-modality utilization in recommender systems | |
CN111026910B (en) | Video recommendation method, device, electronic equipment and computer readable storage medium | |
CN114706987A (en) | Text category prediction method, device, equipment, storage medium and program product | |
Roy et al. | Genre based hybrid filtering for movie recommendation engine | |
CN111966916A (en) | Recommendation method and device, electronic equipment and computer readable storage medium | |
CN116881462A (en) | Text data processing, text representation and text clustering method and equipment | |
CN113327154B (en) | E-commerce user message pushing method and system based on big data | |
CN111507788A (en) | Data recommendation method and device, storage medium and processor | |
CN115618126A (en) | Search processing method, system, computer readable storage medium and computer device | |
CN112734519B (en) | Commodity recommendation method based on convolution self-encoder network | |
CN116127083A (en) | Content recommendation method, device, equipment and storage medium |
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 |