[go: up one dir, main page]

CN113821717B - Information processing method, information processing device, storage medium and electronic device - Google Patents

Information processing method, information processing device, storage medium and electronic device Download PDF

Info

Publication number
CN113821717B
CN113821717B CN202110129258.1A CN202110129258A CN113821717B CN 113821717 B CN113821717 B CN 113821717B CN 202110129258 A CN202110129258 A CN 202110129258A CN 113821717 B CN113821717 B CN 113821717B
Authority
CN
China
Prior art keywords
data
recommended
target user
target
processing
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.)
Active
Application number
CN202110129258.1A
Other languages
Chinese (zh)
Other versions
CN113821717A (en
Inventor
龚志刚
尹翔
王晶晶
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jingdong Century Trading Co Ltd
Beijing Wodong Tianjun Information Technology Co Ltd
Original Assignee
Beijing Jingdong Century Trading Co Ltd
Beijing Wodong Tianjun Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Jingdong Century Trading Co Ltd, Beijing Wodong Tianjun Information Technology Co Ltd filed Critical Beijing Jingdong Century Trading Co Ltd
Priority to CN202110129258.1A priority Critical patent/CN113821717B/en
Publication of CN113821717A publication Critical patent/CN113821717A/en
Application granted granted Critical
Publication of CN113821717B publication Critical patent/CN113821717B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Educational Administration (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Game Theory and Decision Science (AREA)
  • Artificial Intelligence (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The disclosure provides an information processing method, an information processing device, a computer readable storage medium and electronic equipment, and belongs to the technical field of computers. The method comprises the steps of obtaining historical behavior data of a target user and object data of an object to be recommended, determining a data processing strategy of the historical behavior data and the object data according to the data amount of the historical behavior data, determining decay time of the object to be recommended, carrying out decay processing on the historical behavior data and the object data according to the decay time to generate target characteristic data of the target user and the object to be recommended, and processing the target characteristic data according to the data processing strategy to determine the object to be recommended matched with the target user. The information recommendation method and device can improve accuracy of information recommendation.

