CN115393100A - Resource recommendation method and device - Google Patents
Resource recommendation method and device Download PDFInfo
- Publication number
- CN115393100A CN115393100A CN202211062071.5A CN202211062071A CN115393100A CN 115393100 A CN115393100 A CN 115393100A CN 202211062071 A CN202211062071 A CN 202211062071A CN 115393100 A CN115393100 A CN 115393100A
- Authority
- CN
- China
- Prior art keywords
- resource
- resource data
- data
- implicit
- vector corresponding
- 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
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Operations Research (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Computational Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Algebra (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The specification relates to the technical field of block chains, and particularly discloses a resource recommendation method and device, wherein the method comprises the following steps: acquiring historical resource behavior data of a target user; the historical resource behavior data comprises a plurality of resource data and behavior data of the target user on each resource data in the plurality of resource data; implicitly coding each resource data in the multiple resource data to obtain an implicit coding vector corresponding to each resource data; adjusting the weight of the implicit coding vector corresponding to each resource data based on the behavior data of each resource data to obtain the adjusted implicit coding vector corresponding to each resource data; and determining whether to recommend the resource data to be recommended to the target user according to the adjusted implicit coding vector corresponding to each resource data and the implicit coding vector corresponding to the resource data to be recommended. The scheme can improve the accuracy and efficiency of the resource recommendation data.
Description
Technical Field
The present disclosure relates to the field of block chain technologies, and in particular, to a resource recommendation method and apparatus.
Background
With the development of computer technology, more and more resources can be obtained by users, and it is difficult for users to quickly select interested resources from massive resources (such as movies, music, financial products, etc.).
In the related art, resources may be recommended to a user, for example, when a financial product is recommended to the user, social data of the user on a social platform for a period of time is acquired, and keywords associated with the financial product are extracted from the social data of the user. However, the target financial product determined based on the social data of the user may not meet the real demand of the user, and recommending the target financial product to the user may result in low effectiveness of the recommended resource.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the specification provides a resource recommendation method and device, and aims to solve the problem that the resource recommendation method in the prior art is low in effectiveness.
An embodiment of the present specification provides a resource recommendation method, including:
acquiring historical resource behavior data of a target user; the historical resource behavior data comprises a plurality of resource data and behavior data of the target user on each resource data in the plurality of resource data;
carrying out implicit coding on each resource data in the multiple resource data to obtain an implicit coding vector corresponding to each resource data;
adjusting the weight of the implicit coding vector corresponding to each resource data based on the behavior data of each resource data to obtain the adjusted implicit coding vector corresponding to each resource data;
and determining whether to recommend the resource data to be recommended to the target user according to the adjusted implicit coding vector corresponding to each resource data and the implicit coding vector corresponding to the resource data to be recommended.
In one embodiment, implicitly coding each resource data of the multiple resource data to obtain an implicit coding vector corresponding to each resource data includes:
and performing feature extraction on the text information corresponding to each resource data in the resource data by using a feature extraction model, outputting a high-dimensional vector, and obtaining an implicit coding vector corresponding to each resource data.
In one embodiment, the behavior data of the target user for the resource data includes at least one of: clicking behavior data, collecting behavior data, forwarding behavior data and transaction behavior data;
correspondingly, adjusting the weight of the implicit coded vector corresponding to each resource data based on the behavior data of each resource data to obtain the adjusted implicit coded vector corresponding to each resource data, includes:
and counting the behavior data corresponding to each resource data, and adjusting the weight of the implicit coded vector corresponding to each resource data according to the counting result to obtain the adjusted implicit coded vector corresponding to each resource data.
In one embodiment, the behavior data of the target user for the resource data comprises the latest browsing time of the resource data;
correspondingly, adjusting the weight of the implicit coding vector corresponding to each resource data based on the behavior data of each resource data to obtain an adjusted implicit coding vector corresponding to each resource data, including:
and adjusting the weight of the implicit coded vector corresponding to each resource data based on the time interval between the latest browsing time of each resource data and the current time to obtain the adjusted implicit coded vector corresponding to each resource data.
