Content recommendation method and device, electronic equipment and storage medium

By dynamically determining the target parameters in the content scoring algorithm and using multiple user behavior data to calculate content scoring, the problem of poor recommendation results caused by parameter fixation in the prior art is solved, and the improvement of personalized content recommendation is achieved.

CN119066260APending Publication Date: 2024-12-03BEIJING VOLCANO ENGINE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410405529.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-04-03
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the existing content recommendation algorithm, the parameters are fixed, making it difficult to adapt to the personalized needs of different users, resulting in poor recommendation results.

Method used

By obtaining the user's historical behavior data, determining the target parameters in the content scoring algorithm, making it non-fixed, using the predicted values ​​and transformation functions of multiple user behavior data to calculate the content score, and dynamically adjust the recommended order.

Benefits of technology

It has achieved personalized matching of content recommendations, adapted to the interests and behavioral characteristics of different users, and improved the relevance and user experience of recommendations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066260A_ABST
    Figure CN119066260A_ABST
Patent Text Reader

Abstract

The invention provides a content recommendation method and device, electronic equipment and a storage medium. The content recommendation method comprises the steps that a content scoring algorithm is obtained, the content scoring algorithm comprises target parameters, and the content scoring algorithm is used for calculating content scores; determining the value of the target parameter according to the historical behavior data of the user; according to the determined value of the target parameter, calculating the content score of the candidate content by adopting the content scoring algorithm; and performing content recommendation according to the content score of the candidate content. According to the invention, content recommendation is more in line with personalized demands of users.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a content recommendation method, device, electronic device and storage medium. Background Art

[0002] When users use application software such as video software and news software, the software will recommend videos, news and other content to users. The strength of the correlation between the software's recommended content and the user's interests determines whether the user will view the recommended content. Summary of the invention

[0003] The present disclosure provides a content recommendation method, device, electronic device and storage medium.

[0004] The present disclosure adopts the following technical solutions.

[0005] In some embodiments, the present disclosure provides a content recommendation method, comprising:

[0006] Acquire a content scoring algorithm, wherein the content scoring algorithm includes a target parameter and the content scoring algorithm is used to calculate a content score;

[0007] Determine the value of the target parameter according to the user's historical behavior data;

[0008] Calculating the content score of the candidate content using the content scoring algorithm according to the determined value of the target parameter;

[0009] Content recommendation is performed according to the content scores of the candidate content.

[0010] In some embodiments, the present disclosure provides a content recommendation device, including:

[0011] An acquisition unit, configured to acquire a content scoring algorithm, wherein the content scoring algorithm includes a target parameter and the content scoring algorithm is used to calculate a content score;

[0012] A control unit, configured to determine the value of the target parameter according to the historical behavior data of the user;

[0013] The control unit is further configured to calculate the content score of the candidate content using the content score algorithm according to the determined value of the target parameter;

[0014] The recommendation unit is used to recommend content according to the content score of the candidate content.

[0015] In some embodiments, the present disclosure provides an electronic device, comprising: at least one memory and at least one processor;

[0016] The memory is used to store program codes, and the processor is used to call the program codes stored in the memory to execute the above method.

[0017] In some embodiments, the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store program code, and when the program code is executed by a processor, the processor is prompted to perform the above method.

[0018] The method provided by the embodiment of the present disclosure determines the target parameters in the content scoring algorithm according to the historical behavior data of the user, so that the target parameters are non-fixed and different users have different target parameters, so that the content recommendation is more in line with the personalized needs of the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0020] Figure 1 4 is a flowchart of a content recommendation method according to an embodiment of the present disclosure.

[0021] Figure 2 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0023] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0024] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0025] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0026] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0027] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0028] It should be understood that the various steps described in the method embodiments of the present disclosure can be performed in sequence and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0029] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0030] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0031] It should be noted that the modification of “one” mentioned in the present disclosure is illustrative rather than restrictive, and those skilled in the art should understand that it should be understood as “one or more” unless otherwise clearly indicated in the context.

[0032] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0033] The solution provided by the embodiment of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0034] All user data obtained in this disclosure is obtained with the user's permission and authorization.

[0035] When users use software, the software will recommend content to users based on their interests. For example, when using video software, videos will be recommended. The strength of the correlation between the recommended content and the user's interests determines whether the user will view the recommended content. Different users pay different attention to content, and the parameters in the content recommendation algorithm are often fixed, which is not ideal for different users.

[0036] like Figure 1 As shown, Figure 1 Detailed description of the invention The content recommendation method of the present invention includes the following steps.