Description

Information processing method, information processing apparatus, storage medium, and electronic device
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to an information processing method, an information processing apparatus, a computer readable storage medium, and an electronic device.
Background
In order to increase the efficiency of the user's obtaining of valid information, each internet vendor is working to push information to the user that may be of interest to him by means of a recommendation method.
The existing recommendation method mainly comprises two methods, wherein one method is to find other users similar to the user by analyzing the historical behavior data of the user and then to recommend according to the information interested by the similar user, and the other method is to find similar information and recommend according to the characteristics of the information, such as category, price and the like. The two methods respectively realize information recommendation from the angle of a user and the angle of information, but because the characteristic data dimension is single, the accuracy of information recommendation is not high, and the algorithm accuracy can be greatly influenced under the condition that the data amount of historical behavior data is small.
Therefore, it is desirable to provide a method that can effectively improve the accuracy of recommendation.
It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The disclosure provides an information processing method, an information processing device, a computer readable storage medium and an electronic device, so as to improve the problem of low information recommendation accuracy in the prior art at least to a certain extent.
Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure.
According to a first aspect of the disclosure, an information processing method is provided, and the method comprises the steps of obtaining historical behavior data of a target user and object data of an object to be recommended, determining a data processing strategy of the historical behavior data and the object data according to data quantity of the historical behavior data, determining decay time of the object to be recommended, carrying out decay processing on the historical behavior data and the object data according to the decay time to generate target feature data of the target user and the object to be recommended, processing the target feature data according to the data processing strategy to determine the object to be recommended matched with the target user, and wherein the decay time is used for representing a time interval of an initial recommendation score of the object to be recommended from a current time.
In one exemplary embodiment of the disclosure, the determining the data processing policy of the historical behavior data and the object data according to the data amount of the historical behavior data includes determining the data processing policy of the historical behavior data and the object data to be a first processing policy when the data amount of the historical behavior data is greater than a data amount threshold, and determining the data processing policy of the historical behavior data and the object data to be a second processing policy when the data amount of the historical behavior data is not greater than the data amount threshold.
In an exemplary embodiment of the disclosure, the determining the decay time of the object to be recommended, and performing decay processing on the historical behavior data and the object data according to the decay time, generating target feature data of the target user and the object to be recommended includes determining an initial recommendation score of the object to be recommended according to the historical behavior data or the object data, and reducing the initial recommendation score according to the decay time, and generating the target feature data.
In an exemplary embodiment of the disclosure, the step of reducing the initial recommendation score according to the decay time to generate the target feature data includes the steps of constructing a decay function with a current recommendation score and the decay time in an inverse proportion relation, reducing the initial recommendation score through the decay function to obtain the current recommendation score of the object to be recommended, and processing the historical behavior data or the object data according to the current recommendation score of the object to be recommended to generate the target feature data.
In an exemplary embodiment of the disclosure, the step of reducing the initial recommendation score through the decay function to obtain the current recommendation score of the object to be recommended includes the steps of calculating a decay weight of the initial recommendation score through the decay function, and multiplying the decay weight with the initial recommendation score to obtain the current recommendation score of the object to be recommended.
In one exemplary embodiment of the present disclosure, the calculating the decay weight of the initial recommendation score by the decay function includes calculating the decay weight of the initial recommendation score by the following formula:
y=ae-μΔt
where Δt is the decay time, a is the initial recommended score, and μ is the decay rate.
In an exemplary embodiment of the disclosure, the processing the target feature data according to the data processing policy to determine an object to be recommended matching the target user includes processing the target feature data according to the first processing policy to obtain a similar user of the target user, determining an object to be recommended matching the target user according to a relevance score of the similar user and the object to be recommended, and/or processing the target feature data according to the second processing policy to determine an object to be recommended matching the target user.
In an exemplary embodiment of the disclosure, the processing the target feature data according to the first processing policy to obtain a similar user of the target user, and determining an object to be recommended matching the target user according to a relevance score of the similar user and the object to be recommended includes generating a behavior feature matrix of the target user according to the target feature data, determining the similar user of the target user according to the behavior feature matrix, determining an interest degree of the target user in the object to be recommended according to the similarity of the similar user and the target user, and determining the object to be recommended matching the target user according to the interest degree.
In an exemplary embodiment of the disclosure, the processing the target feature data according to the second processing policy determines an object to be recommended that matches the target user, and the processing includes generating a user feature vector of the target user and an object feature vector of the object to be recommended according to the target feature data, and determining the object to be recommended that matches the target user by calculating similarity of the user feature vector and the object feature vector.
In one exemplary embodiment of the disclosure, the determining the object to be recommended matching the target user by calculating the similarity of the user feature vector and the object feature vector includes determining a similar object of the object to be recommended according to the historical behavior data, and determining the object to be recommended matching the target user according to the association degree score of the target user and the similar object.
According to a second aspect of the present disclosure, there is provided an information processing apparatus including an acquisition module configured to acquire historical behavior data of a target user and object data of an object to be recommended, a determination module configured to determine a data processing policy of the historical behavior data and the object data according to a data amount of the historical behavior data, a generation module configured to determine a decay time of the object to be recommended, and perform decay processing on the historical behavior data and the object data according to the decay time, to generate target feature data of the target user and the object to be recommended, and a processing module configured to process the target feature data according to the data processing policy, to determine an object to be recommended that matches the target user, wherein the decay time is configured to represent a time interval of a generation time of an initial recommendation score of the object to be recommended from a current time.
In one exemplary embodiment of the present disclosure, the determining module is configured to determine that the data processing policy of the historical behavior data and the object data is a first processing policy when the data amount of the historical behavior data is greater than a data amount threshold, and determine that the data processing policy of the historical behavior data and the object data is a second processing policy when the data amount of the historical behavior data is not greater than the data amount threshold.
In an exemplary embodiment of the disclosure, the generating module is configured to determine an initial recommendation score of the object to be recommended according to the historical behavior data or the object data, reduce the initial recommendation score according to the decay time, and generate the target feature data.
In an exemplary embodiment of the disclosure, the generating module is further configured to construct an decay function with a current recommendation score and a decay time according to an inverse proportion relationship, reduce the initial recommendation score through the decay function, obtain a current recommendation score of the object to be recommended, and process the historical behavior data or the object data according to the current recommendation score of the object to be recommended, so as to generate the target feature data.
In an exemplary embodiment of the present disclosure, the generating module is further configured to calculate an attenuation weight of the initial recommendation score through the attenuation function, and multiply the attenuation weight with the initial recommendation score to obtain a current recommendation score of the object to be recommended.
In an exemplary embodiment of the present disclosure, the generating module is further configured to calculate the decay weight of the initial recommendation score by:
y=ae-μΔt
where Δt is the decay time, a is the initial recommended score, and μ is the decay rate.
In an exemplary embodiment of the disclosure, the processing module is configured to process the target feature data according to the first processing policy, obtain similar users of the target user, determine an object to be recommended that matches the target user according to a relevance score of the similar users and the object to be recommended, and/or process the target feature data according to the second processing policy, and determine the object to be recommended that matches the target user.
In an exemplary embodiment of the disclosure, the processing module is further configured to generate a behavior feature matrix of the target user according to the target feature data, determine a similar user of the target user according to the behavior feature matrix, determine an interest degree of the target user in the object to be recommended according to a similarity between the similar user and the target user and a relevance score of the similar user to the object to be recommended, and determine the object to be recommended matching the target user according to the interest degree.
In an exemplary embodiment of the disclosure, the processing module is further configured to generate, according to the target feature data, a user feature vector of the target user and an object feature vector of the object to be recommended, and determine the object to be recommended that matches the target user by calculating a similarity between the user feature vector and the object feature vector.