In one embodiment, determining whether to recommend the resource data to be recommended to the target user according to the adjusted implicit coding vector corresponding to each resource data and the implicit coding vector corresponding to the resource data to be recommended includes:
averaging the adjusted implicit coding vectors corresponding to the resource data to obtain target implicit coding vectors;
calculating the similarity between the target implicit coding vector and the implicit coding vector corresponding to the resource to be recommended;
and recommending the resource data to be recommended to the target user under the condition that the similarity is greater than the preset similarity.
In one embodiment, calculating the similarity between the target implicit coding vector and the implicit coding vector corresponding to the resource to be recommended includes:
calculating the spatial distance between the target implicit coding vector and the resource to be recommended;
and determining the similarity between the target implicit coding vector and the implicit coding vector corresponding to the resource to be recommended based on the spatial distance between the target implicit coding vector and the resource to be recommended.
An embodiment of the present specification further provides a resource recommendation device, including: the acquisition module is used for acquiring historical resource behavior data of a target user; the historical resource behavior data comprises a plurality of resource data and behavior data of the target user on each resource data in the plurality of resource data;
implicitly coding each resource data in the multiple resource data to obtain an implicit coding vector corresponding to each resource data;
adjusting the weight of the implicit coding vector corresponding to each resource data based on the behavior data of each resource data to obtain the adjusted implicit coding vector corresponding to each resource data;
and determining whether to recommend the resource data to be recommended to the target user according to the adjusted implicit coding vector corresponding to each resource data and the implicit coding vector corresponding to the resource data to be recommended.
Embodiments of the present specification further provide a computer device, including a processor and a memory for storing processor-executable instructions, where the processor executes the instructions to implement the steps of the resource recommendation method in any of the above embodiments.
Embodiments of the present specification further provide a computer-readable storage medium, on which computer instructions are stored, and when executed, the instructions implement the steps of the resource recommendation method described in any of the above embodiments.
Embodiments of the present specification further provide a computer program product, which includes a computer program/instruction, and when executed by a processor, the computer program/instruction implements the steps of the resource recommendation method described in any of the above embodiments.
In an embodiment of the present specification, a resource recommendation method is provided, where a server may obtain historical resource behavior data of a target user, where the historical resource behavior data may include multiple resource data and behavior data of the target user on each resource data in the multiple resource data, perform implicit coding on each resource data in the multiple resource data to obtain an implicit coding vector corresponding to each resource data, then adjust a weight of the implicit coding vector corresponding to each resource data based on the behavior data of each resource data to obtain an adjusted implicit coding vector corresponding to each resource data, and determine whether to recommend the resource data to be recommended to the target user according to the adjusted implicit coding vector corresponding to each resource data and the implicit coding vector corresponding to the resource data to be recommended. In the above scheme, the implicit coding vector may be obtained by extracting features of the resource data, and then the weight adjustment in the preference dimension and the time dimension may be performed on the feature vector by using behavior data of each resource data of the multiple resource data of the target user, so as to characterize the preference of the user for the multiple resource data, for example, the expected income and risk preference of the user for financial products may be analyzed, and then similar financial products may be recommended for the user based on the features characterizing the expected income and risk preference of the user, so that the effectiveness and efficiency of resource recommendation may be improved, and the user experience may be improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification, are incorporated in and constitute a part of this specification, and are not intended to limit the specification. In the drawings:
FIG. 1 is a diagram illustrating an application scenario of a resource recommendation method in an embodiment of the present specification;
FIG. 2 is a flow diagram illustrating a resource recommendation method in one embodiment of the present specification;
FIG. 3 is a flow diagram illustrating a resource recommendation method in one embodiment of the present specification;
FIG. 4 is a schematic diagram of a resource recommendation device in one embodiment of the present specification;
FIG. 5 shows a schematic diagram of a computer device in one embodiment of the present description.