In an exemplary embodiment of the disclosure, the processing module is further configured to determine a similar object of the object to be recommended according to the historical behavior data, and determine an object to be recommended matching the target user according to a relevance score of the target user and the similar object.
According to a third aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements any one of the above-described information processing methods.
According to a fourth aspect of the present disclosure, there is provided an electronic device comprising a processor and a memory for storing executable instructions of the processor, wherein the processor is configured to perform any one of the above information processing methods via execution of the executable instructions.
The present disclosure has the following beneficial effects:
According to the information processing method, the information processing apparatus, the computer-readable storage medium and the electronic device in the present exemplary embodiment, it is possible to determine a data processing policy of historical behavior data and object data according to a data amount of the historical behavior data, determine a decay time of an object to be recommended, perform decay processing on the historical behavior data and the object data according to the decay time, generate target feature data of a target user and the object to be recommended, and further process the target feature data according to the data processing policy, and determine the object to be recommended that matches the target user. On one hand, by determining the decay time of the object to be recommended and carrying out decay processing on the historical behavior data and the object data according to the decay time, the dynamic change amount of the user interest degree can be determined by combining the influence of the time factor on the user interest degree, the accuracy of information recommendation is improved, and the time for searching the object of interest by the user is reduced.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely some embodiments of the present disclosure and that other drawings may be derived from these drawings without undue effort.
Fig. 1 shows a flowchart of an information processing method in the present exemplary embodiment;
FIG. 2 illustrates a data processing flow diagram of a first processing strategy in the present exemplary embodiment;
fig. 3 shows a sub-flowchart of an information processing method in the present exemplary embodiment;
FIG. 4 shows a schematic diagram of an interaction behavior in the present exemplary embodiment;
Fig. 5 shows a sub-flowchart of another information processing method in the present exemplary embodiment;
fig. 6 shows a sub-flowchart of still another information processing method in the present exemplary embodiment;
FIG. 7 shows a schematic diagram of a behavioral characteristics matrix in the present exemplary embodiment;
FIG. 8 illustrates a flowchart for determining target user interest level in the present exemplary embodiment;
fig. 9 shows a flowchart of generating feature vectors in the present exemplary embodiment;
Fig. 10 shows another flowchart of generating feature vectors in the present exemplary embodiment;
FIG. 11 shows a data processing flow diagram of a second processing strategy in the present exemplary embodiment;
fig. 12 is a flowchart showing another information processing method in the present exemplary embodiment;
fig. 13 is a block diagram showing a configuration of an information processing apparatus in the present exemplary embodiment;
fig. 14 shows an electronic device for implementing the above method in the present exemplary embodiment.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein, but rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
In view of the foregoing various problems, exemplary embodiments of the present disclosure first provide an information processing method. The method may be performed by a computer or by a server in the background of an application to determine objects to be recommended that match a target user, e.g., albums, music or singers, etc., that match the target user may be determined in a music class application.
Fig. 1 shows a flow of the present exemplary embodiment, which may include the following steps S110 to S140:
S110, acquiring historical behavior data of a target user and object data of an object to be recommended.
The historical behavior data may be log data related to a recommended object, i.e., content or object acted by the interactive behavior of the target user, for example, may be behavior data of any one or more of clicking, searching, purchasing, collecting, etc. the target user generates the recommended object in a period of time in the past, the object to be recommended refers to the content or object to be recommended to the user, may include a recommended object generated by the target user and a recommended object not generated by the target user, and the object data of the object to be recommended may include feature data such as class, price, user score, etc. of the object to be recommended. In addition, the historical behavior data can include implicit data and explicit data according to the interaction relation between the target user and the recommended object, wherein the implicit data can be data generated by any one or more behaviors such as clicking, viewing and the like of the recommended object by the target user, and the explicit data can be data generated by any one or more behaviors such as comment, searching, purchasing, sharing and collecting and the like of the recommended object by the target user.
In the present exemplary embodiment, the historical behavior data of the target user and the object data of the object to be recommended may be read through a corresponding database or data platform. For example, the historical behavior data of the target user and the object data of the object to be recommended may be extracted from the database or the data platform by using the user identification of the target user and the object identification of the object to be recommended as indexes, respectively.
Further, considering that the type of the interaction behavior between the user and the object to be recommended may also indicate the interest degree of the user to be recommended, in an alternative embodiment, referring to fig. 2, after the historical behavior data of the target user is obtained in step S210, implicit data and explicit data in the historical behavior data may also be determined in step S220, for example, the interaction behavior of the target user to be recommended may be determined according to the historical behavior data, and further, whether the interaction behavior matches the interaction behavior corresponding to the implicit data and the explicit data may be determined, so as to divide the historical behavior data into the implicit data and the explicit data.
And S120, determining a data processing strategy of the historical behavior data and the object data according to the data quantity of the historical behavior data.
The data processing policy refers to a processing method of the historical behavior data and the object data, and may include processing data, processing steps, and a data format of the historical behavior data and the object data, such as a dimension of the output data.
The historical behavior data can be used as an important basis for analyzing the interestingness of the target user. When the data volume of the historical behavior data is large, the historical behavior data can be analyzed to obtain more accurate interest level of the target user, but when the data volume of the historical behavior data is small, the historical behavior data cannot fully reflect the interest level of the target user. Accordingly, the data processing policy of the history behavior data and the object data can be determined from the data amount of the history behavior data, for example, the processing data duty ratio of the history behavior data and the object data, and the processing steps of the two data, respectively, can be determined from the data amount of the history behavior data.
In an alternative embodiment, step S120 may be implemented by the following method:
when the data amount of the historical behavior data is larger than the data amount threshold, determining the data processing strategies of the historical behavior data and the object data as first processing strategies.
And when the data quantity of the historical behavior data is not greater than the data quantity threshold, determining the data processing strategies of the historical behavior data and the object data as second processing strategies.
The data amount threshold may be set by an operator according to experience, for example, the data amount threshold of the historical behavior data in one month may be set to 10 ten thousand pieces according to a time range corresponding to the historical behavior data, and the data amount of the historical behavior data in one week may be set to 1 ten thousand pieces, where the first processing policy and the second processing policy refer to data processing policies of the historical behavior data and the object data when the data amount of the historical behavior data is greater than the data amount threshold and not greater than the data amount threshold, and may include a data duty ratio and a processing step of the data, a format of the output data, and the like of the data to be processed in the historical behavior data and the object data. In this exemplary embodiment, according to the size of the data amount of the historical behavior data, the first processing policy may be to analyze the historical behavior data, determine similar users of the target user, and determine the object to be recommended that matches the target user according to the interest level of the object to be recommended by the similar users, and the second processing policy may be to analyze the historical behavior data and the object data, and determine the object to be recommended that matches the target user.
As described above, the data size of the historical behavior data determines whether the historical behavior data can fully represent the interestingness of the target user, and the data size determines the data processing policy of the historical behavior data and the object data, so that the association relationship between the data size of the historical behavior data and the data processing policy can be established. When the data volume of the historical behavior data is not greater than the data volume threshold, the historical behavior data cannot fully reflect the interest of the target user on the recommended object, and only the historical behavior data is analyzed to judge the interest of the target user accurately, so that the historical behavior data and the object data can be processed by adopting a second data strategy.
The corresponding data processing strategy is determined according to the data quantity of the historical behavior data, so that the data processing modes of the historical behavior data and the object data can be determined in advance, the problem of low calculation accuracy caused by adopting the same data processing mode is avoided, and the data processing efficiency can be improved.
S130, determining the decay time of the object to be recommended, and carrying out decay processing on the historical behavior data and the object data according to the decay time to generate target users and target feature data of the object to be recommended.
The decay time may be used to represent a time interval between the generation time of the initial recommendation score of the object to be recommended and the current time, for example, the generation time of the initial recommendation score of the object to be recommended is t p, the current time is t n, and then the decay time Δt=t n-tp. The initial recommendation score may be used to represent the initial popularity of the object to be recommended and the likelihood that the object to be recommended is recommended to the target user, and in general, the higher the initial recommendation score, the higher the likelihood that the object to be recommended is recommended to the target user, and conversely, the lower the likelihood that the object to be recommended is recommended to the target user. The target feature data may be feature data generated from historical behavior data of the target user and object data of the object to be recommended, and may include an interaction behavior feature, an interaction time, an interaction place of the target user with the object to be recommended, or a category feature, a price feature, etc. of the object to be recommended. The target feature data may include feature data of the user itself such as the sex, age, occupation, and region of the target user.
The applicant of the present disclosure has found through research that the interest level of the user to the object to be recommended may continuously decline with the increase of time, and therefore, the historical behavior data and the object data may be attenuated according to the attenuation time of the object to be recommended to generate target feature data of the target user and the object to be recommended.
In general, with the increasing time, if the target user does not generate new interaction with the object to be recommended, the interest level of the target user in the object to be recommended may be indicated to be continuously reduced, and meanwhile, in the recommending process, the object to be recommended may be continuously updated with the increasing time, that is, if the object to be recommended is not updated, the interest level of the target user in the object to be recommended may be continuously reduced with the increasing time. Thus, in an alternative embodiment, referring to FIG. 3, step S130 may be implemented by the following steps S310-S320:
and S310, determining an initial recommendation score of the object to be recommended according to the historical behavior data or the object data.
And S320, reducing the initial recommendation score according to the decay time, and generating the target characteristic data.
In this exemplary embodiment, an initial recommendation score of the object to be recommended may be determined according to the above-mentioned historical behavior data or object data, for example, when the target user and the object to be recommended generate an interactive behavior, an interactive behavior type, an interactive behavior duration, and the like of the object to be recommended may be determined according to the historical behavior data, and further, when the target user and the object to be recommended do not have an interactive behavior, an initial recommendation score of the object to be recommended may be determined according to the object data, where the initial recommendation score may be a recommendation score that is estimated and generated in advance by an operator, or may be a default recommendation score of the object to be recommended.
Fig. 4 shows a schematic diagram of interaction behavior of a user and an object to be recommended, as shown in the drawing, the target user 1 generates interaction behavior of collection, purchasing and browsing respectively for the object to be recommended A, B, C, the target user 2 generates interaction behavior of collection, clicking and purchasing respectively for the object to be recommended A, B, D, and the target user 3 generates interaction behavior of clicking and collecting respectively for the objects to be recommended B and D, thereby, according to the interaction behavior type of the object to be recommended by the target user, the initial recommendation score can be set to a score corresponding to the interaction behavior type, and referring to the following table 1, according to the interaction behavior type of the object to be recommended by the target user, the initial recommendation score of the interaction behaviors of collection and browsing can be determined to be 5, and the initial recommendation score of the interaction behaviors of clicking and purchasing can be determined to be 3.
TABLE 1
After determining the initial recommendation score of the object to be recommended, the initial recommendation score can be reduced according to the decay time, so that the recommendation score of each object to be recommended at the current time is obtained, and further target feature data is generated.
In order to facilitate determining the current recommendation score of the object to be recommended, in an alternative embodiment, the current recommendation score of the object to be recommended may be calculated by a pre-constructed decay function, that is, as shown in fig. 5, step S320 may be implemented by the following steps S510 to S520:
S510, constructing an attenuation function with the current recommendation score and the attenuation time conforming to the inverse proportion relation, and reducing the initial recommendation score through the attenuation function to obtain the current recommendation score of the object to be recommended.
And S520, processing the historical behavior data or the object data according to the current recommendation score of the object to be recommended to generate target feature data.
The decay function may be any function that the current recommendation score and the decay time conform to an inverse proportion relation, for example, the decay function may be set as s= -k Δt+b, where S is the current recommendation score, Δt is the decay time, k and b are constants, and the current recommendation score is the recommendation score of the object to be recommended at the current moment, and generally, if the target user does not interact with the object to be recommended within the decay time, the current recommendation score should be smaller than the initial recommendation score.
The current recommendation score of the object to be recommended after time attenuation can be obtained by performing attenuation calculation on the initial recommendation score according to a pre-constructed attenuation function, and further the historical behavior data and the object data can be processed according to the current recommendation score of the object to be recommended, for example, the characteristic data of the initial recommendation score can be added in the historical behavior data and the object data, so that target characteristic data of the target user and the object to be recommended can be generated.
In an alternative embodiment, the above-mentioned decay function may also be set as a function of a decay factor for calculating the initial recommendation score, which may be used to represent the degree of decay of the initial recommendation score. Thus, the method for reducing the initial recommendation score through the decay function and obtaining the current recommendation score of the object to be recommended can be realized by the following steps:
And calculating the attenuation weight of the initial recommendation score through the attenuation function.
And multiplying the attenuation weight with the initial recommendation score to obtain the current recommendation score of the object to be recommended.
The attenuation weight may be used to represent the attenuation degree of the initial recommendation score, where a higher attenuation weight indicates a higher attenuation degree of the initial recommendation score, and conversely, indicates a lower attenuation degree of the initial recommendation score.
The accuracy of determining the current recommendation score can be improved by calculating the decay weight of the initial recommendation score through the decay function. The current recommendation score of the object to be recommended at the current moment can be obtained by multiplying the attenuation weight by the initial recommendation score, for example, assuming that the initial recommendation score of the object i to be recommended is M i and the attenuation weight of the initial recommendation score is y i, the current recommendation score is M i*yi.
The applicant of the present disclosure finds through research that the interest degree of the user on the object to be recommended is related to the memory degree of the user on the object to be recommended, and according to the memory rule of people, the memory amount of the user on the object to be recommended shows a forgetting rule as shown in the following table 2:
TABLE 2
Time interval Memory quantity
Just complete 100%
After 20 minutes 58.2%
After 1 hour 44.2%
8-9 Hours 35.8%
For 1 day 33.7%
For 2 days 27.8%
For 6 days 25.4%
For 30 days 21.1%
By fitting the above-mentioned memory curve, it is possible to determine the memory change rule of the target user to the object to be recommended, that is, the decay weight of the initial recommendation score of the object to be recommended conforms to the memory rule of the following formula (1):
y=ae-μt (1)
wherein y is the attenuation weight of the initial recommendation score of the object to be recommended, a is the initial recommendation score, mu is the attenuation rate, and t is the time interval.
Thus, in an alternative embodiment, when calculating the decay weight of the initial recommendation score by the decay function, the decay weight may be calculated by the following equation (2):
y=ae-μΔt (2)
where Δt is the decay time, a is the initial recommended score, and μ is the decay rate.
After obtaining the current recommendation score of the object to be recommended, the historical behavior data or the object data can be processed according to the current recommendation score to obtain the target feature data. For example, when there is an interactive behavior between the target user and the object to be recommended, the initial recommendation score determined according to the type of the interactive behavior may be attenuated, and the obtained current recommendation score may be used as feature data and added to behavior feature data generated according to the historical behavior data to obtain the target feature data, or when there is no interactive behavior between the target user and the object to be recommended, the initial recommendation score determined according to the object data may be attenuated, and the obtained current recommendation score may be used as feature data and added to feature data generated according to the historical behavior data and the object data to obtain the target feature data.
And S140, processing the target characteristic data according to the data processing strategy, and determining an object to be recommended, which is matched with the target user.
After the target feature data is obtained, the target feature data can be processed according to the data processing strategy, so that an object to be recommended, which is matched with the target user, is determined.
In an alternative embodiment, referring to fig. 6, step S140 may be obtained by the following steps S610 to S620:
S610, processing the target feature data according to a first processing strategy to obtain similar users of the target user, and determining the object to be recommended matched with the target user according to the association degree score of the similar users and the object to be recommended.
And S620, processing the target feature data according to a second processing strategy, and determining an object to be recommended, which is matched with the target user.
The association degree score of the similar user and the object to be recommended can be data such as scores of the similar user and the object to be recommended.
In an alternative embodiment, step S610 may be implemented by the following method:
And generating a behavior feature matrix of the target user according to the target feature data, and determining similar users of the target user according to the behavior feature matrix.
According to the similarity between the similar users and the target users and the relevance score of the similar users to the object to be recommended, determining the interest degree of the target users to the object to be recommended, and determining the object to be recommended matched with the target users according to the interest degree.