Detailed Description
The principles and spirit of the present description will be described below with reference to several exemplary embodiments. It is understood that these embodiments are presented merely to enable those skilled in the art to better understand and to implement the description, and are not intended to limit the scope of the description in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As will be appreciated by one skilled in the art, embodiments of the present description may be embodied as a system, an apparatus, a method, or a computer program product. Accordingly, the present disclosure may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.
According to the technical scheme, the data acquisition, storage, use, processing and the like meet the relevant regulations of national laws and regulations.
The embodiment of the specification provides a resource recommendation method. Fig. 1 is a schematic diagram illustrating an application scenario of a resource recommendation method in an embodiment of the present specification. As shown in fig. 1, a server may receive a resource recommendation request sent by a client, where the resource recommendation request may carry a user identifier of a target user. The server can respond to the resource recommendation request and acquire historical resource behavior data corresponding to the user identification from the database. The historical resource behavior data of the target user may include a plurality of resource data and behavior data of the target user for each resource data of the plurality of resource data. The server can perform implicit coding on each resource data in the multiple resource data to obtain an implicit coding vector corresponding to each resource data. Then, the server may adjust the weight of the implicit coding vector corresponding to each resource data based on the behavior data of each resource data, so as to obtain an adjusted implicit coding vector corresponding to each resource data. The server may determine whether to recommend the resource data to be recommended to the client of the target user according to the adjusted implicit coding vector corresponding to each resource data and the implicit coding vector corresponding to the resource data to be recommended.
Fig. 2 shows a flowchart of a resource recommendation method in an embodiment of the present specification. Although the present specification 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 specification 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. 2, a resource recommendation method provided in an embodiment of the present specification may include the following steps:
step S201, acquiring historical resource behavior data of a target user; the historical resource behavior data comprises a plurality of resource data and behavior data of the target user on each resource data in the plurality of resource data.
Specifically, the method in the present embodiment may be applied to a server. The server can receive a resource recommendation request sent by the client. The resource recommendation request can be sent by the user through the client actively, or can be sent automatically by the application program in the client under the specified condition. The resource recommendation request may carry a user identifier of the target user.
The server can respond to the resource recommendation request and obtain historical resource behavior data of the target user based on the user identification. The historical resource behavior data may include a plurality of resource data and behavior data of the target user for each resource data of the plurality of resource data.
Step S202, each resource data in the multiple resource data is coded in an implicit mode, and an implicit coding vector corresponding to each resource data is obtained.
After obtaining the historical resource behavior data of the target object, the server may perform implicit coding on each resource data in the multiple resource data to obtain an implicit coding vector corresponding to each resource data.
In some embodiments of this specification, implicitly coding each resource data in the multiple resource data to obtain an implicit coding vector corresponding to each resource data may include: and performing feature extraction on the text information corresponding to each resource data in the resource data by using a feature extraction model, outputting a high-dimensional vector, and obtaining an implicit coding vector corresponding to each resource data. The feature extraction model may include a feature processing model such as LSTM and Transformer. The text information can be processed and then high-dimensional vectors are output, rich information meanings in the text are expressed in a high-dimensional space, and the richness of features is further improved while the text information is converted into data information which can be processed by a computer.
Implicit coding vectors may characterize implicit commonality characteristics of resource data. The same features of different products implicit in the text information are represented in the form of high-dimensional space vectors. For example, these characteristics may specifically include implicit profitability and risk preferences, product type, and the like.
Step S203, adjusting the weight of the implicit coded vector corresponding to each resource data based on the behavior data of each resource data, to obtain an adjusted implicit coded vector corresponding to each resource data.
After the 0 implicit coding vector of each resource data is obtained, the weight of the implicit coding vector corresponding to each resource data may be adjusted based on the behavior data of each resource data, so as to obtain an adjusted implicit coding vector. For example, the weight may be adjusted according to the number of times of user clicking, collecting, forwarding and the like, or according to the length and the distance of browsing time.
Step S204, determining whether to recommend the resource data to be recommended to the target user according to the adjusted implicit coding vector corresponding to each resource data and the implicit coding vector corresponding to the resource data to be recommended.