As shown in step S230 of fig. 2, the interaction behavior of the target user with the object to be recommended may be determined according to the target feature data, and a behavior feature matrix of the target user may be generated. Taking the above target users 1,2 and 3 as an example, the initial recommendation score may be multiplied by the attenuation weight to generate a behavior feature matrix as shown in fig. 7, where y ij represents the attenuation weight of the target user i to the object j to be recommended. Then, step S240 may be performed, i.e. calculating a set of users similar to the target user through the behavior feature matrix of the target user, i.e. similar users of the target user, for example, the similarity between feature data of the target user may be calculated through a corresponding similarity calculation formula to determine similar users, and taking cosine similarity as an example, the similarity between any two target users may be calculated through the following formula (3):
Wherein a and B are feature vectors generated from feature data of different target users, respectively.
After calculating the similarity between any two target users, other target users with the similarity greater than a certain threshold may be determined to be similar users of the target users, or as shown in fig. 2, or the similarity may be sorted in descending order according to step S250, where other target users corresponding to the first k similarities are determined to be similar users of the target users, and k is a positive integer. Then, according to the similarity between the similar users and the target users and the relevance score of the similar users to the object to be recommended, the interest degree of the target users to the object to be recommended can be determined, and the object to be recommended matched with the target users can be determined according to the interest degree, for example, the interest degrees can be ranked, so that the object to be recommended corresponding to the first m interest degrees is determined to be the object to be recommended matched with the target users, and m is a positive integer.
For example, referring to fig. 8, for the target user 1, the relevance scores of the similar users 1, 2 and 3 for the object a to be recommended are r11, r12 and r13, respectively, and the similarity of the target user 1 and the similar users 1, 2 and 3 is w11, w12 and w13, respectively, so that in an alternative embodiment, the interest degree of the target user for the object a to be recommended may be obtained:
P(u,j)=∑v∈S(q,K)∩N(j)wuv*rvj (4)
Where N (j) represents a set of similar users for the object j to be recommended, and r vj represents a relevance score for the target user V for the object j to be recommended. w uv denotes the similarity of the target user u to the similar user v.
In an alternative embodiment, when determining the interest level of the target user to the object to be recommended, the interest level may also be determined directly according to the relevance score of the similar user to the object to be recommended, for example, the average of the relevance scores of the similar user to the object to be recommended may be determined directly as the interest level of the target user to the object to be recommended.
In processing the target feature data according to the second processing policy, in an alternative embodiment, the interest level of the target user for the object to be recommended may be determined by determining a matching level between the interest of the target user and the feature of the object to be recommended. Specifically, in step S620, the processing of the target feature data according to the second processing policy may be implemented by the following method:
respectively generating a user feature vector of a target user and an object feature vector of an object to be recommended according to the target feature data;
and determining the object to be recommended matched with the target user by calculating the similarity of the user feature vector and the object feature vector.
The user feature vector may be used to represent the features of the recommended objects preferred by the target user, and may include the category, price, etc. of the recommended objects, and the object feature vector may be used to represent the features of each object to be recommended, and may include the category, price, etc. of the object to be recommended.
As shown in fig. 9, a user feature vector may be constructed according to basic information and historical behavior data of a target user, and an object feature vector may be constructed according to object data of an object to be recommended, so that the object to be recommended matching the target user is determined by calculating the similarity of the user feature vector and the object feature vector.
By calculating the similarity between the user feature vector and the object feature vector, the matching degree of the features of the recommended object preferred by the user and the features of the object to be recommended can be determined, so that the object to be recommended with higher matching degree can be determined as the object to be recommended which is matched with the target user.
In addition, in an alternative embodiment, the user feature vector and the object feature vector may be generated through feature engineering, specifically, referring to fig. 10, the user feature vector and the object feature vector may be generated by processing basic information, historical behavior data, and object data of the object to be recommended of the target user in the following steps S1010 to S1040:
s1010, preprocessing basic information, historical behavior data and object data of an object to be recommended of a target user, and removing test data, dirty data, abnormal data and the like in the data.
And S1020, extracting user characteristics and object characteristics.
Specifically, user attribute data, numeric class data, time class data, and the like of the target user may be extracted. The user attribute data may include gender, address, height, identity occupation, interaction behavior with an object to be recommended, etc., the numerical class data may include age, duration of interaction behavior, etc., and the time class data may include date of birth, registration time, time of interaction behavior generation, etc. For the object data of the object to be recommended, the object attribute data, the numerical class data, the time class data and the like of the object to be recommended can also be extracted. The object attribute data may include an object category, a store, a color, a use, and the like of the object to be recommended, the numerical class data may include a price, a collection number, a purchase number, and the like, and the time class data may include a production date of the object to be recommended, and the like.
And S1030, carrying out feature processing on the user features and the object features. For example, one-hot encoding (one-hot encoding) may be performed on attribute data in the user feature and the object feature, normalization and discretization processing may be performed on numeric class data, and for time class data, attenuation processing may be performed on the above feature by determining an attenuation time.
And S1040, performing feature selection on the processed user features and object features to generate user feature vectors and object feature vectors. For example, the gender, age, interaction behavior, time of interaction behavior generation, identity occupation, and the like of the target user may be selected from the user features, and the object category, use, object score, price, number of purchases, number of collections, date of production, and the like of the object to be recommended may be selected from the object features.
Further, in order to recommend a new object to be recommended to the target user, in an alternative embodiment, when calculating the similarity between the user feature vector and the object feature vector to determine the object to be recommended matching the target user, the similar object of the object to be recommended may be determined according to the historical behavior data, and the object to be recommended matching the target user may be determined according to the relevance score of the target user and the similar object.
FIG. 11 shows a data processing flow diagram of a second processing strategy, which may include the following steps S1110-S1160:
Step S1110, determining an initial recommendation score of the object to be recommended according to the object data, and reducing the initial recommendation score according to the decay time to generate target feature data, wherein the target feature data can comprise basic information and historical behavior data of a target user and the object data of the object to be recommended.
And S1120, generating a user feature vector and an object feature vector according to the target feature data.
And S1130, calculating the similarity between the user feature vector and the object feature vector.
And S1140, determining the similarity between the objects to be recommended by adopting algorithms such as Nearest Neighbor (KNN) and the like.
S1150, the recommended objects which have the similarity between the objects to be recommended larger than a certain threshold and have no interaction behavior generated by the target user are used as similar objects of the objects to be recommended.
And S1160, determining similar objects corresponding to the first n relevance scores as objects to be recommended, which are matched with the target user, according to the relevance scores of the target user and the similar objects, wherein n is a positive integer.
In addition, when the features of the objects to be recommended are fewer or belong to the structural features, when the similarity between the objects to be recommended is determined according to step S1140, a decision tree class classification algorithm may be used to classify the similarity into a plurality of classes, so as to determine the similarity between the objects to be recommended.
Further, fig. 12 shows a flow of another information processing method in the present exemplary embodiment, and as shown in fig. 12, the method may include the following steps S1201 to S1214:
step S1201, historical behavior data of a target user and object data of an object to be recommended are obtained.
Step S1202, determining whether the data amount of the historical behavior data is greater than the data amount threshold, if so, executing step S1203, and if not, executing step S1209.
Step S1203, determining a data processing strategy of the historical behavior data and the object data as a first processing strategy.
And S1204, determining initial recommendation scores of the objects to be recommended and decay time of the objects to be recommended according to the historical behavior data, and then carrying out decay calculation on the initial recommendation scores according to the decay time to determine current recommendation scores of the objects to be recommended.
And S1205, processing the historical behavior data according to the current recommendation score of the object to be recommended, and generating target characteristic data of the target user and the object to be recommended.
And S1206, generating a behavior feature matrix of the target user according to the target feature data.
S1207, calculating the similarity among all the target users according to the behavior feature matrix, and determining the similar users of the target users.
S1208, determining the interest degree of the target user on the object to be recommended according to the association degree score of the similar user and the object to be recommended.
Step s1209, determining the data processing policy of the historical behavior data and the object data as a second processing policy.