And then, whether the resource data to be recommended is recommended to the target user can be determined according to the adjusted implicit coding vector corresponding to each resource data and the implicit coding vector corresponding to the resource data to be recommended. For example, whether the behavior data of the resource data similar to the resource data to be recommended meets the preset condition may be determined according to the similarity between the implicit coding vector corresponding to the resource data to be recommended and the adjusted implicit coding vector corresponding to each resource data, for example, if the behavior data of the resource data similar to the resource data to be recommended includes behaviors of purchasing, clicking, collecting, forwarding and the like, the recommendation is performed.
In the above embodiment, the implicit coding vector may be obtained by extracting features of the resource data, then the weight adjustment in the preference dimension and the time dimension may be performed on the feature vector by using behavior data of each resource data of the multiple resource data of the target user, so as to characterize the preference of the user for the multiple resource data, for example, the expected income and risk preference of the user for financial products may be analyzed, then, similar financial products may be recommended for the user based on the features characterizing the expected income and risk preference of the user, so that the effectiveness and efficiency of resource recommendation may be improved, and the user experience may be improved.
The server can adjust the weight of the implicit coding vectors corresponding to the resource data in the user preference dimension according to whether the user has behavior data such as collection, forwarding and purchasing. Specifically, in some embodiments of the present specification, the behavior data of the target user for the resource data may include at least one of: clicking behavior data, collecting behavior data, forwarding behavior data, transaction behavior data and browsing duration; correspondingly, adjusting the weight of the implicit coding vector corresponding to each resource data based on the behavior data of each resource data to obtain the adjusted implicit coding vector corresponding to each resource data may include: and counting the behavior data corresponding to each resource data, and adjusting the weight of the implicit coded vector corresponding to each resource data according to the counting result to obtain the adjusted implicit coded vector corresponding to each resource data. For example, the target user is more biased towards the resource data corresponding to the implicitly encoded vector with the higher weight. In the case that the resource data to be recommended is similar to the diet coding vector with higher weight, the recommendation can be made to the target user. By the method, the effectiveness of resource recommendation can be improved.
The server can perform weight adjustment on the time dimension on the implicit coding vector corresponding to each resource data according to the browsing time of the user. Specifically, in some embodiments of the present specification, the behavior data of the target user for the resource data may include a latest browsing time of the resource data; correspondingly, adjusting the weight of the implicit coding vector corresponding to each resource data based on the behavior data of each resource data to obtain the adjusted implicit coding vector corresponding to each resource data may include: and adjusting the weight of the implicit coded vector corresponding to each resource data based on the time interval between the latest browsing time of each resource data and the current time to obtain the adjusted implicit coded vector corresponding to each resource data.
In one embodiment, the product implicit coding vector is weight adjusted in the time dimension according to time. For example, the weight adjustment may be performed according to the following formula:
wherein, score i Score for ith click record, t 0 Representing the current time, t i And k and b are constants and represent the occurrence time of the ith click record. The earlier the browsing time point of the resource data is from the present, the lower the contribution of the browsing history to the product.
Referring to fig. 3, a flowchart of a resource recommendation method in the present embodiment is shown. As shown in fig. 3, in some embodiments of the present specification, determining whether to recommend the resource data to be recommended to the target user according to the adjusted implicit coding vector corresponding to each resource data and the implicit coding vector corresponding to the resource data to be recommended may include:
step S301, averaging the adjusted implicit coding vectors corresponding to the resource data to obtain a target implicit coding vector;
step S302, calculating the similarity between the target implicit coding vector and the implicit coding vector corresponding to the resource to be recommended;
and step S303, recommending the resource data to be recommended to the target user under the condition that the similarity is greater than the preset similarity.
Specifically, all resource data are sorted according to the occurrence sequence of click time, for the ith resource data, N resource data in front of the ith resource data are selected, and the average value of the implicit vectors of the N resource data is calculated to serve as the user windage yaw and income expectation guidance to obtain the target implicit coding vector. Then, the similarity between the target implicit coding vector and the implicit coding vector corresponding to the resource to be recommended can be calculated. And recommending the resource data to be recommended to the target user under the condition that the similarity is greater than the preset similarity. By the method, whether the current resource data to be recommended is recommended to the target user can be conveniently determined.
In some embodiments of the present specification, calculating a similarity between the target implicit coding vector and the implicit coding vector corresponding to the resource to be recommended may include: calculating the spatial distance between the target implicit coding vector and the resource to be recommended; and determining the similarity between the target implicit coding vector and the implicit coding vector corresponding to the resource to be recommended based on the spatial distance between the target implicit coding vector and the resource to be recommended. The spatial distance may include a euclidean distance, a manhattan distance, and the like. Through the method, the similarity between the target implicit coding vector and the coding vector of the resource data to be recommended can be obtained.
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. For details, reference may be made to the description of the related embodiments of the related processing, and details are not repeated herein.
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.
The above method is described below with reference to a specific example, however, it should be noted that the specific example is only for better describing the present specification and should not be construed as an undue limitation on the present specification.
The embodiment provides a resource data recommendation method. The resource data in this embodiment may include financial products. Specifically, the method in the present embodiment may include the following.
The data collection process is that for a user 1, all product records clicked by the user are captured, the clicking behavior of the user reflects the risk preference and the income expectation of the user, and when a certain product is similar to the risk preference and the income expectation, the product is more easily attracted by the user and the clicking behavior occurs. Therefore, the endogenous preference of the user can be obtained by extracting past browsing product records of the user. Collecting behavior data of browsing time, collection, forwarding and the like of a user after clicking;
all financial products that have click behavior can be implicitly coded using text processing tools to extract their internal implicit commonalities. Through this process, text information that is rendered computationally infeasible by a computer is converted into digital information.
The weight adjustment on the user preference dimension can be carried out on the product implicit coding vector according to whether the user has behavior data such as collection, forwarding and the like and the user browsing time;
the product implicit coding vector can be subjected to weight adjustment in a time dimension according to time.
Wherein t0 represents the current time, ti represents the occurrence time of the ith click record, and k and b are constants.
The financial products can be sorted according to the occurrence sequence of clicking time, for the ith financial product, the N financial products in front of the ith financial product are selected, the average value of the implicit vectors of the N products is calculated to serve as the expected guidance of the wind bias and the income of the user, the final result is obtained after the average value is fused with the implicit vectors of the ith financial product, the degree of fit between the product and the preference of the user is judged, and finally whether the recommendation service is carried out on the user is determined according to the test result of the wind bias of the user.
The method in the embodiment improves the recommendation capability of the financial products, and can recommend the financial products suitable for the windage yaw of the user according to the preference of the user; the processing speed is high, the error rate is low, and a large amount of time cost and labor cost can be saved; has high mobility, low migration cost, wide application range and low popularization cost.
Based on the same inventive concept, the embodiment of the present specification further provides a resource recommendation device, as described in the following embodiments. Because the principle of the resource recommendation device for solving the problems is similar to the resource recommendation method, the resource recommendation device can be implemented by the resource recommendation method, and repeated parts are not described again. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated. Fig. 4 is a block diagram of a configuration of a resource recommendation device according to an embodiment of the present specification, and as shown in fig. 4, the resource recommendation device includes: an obtaining module 401, an encoding module 402, an adjusting module 403, and a recommending module 404, which are described below.
The obtaining module 401 is configured to obtain historical resource behavior data of a target user; the historical resource behavior data comprises a plurality of resource data and behavior data of the target user on each resource data in the plurality of resource data.
The encoding module 402 is configured to perform implicit encoding on each resource data in the multiple resource data to obtain an implicit encoding vector corresponding to each resource data.
The adjusting module 403 is configured to adjust the weight of the implicit coding vector corresponding to each resource data based on the behavior data of each resource data, so as to obtain an adjusted implicit coding vector corresponding to each resource data.
The recommending module 404 is configured to determine whether to recommend the resource data to be recommended to the target user according to the adjusted implicit coding vector corresponding to each resource data and the implicit coding vector corresponding to the resource data to be recommended.