S1210, determining an initial recommendation score of the object to be recommended and a decay time of the object to be recommended according to the object data, and then performing decay calculation on the initial recommendation score according to the decay time to determine a current recommendation score of the object to be recommended.
And S1211, processing the object data according to the current recommendation score of the object to be recommended, and generating target characteristic data of the target user and the object to be recommended.
And S1212, generating a user feature vector of the target user and an object feature vector of the object to be recommended according to the target feature data.
Step S1213, calculating the similarity between the user feature vector and the object feature vector.
Step S1214, determining an object to be recommended, which is matched with the target user. Specifically, after the interest degree of the target user in the object to be recommended is determined according to the association degree score of the similar user and the object to be recommended, the object to be recommended corresponding to the first k interest degrees is taken as the object to be recommended matched with the target user according to the interest degree of the target user in the object to be recommended, and the object to be recommended corresponding to the first k similarity degrees is taken as the object to be recommended matched with the target user according to the similarity of the user feature vector and the object feature vector.
In summary, according to the information processing method in the present exemplary embodiment, the data processing policy of the historical behavior data and the object data may be determined according to the data amount of the historical behavior data, the decay time of the object to be recommended may be determined, the historical behavior data and the object data may be subjected to decay processing according to the decay time, the target feature data of the target user and the object to be recommended may be generated, and then the target feature data may be processed according to the data processing policy, and the object to be recommended matching the target user may be determined. On one hand, by determining the decay time of the object to be recommended and carrying out decay processing on the historical behavior data and the object data according to the decay time, the dynamic change amount of the user interest degree can be determined by combining the influence of the time factor on the user interest degree, the accuracy of information recommendation is improved, and the time for searching the object of interest by the user is reduced.
Further, in this exemplary embodiment, there is provided an information processing apparatus, referring to fig. 13, the information processing apparatus 1300 may include an acquisition module 1310 configured to acquire historical behavior data of a target user and object data of an object to be recommended, a determination module 1320 configured to determine a data processing policy of the historical behavior data and the object data according to a data amount of the historical behavior data, a generation module 1330 configured to determine a decay time of the object to be recommended and perform a decay process on the historical behavior data and the object data according to the decay time to generate target feature data of the target user and the object to be recommended, and a processing module 1340 configured to process the target feature data according to the data processing policy to determine the object to be recommended that matches the target user, wherein the decay time may be used to represent a time interval of an initial recommendation score of the object to be recommended from a current time.
In one exemplary embodiment of the present disclosure, the determining module 1320 may be configured to determine the data processing policies of the historical behavior data and the object data to be the first processing policy when the data amount of the historical behavior data is greater than the data amount threshold, and determine the data processing policies of the historical behavior data and the object data to be the second processing policy when the data amount of the historical behavior data is not greater than the data amount threshold.
In an exemplary embodiment of the present disclosure, the generating module 1330 may be configured to determine an initial recommendation score for the object to be recommended according to the historical behavior data or the object data, reduce the initial recommendation score according to the decay time, and generate the target feature data.
In an exemplary embodiment of the present disclosure, the generating module 1330 may be further configured to construct a decay function having a current recommendation score and a decay time in an inverse proportion relationship, and reduce the initial recommendation score by using the decay function to obtain a current recommendation score of the object to be recommended, and process the historical behavior data or the object data according to the current recommendation score of the object to be recommended to generate the target feature data.
In an exemplary embodiment of the present disclosure, the generating module 1330 may be further configured to calculate a decay weight of the initial recommendation score by a decay function, and multiply the decay weight with the initial recommendation score to obtain a current recommendation score for the object to be recommended.
In one exemplary embodiment of the present disclosure, the generation module 1330 may also be configured to calculate the decay weight of the initial recommendation score by:
y=ae-μΔt
where Δt is the decay time, a is the initial recommended score, and μ is the decay rate.
In an exemplary embodiment of the present disclosure, the processing module 1340 may be configured to process the target feature data according to a first processing policy to obtain similar users of the target user, determine an object to be recommended that matches the target user according to a relevance score of the similar users to the object to be recommended, and/or process the target feature data according to a second processing policy to determine the object to be recommended that matches the target user.
In an exemplary embodiment of the disclosure, the processing module 1340 may be further configured to generate a behavior feature matrix of the target user according to the target feature data, determine a similar user of the target user according to the behavior feature matrix, determine an interest level of the target user in the object to be recommended according to a similarity between the similar user and the target user and a relevance score of the similar user in the object to be recommended, and determine the object to be recommended matching the target user according to the interest level.
In an exemplary embodiment of the present disclosure, the processing module 1340 may be further configured to generate a user feature vector of the target user and an object feature vector of the object to be recommended according to the target feature data, and determine the object to be recommended matching the target user by calculating a similarity between the user feature vector and the object feature vector.
In an exemplary embodiment of the present disclosure, the processing module 1340 may be further configured to determine similar objects of the object to be recommended according to the historical behavior data, and determine the object to be recommended matching the target user according to the association score of the target user with the similar objects.
The specific details of each module in the above apparatus are already described in the method section embodiments, and the details of the undisclosed solution may be referred to the method section embodiments, so that they will not be described in detail.
Those skilled in the art will appreciate that the various aspects of the present disclosure may be implemented as a system, method, or program product. Accordingly, aspects of the present disclosure may be embodied in the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects that may be referred to herein collectively as a "circuit," module, "or" system.
Exemplary embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon a program product capable of implementing the method described above in the present specification. In some possible implementations, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the disclosure as described in the "exemplary methods" section of this specification, when the program product is run on the terminal device.
The program product for implementing the above-described method of the exemplary embodiments of the present disclosure may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of a readable storage medium include an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
The exemplary embodiment of the disclosure also provides an electronic device capable of implementing the method. An electronic device 1400 according to such an exemplary embodiment of the present disclosure is described below with reference to fig. 14. The electronic device 1400 shown in fig. 14 is merely an example and should not be construed as limiting the functionality and scope of use of the disclosed embodiments.
As shown in fig. 14, the electronic device 1400 may be embodied in the form of a general purpose computing device. The components of the electronic device 1400 may include, but are not limited to, the at least one processing unit 1410 described above, the at least one memory unit 1420 described above, a bus 1430 connecting the different system components (including the memory unit 1420 and the processing unit 1410), and a display unit 1440.
Wherein the memory unit 1420 stores program code that can be executed by the processing unit 1410, such that the processing unit 1410 performs steps according to various exemplary embodiments of the present disclosure described in the above-described "exemplary methods" section of the present specification. For example, the processing unit 1410 may perform the method steps shown in fig. 1-3, fig. 5-6, fig. 8-13, etc.
The memory unit 1420 may include readable media in the form of volatile memory units, such as Random Access Memory (RAM) 1421 and/or cache memory 1422, and may further include Read Only Memory (ROM) 1423.
The memory unit 1420 may also include a program/utility 1424 having a set (at least one) of program modules 1425, such program modules 1425 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
Bus 1430 may be a local bus representing one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or using any of a variety of bus architectures.
The electronic device 1400 may also communicate with one or more external devices 1500 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 1400, and/or any device (e.g., router, modem, etc.) that enables the electronic device 1400 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 1450. Also, electronic device 1400 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 1460. As shown, the network adapter 1460 communicates with other modules of the electronic device 1400 via the bus 1430. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with the electronic device 1400, including, but not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with exemplary embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Furthermore, the above-described figures are only schematic illustrations of processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily appreciated that the processes shown in the above figures do not indicate or limit the temporal order of these processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, for example, among a plurality of modules.
From the description of the embodiments above, those skilled in the art will readily appreciate that the exemplary embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the exemplary embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the exemplary embodiments of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims (10)

1. An information processing method, characterized in that the method comprises:
acquiring historical behavior data of a target user and object data of an object to be recommended;
The method comprises the steps of determining a data processing strategy of historical behavior data and object data according to the data quantity of the historical behavior data, wherein the data processing strategy of the historical behavior data and the object data is determined according to the data quantity of the historical behavior data, and comprises the steps of determining the data processing strategy of the historical behavior data and the object data as a first processing strategy when the data quantity of the historical behavior data is larger than a data quantity threshold value, and determining the data processing strategy of the historical behavior data and the object data as a second processing strategy when the data quantity of the historical behavior data is not larger than the data quantity threshold value;
Determining the decay time of the object to be recommended according to the time interval between the generation time of the initial recommendation score of the object to be recommended and the current time;
The initial recommendation score is reduced according to the decay time, and target characteristic data of the target user and the object to be recommended are generated;
The processing of the target feature data according to the data processing strategy to determine the object to be recommended, which is matched with the target user, comprises the steps of processing the target feature data according to the first processing strategy to obtain a similar user of the target user, determining the object to be recommended, which is matched with the target user, according to the association degree score of the similar user and the object to be recommended, and/or processing the target feature data according to the second processing strategy to determine the object to be recommended, which is matched with the target user.
2. The method of claim 1, wherein said reducing said initial recommendation score according to said decay time generates said target feature data comprising:
constructing an attenuation function of which the current recommendation score and the attenuation time accord with the inverse proportion relation, and reducing the initial recommendation score through the attenuation function to obtain the current recommendation score of the object to be recommended;
And processing the historical behavior data or the object data according to the current recommendation score of the object to be recommended to generate the target feature data.
3. The method of claim 2, wherein the reducing the initial recommendation score by the decay function results in a current recommendation score for the object to be recommended, comprising:
calculating the attenuation weight of the initial recommendation score through the attenuation function;
and multiplying the attenuation weight with the initial recommendation score to obtain the current recommendation score of the object to be recommended.
4. A method according to claim 3, wherein said calculating the decay weight of the initial recommendation score by the decay function comprises:
the decay weight of the initial recommendation score is calculated by the following formula:
;
where Δt is the decay time, a is the initial recommended score, and μ is the decay rate.
5. The method of claim 1, wherein the processing the target feature data according to the first processing policy to obtain similar users of the target user, and determining the object to be recommended matching the target user according to the association degree score of the similar users and the object to be recommended, includes:
Generating a behavior feature matrix of the target user according to the target feature data, and determining similar users of the target user according to the behavior feature matrix;
and determining the interest degree of the target user on the object to be recommended according to the similarity between the similar user and the target user and the association degree score of the similar user on the object to be recommended, and determining the object to be recommended matched with the target user according to the interest degree.
6. The method of claim 1, wherein processing the target feature data according to the second processing policy determines an object to be recommended that matches the target user, comprising:
Generating a user feature vector of the target user and an object feature vector of the object to be recommended according to the target feature data;
And determining the object to be recommended matched with the target user by calculating the similarity of the user feature vector and the object feature vector.
7. The method of claim 6, wherein the determining the object to be recommended that matches the target user by calculating the similarity of the user feature vector and the object feature vector comprises:
Determining similar objects of the object to be recommended according to the historical behavior data;
And determining the object to be recommended matched with the target user according to the association degree score of the target user and the similar object.
8. An information processing apparatus for implementing the information processing method of claim 1, the apparatus comprising:
The acquisition module is used for acquiring historical behavior data of the target user and object data of an object to be recommended;
A determining module, configured to determine a data processing policy of the historical behavior data and the object data according to a data amount of the historical behavior data;
the generation module is used for determining the decay time of the object to be recommended, carrying out decay processing on the historical behavior data and the object data according to the decay time, and generating target characteristic data of the target user and the object to be recommended;
And the processing module is used for processing the target characteristic data according to the data processing strategy and determining an object to be recommended, which is matched with the target user.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of any of claims 1-7.
10. An electronic device, comprising:
Processor, and
A memory for storing executable instructions of the processor;
Wherein the processor is configured to perform the method of any of claims 1-7 via execution of the executable instructions.
CN202110129258.1A 2021-01-29 2021-01-29 Information processing method, information processing device, storage medium and electronic device Active CN113821717B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110129258.1A CN113821717B (en) 2021-01-29 2021-01-29 Information processing method, information processing device, storage medium and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110129258.1A CN113821717B (en) 2021-01-29 2021-01-29 Information processing method, information processing device, storage medium and electronic device