In some embodiments of the present description, the encoding module may be specifically configured to: and performing feature extraction on the text information corresponding to each resource data in the resource data by using a feature extraction model, outputting a high-dimensional vector, and obtaining an implicit coding vector corresponding to each resource data.
In some embodiments of the present specification, the behavior data of the target user for the resource data includes at least one of: clicking behavior data, collecting behavior data, forwarding behavior data and transaction behavior data; correspondingly, the adjusting module may be specifically configured to: and counting the behavior data corresponding to each resource data, and adjusting the weight of the implicit coded vector corresponding to each resource data according to the counting result to obtain the adjusted implicit coded vector corresponding to each resource data.
In some embodiments of the present specification, the behavior data of the target user for the resource data includes a latest browsing time of the resource data; correspondingly, the adjusting module may be specifically configured to: and adjusting the weight of the implicit coding vector corresponding to each resource data based on the time interval between the latest browsing time of each resource data and the current time to obtain the adjusted implicit coding vector corresponding to each resource data.
In some embodiments of the present description, the recommendation module may be specifically configured to: calculating the mean value of the adjusted implicit coding vectors corresponding to the resource data to obtain a target implicit coding vector; calculating the similarity between the target implicit coding vector and the implicit coding vector corresponding to the resource to be recommended; and recommending the resource data to be recommended to the target user under the condition that the similarity is greater than the preset similarity.
In some embodiments of the present specification, calculating a similarity between the target implicit coding vector and the implicit coding vector corresponding to the resource to be recommended includes: calculating the spatial distance between the target implicit coding vector and the resource to be recommended; and determining the similarity between the target implicit coding vector and the implicit coding vector corresponding to the resource to be recommended based on the spatial distance between the target implicit coding vector and the resource to be recommended.
From the above description, it can be seen that the embodiments of the present specification achieve the following technical effects: the implicit coding vector can be obtained by extracting the characteristics of the resource data, then the weight adjustment on the preference dimension and the time dimension can be carried out on the characteristic vector through the behavior data of the target user on each resource data in the multiple resource data, the preference of the user on the multiple resource data can be represented, for example, the expected income and risk preference of the user on financial products can be analyzed, then similar financial products can be recommended for the user based on the characteristics representing the expected income and risk preference of the user, the effectiveness and efficiency of resource recommendation can be improved, and the user experience is improved.
The embodiment of the present specification further provides a computer device, which may specifically refer to fig. 5, where the computer device according to the resource recommendation method provided in the embodiment of the present specification is configured by a schematic structural diagram, and the computer device may specifically include an input device 51, a processor 52, and a memory 53. Wherein the memory 53 is configured to store processor-executable instructions. The processor 52, when executing the instructions, performs the steps of the resource recommendation method described in any of the embodiments above.
In this embodiment, the input device may be one of the main devices for exchanging information between a user and a computer system. The input device may include a keyboard, a mouse, a camera, a scanner, a light pen, a handwriting input board, a voice input device, etc.; the input device is used to input raw data and a program for processing these numbers into the computer. The input device can also acquire and receive data transmitted by other modules, units and devices. The processor may be implemented in any suitable way. For example, the processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller and embedded microcontroller, and so forth. The memory may in particular be a memory device used in modern information technology for storing information. The memory may include multiple levels, and in a digital system, the memory may be any memory as long as it can store binary data; in an integrated circuit, a circuit without a physical form and with a storage function is also called a memory, such as a RAM, a FIFO and the like; in the system, the storage device in physical form is also called a memory, such as a memory bank, a TF card and the like.
In this embodiment, the functions and effects of the specific implementation of the computer device can be explained in comparison with other embodiments, and are not described herein again.
The present specification also provides a computer storage medium based on a resource recommendation method, where the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the computer storage medium implements the steps of the resource recommendation method in any of the above embodiments.
In this embodiment, the storage medium includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Cache (Cache), a Hard Disk Drive (HDD), or a Memory Card (Memory Card). The memory may be used to store computer program instructions. The network communication unit may be an interface for performing network connection communication, which is set in accordance with a standard prescribed by a communication protocol.