Publications (2)

Publication Number Publication Date
CN113821717A CN113821717A (en) 2021-12-21
CN113821717B true CN113821717B (en) 2025-03-21

Family

ID=78912373

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110129258.1A Active CN113821717B (en) 2021-01-29 2021-01-29 Information processing method, information processing device, storage medium and electronic device

Country Status (1)

Country Link
CN (1) CN113821717B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114399057A (en) * 2022-01-28 2022-04-26 青岛海尔科技有限公司 Weight adjustment method and device, storage medium and electronic device
CN114210597B (en) * 2022-02-22 2022-04-26 深圳市正和兴电子有限公司 Conductive adhesive recommendation method and system for semiconductor device and readable storage medium
CN116795955A (en) * 2022-03-17 2023-09-22 腾讯科技（深圳）有限公司 Data processing method, device, computer equipment and storage medium
CN114595394B (en) * 2022-03-22 2024-08-16 平安证券股份有限公司 Retrieval ordering method, device, terminal equipment and medium based on user behaviors

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104216884A (en) * 2013-05-29 2014-12-17 酷盛(天津）科技有限公司 Collaborative filtering system and method on basis of time decay
CN107729542A (en) * 2017-10-31 2018-02-23 咪咕音乐有限公司 A kind of information methods of marking and device and storage medium

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5740814B2 (en) * 2009-12-22 2015-07-01 ソニー株式会社 Information processing apparatus and method
CN107220852A (en) * 2017-05-26 2017-09-29 北京小度信息科技有限公司 Method, device and server for determining target recommended user
US11710102B2 (en) * 2017-07-31 2023-07-25 Box, Inc. Forming event-based recommendations
CN109408665B (en) * 2018-12-29 2021-11-23 咪咕音乐有限公司 Information recommendation method and device and storage medium
CN110659425B (en) * 2019-09-25 2022-05-17 秒针信息技术有限公司 Resource allocation method and device, electronic equipment and readable storage medium
CN110825977A (en) * 2019-10-10 2020-02-21 平安科技（深圳）有限公司 A data recommendation method and related equipment
CN110851737B (en) * 2019-11-13 2024-03-12 哈工大机器人湖州国际创新研究院 Recommendation method, recommendation device, electronic equipment and computer storage medium
CN111339419A (en) * 2020-02-27 2020-06-26 厦门美图之家科技有限公司 Information recommendation method and device, electronic equipment and storage medium
CN111966903A (en) * 2020-08-18 2020-11-20 中国银行股份有限公司 Application software function recommendation method and device

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104216884A (en) * 2013-05-29 2014-12-17 酷盛(天津）科技有限公司 Collaborative filtering system and method on basis of time decay
CN107729542A (en) * 2017-10-31 2018-02-23 咪咕音乐有限公司 A kind of information methods of marking and device and storage medium

Also Published As

Publication number Publication date
CN113821717A (en) 2021-12-21

Similar Documents

Publication Publication Date Title
CN113821717B (en) Information processing method, information processing device, storage medium and electronic device
Tang et al. Exploiting homophily effect for trust prediction
US9176969B2 (en) Integrating and extracting topics from content of heterogeneous sources
WO2019214245A1 (en) Information pushing method and apparatus, and terminal device and storage medium
JP2019185716A (en) Entity recommendation method and device
CN110008397B (en) A recommended model training method and device
CN111723292A (en) Recommendation method and system based on graph neural network, electronic device and storage medium
CN113837843B (en) Product recommendation method and device, medium and electronic equipment
JP2024518458A (en) System and method for automatic topic detection in text
CN107491985A (en) The user's methods of marking and device of electric business platform, electronic equipment, storage medium
CN103309869A (en) Method and system for recommending display keyword of data object
US20200250715A1 (en) Automatic rule generation for recommendation engine using hybrid machine learning
CN115329207B (en) Intelligent sales information recommendation method and system
CN111178949A (en) Service resource matching reference data determination method, device, equipment and storage medium
CN111429161A (en) Feature extraction method, feature extraction device, storage medium, and electronic apparatus
CN117746546A (en) Service business processing method and system based on caller
CN116070024A (en) Article Recommendation Method and Device Based on New Energy Cloud and User Behavior
CN112116159A (en) Information interaction method and device, computer readable storage medium and electronic equipment
CN119739922A (en) Method and device for index recommendation, electronic device and storage medium
CN112307334B (en) Information recommendation method, information recommendation device, storage medium and electronic equipment
CN111737607B (en) Data processing method, device, electronic equipment and storage medium
CN117648444B (en) Patent clustering method and system based on graph convolution attribute aggregation
CN112036987B (en) Method and device for determining recommended commodity
CN119048251A (en) Personalized insurance service recommendation method based on artificial intelligence
CN113779967A (en) Enterprise transformation information generation method and device, storage medium and electronic equipment

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
GR01 Patent grant
GR01 Patent grant