In this embodiment, the functions and effects specifically realized by the program instructions stored in the computer storage medium can be explained by comparing with other embodiments, and are not described herein again.
Embodiments of the present specification further provide a computer program product, which includes a computer program/instruction, and when executed by a processor, the computer program/instruction implements the steps of the resource recommendation method described in any of the above embodiments.
It will be apparent to those skilled in the art that the modules or steps of the embodiments of the present specification described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed over a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different from that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, embodiments of the present description are not limited to any specific combination of hardware and software.
It is to be understood that the above description is intended to be illustrative, and not restrictive. Many embodiments and many applications other than the examples provided will be apparent to those of skill in the art upon reading the above description. The scope of the description should, therefore, be determined not with reference to the above description, but should instead be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.
The above description is only a preferred embodiment of the present disclosure, and is not intended to limit the present disclosure, and it will be apparent to those skilled in the art that various modifications and variations can be made in the embodiment of the present disclosure. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present specification shall be included in the protection scope of the present specification.
Claims (10)
1. A method for resource recommendation, comprising:
acquiring historical resource behavior data of a target user; the historical resource behavior data comprises a plurality of resource data and behavior data of the target user on each resource data in the plurality of resource data;
implicitly coding each resource data in the multiple resource data to obtain an implicit coding vector corresponding to each resource data;
adjusting the weight of the implicit coding vector corresponding to each resource data based on the behavior data of each resource data to obtain the adjusted implicit coding vector corresponding to each resource data;
and determining whether to recommend the resource data to be recommended to the target user according to the adjusted implicit coding vector corresponding to each resource data and the implicit coding vector corresponding to the resource data to be recommended.
2. The resource recommendation method according to claim 1, wherein implicitly coding each resource data of the plurality of resource data to obtain an implicit coding vector corresponding to each resource data comprises:
and performing feature extraction on the text information corresponding to each resource data in the resource data by using a feature extraction model, outputting a high-dimensional vector, and obtaining an implicit coding vector corresponding to each resource data.
3. The resource recommendation method according to claim 1, wherein the behavior data of the target user for the resource data comprises at least one of: clicking behavior data, collecting behavior data, forwarding behavior data and transaction behavior data;
correspondingly, adjusting the weight of the implicit coded vector corresponding to each resource data based on the behavior data of each resource data to obtain the adjusted implicit coded vector corresponding to each resource data, includes:
and counting the behavior data corresponding to each resource data, and adjusting the weight of the implicit coded vector corresponding to each resource data according to the counting result to obtain the adjusted implicit coded vector corresponding to each resource data.
4. The resource recommendation method according to claim 1, wherein the behavior data of the target user for the respective resource data includes a latest browsing time for the respective resource data;
correspondingly, adjusting the weight of the implicit coding vector corresponding to each resource data based on the behavior data of each resource data to obtain an adjusted implicit coding vector corresponding to each resource data, including:
and adjusting the weight of the implicit coding vector corresponding to each resource data based on the time interval between the latest browsing time of each resource data and the current time to obtain the adjusted implicit coding vector corresponding to each resource data.
5. The resource recommendation method according to claim 1, wherein determining whether to recommend the resource data to be recommended to the target user according to the adjusted implicit coding vector corresponding to each resource data and the implicit coding vector corresponding to the resource data to be recommended includes:
averaging the adjusted implicit coding vectors corresponding to the resource data to obtain target implicit coding vectors;
calculating the similarity between the target implicit coding vector and the implicit coding vector corresponding to the resource to be recommended;
and recommending the resource data to be recommended to the target user under the condition that the similarity is greater than the preset similarity.
6. The resource recommendation method according to claim 5, wherein calculating the similarity between the target implicit coding vector and the implicit coding vector corresponding to the resource to be recommended comprises:
calculating the spatial distance between the target implicit coding vector and the resource to be recommended;
and determining the similarity between the target implicit coding vector and the implicit coding vector corresponding to the resource to be recommended based on the spatial distance between the target implicit coding vector and the resource to be recommended.
7. A resource recommendation device, comprising:
the acquisition module is used for acquiring historical resource behavior data of a target user; the historical resource behavior data comprises a plurality of resource data and behavior data of the target user on each resource data in the plurality of resource data;
the encoding module is used for carrying out implicit encoding on each resource data in the multiple resource data to obtain an implicit encoding vector corresponding to each resource data;
the adjusting module is used for adjusting the weight of the implicit coding vector corresponding to each resource data based on the behavior data of each resource data to obtain the adjusted implicit coding vector corresponding to each resource data;
and the recommending module is used for determining whether to recommend the resource data to be recommended to the target user according to the adjusted implicit coding vector corresponding to each resource data and the implicit coding vector corresponding to the resource data to be recommended.
8. A computer device comprising a processor and a memory for storing processor-executable instructions which, when executed by the processor, implement the steps of the method of any one of claims 1 to 6.
9. A computer-readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the steps of the method of any one of claims 1 to 6.
10. A computer program product comprising computer programs/instructions, characterized in that the computer programs/instructions, when executed by a processor, implement the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211062071.5A CN115393100A (en) | 2022-08-31 | 2022-08-31 | Resource recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211062071.5A CN115393100A (en) | 2022-08-31 | 2022-08-31 | Resource recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115393100A true CN115393100A (en) | 2022-11-25 |
Family
ID=84124521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211062071.5A Pending CN115393100A (en) | 2022-08-31 | 2022-08-31 | Resource recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115393100A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117997959A (en) * | 2024-04-07 | 2024-05-07 | 厦门两万里文化传媒有限公司 | Resource intelligent matching method and system based on meta universe |
-
2022
- 2022-08-31 CN CN202211062071.5A patent/CN115393100A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117997959A (en) * | 2024-04-07 | 2024-05-07 | 厦门两万里文化传媒有限公司 | Resource intelligent matching method and system based on meta universe |
| CN117997959B (en) * | 2024-04-07 | 2024-06-04 | 厦门两万里文化传媒有限公司 | Resource intelligent matching method and system based on meta universe |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109033408B (en) | Information pushing method and device, computer readable storage medium and electronic equipment | |
| CN110442712B (en) | Risk determination method, risk determination device, server and text examination system | |
| CN110990546B (en) | Intelligent question-answer corpus updating method and device | |
| CN111371767B (en) | Malicious account identification method, malicious account identification device, medium and electronic device | |
| CN111125658B (en) | Method, apparatus, server and storage medium for identifying fraudulent user | |
| CN115082041B (en) | User information management method, device, equipment and storage medium | |
| CN111708942B (en) | Multimedia resource pushing method, device, server and storage medium | |
| CN112231555A (en) | Recall method, apparatus, device and storage medium based on user portrait label | |
| CN111984792A (en) | Website classification method and device, computer equipment and storage medium | |
| CN112100504A (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN111797320A (en) | Data processing method, device, equipment and storage medium | |
| CN110598126B (en) | Cross-social network user identity recognition method based on behavior habits | |
| CN111651666A (en) | User theme recommendation method and device, computer equipment and storage medium | |
| CN115393100A (en) | Resource recommendation method and device | |
| CN113011886B (en) | Method and device for determining account type and electronic equipment | |
| CN113204699B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN107644042B (en) | Software program click rate pre-estimation sorting method and server | |
| CN111143533A (en) | Customer service method and system based on user behavior data | |
| CN116089616A (en) | Theme text acquisition method, device, equipment and storage medium | |
| CN115796937A (en) | Big data complex relevance electric power supply and demand trend analysis method and device | |
| CN110275986B (en) | Video recommendation method based on collaborative filtering, server and computer storage medium | |
| CN109308565B (en) | Crowd performance grade identification method and device, storage medium and computer equipment | |
| CN113761272A (en) | Data processing method, data processing equipment and computer readable storage medium | |
| CN111984867A (en) | Network resource determination method and device | |
| CN113076450B (en) | Determination method and device for target recommendation list |
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 |