[0037] S11. Obtain a content scoring algorithm, wherein the content scoring algorithm includes a target parameter and the content scoring algorithm is used to calculate a content score.

[0038] In some embodiments, the method proposed in the present disclosure can be used in a terminal or a server, specifically in video software, news software, etc. The content scoring algorithm is an algorithm for calculating the content score of candidate content, which can be represented by a formula or a function. The content scoring algorithm has parameters, and the target parameter can be a part of the parameters in the content scoring algorithm, and the value of the target parameter is undetermined in the content scoring algorithm. The target parameter can include one or more parameters, and the target parameter can include method parameters or numerical parameters. The method parameter describes the method used in the content scoring algorithm to calculate part of the content, and the numerical parameter describes the numerical value of part of the content in the content scoring algorithm.

[0039] S12. Determine the value of the target parameter according to the user's historical behavior data.

[0040] In some embodiments, the number of types of the historical behavior data is at least two, and the user's historical behavior data includes a variety of past behavior data of the user, for example, data on the user's click behavior, reading time, like behavior, attention behavior, and dislike behavior. The user's historical behavior data reflects the user's personalized information. The value of the target parameter is determined by the user's historical behavior data, so that for different users, the parameters in the content scoring algorithm are non-fixed and can be adapted to the user.

[0041] S13. Calculate the content score of the candidate content using a content score algorithm according to the determined value of the target parameter.

[0042] In some embodiments, after obtaining the value of the target parameter, it is brought into the content scoring algorithm to calculate the content score of each candidate content. There are usually multiple candidate contents.

[0043] S14. Recommend content based on the content scores of the candidate content.

[0044] In some embodiments, the content score shows the matching degree between the candidate content and the personalized interests of the user. The recommendation order of each candidate content can be determined according to the content score, and the content that needs to be recommended first can be determined.

[0045] In some embodiments of the present disclosure, target parameters in a content scoring algorithm are determined based on historical behavior data of users, so that the target parameters are non-fixed and different users have different target parameters, making content recommendations more in line with the personalized needs of users.

[0046] In some embodiments of the present disclosure, the value of the target parameter is determined based on the user's historical behavior data, including: when calculating the value of the target parameter as different candidate values, the strength of the correlation between the content score calculated by the content scoring algorithm and the user's historical behavior data; using the candidate value corresponding to the maximum value when the correlation strength is the maximum value as the value of the target parameter.

[0047] In some embodiments, multiple candidate values ​​may be set in advance for each target parameter. Alternatively, multiple candidate values ​​that can be selected may be calculated in real time or in advance based on the user's historical behavior data. For each target parameter, an enumeration method may be used to calculate each case when different target parameters select different candidate values, and the strength of the correlation between the calculated content score and the user's historical behavior data may be determined for each case. The greater the strength of the correlation, the better the match between the content scoring algorithm and the user's historical behavior data, and the more it can meet the user's personalized needs.

[0048] In some embodiments of the present disclosure, when the value of the target parameter is calculated as different candidate values, the strength of the correlation between the content score calculated by the content scoring algorithm and the user's historical behavior data includes: when the value of the target parameter is calculated as different candidate values, the AUC (Area Under Curve, the area under the receiver operating characteristic curve and the coordinate axis) of the first behavior data and the content score calculated by the content scoring algorithm, and the Pearson correlation coefficient of the second behavior data and the content score calculated by the content scoring algorithm; the product of the AUC and the Pearson correlation coefficient is used as the correlation strength; wherein the historical behavior data includes the first behavior data and the second behavior data.

[0049] In some embodiments, the first behavior data and the second behavior data are the data that the user sets as the data that he or she pays most attention to. In this way, the content scoring algorithm can well match the needs of the user, and the user is most likely to perform the same type of behavior as the first behavior data and the second behavior data on the recommended content. Specifically, for example, the first behavior data is click behavior data, and the second behavior data is viewing time data. This indicates that the content recommended according to the content scoring formula can extend the time that the user watches the content, and the content scoring formula calculated by the method in this embodiment can make the recommended content be watched by the user for a long time. For example, the first behavior data is click behavior data, and the second behavior data is like behavior data. This indicates that the content recommended according to the content scoring formula is most likely to obtain the user's likes for the content.

[0050] Specifically, taking the target parameters including method parameters and numerical parameters, the first behavior data is click behavior data, and the second behavior data is viewing time data as an example, the MapReduce technology can be used to search for candidate methods and candidate values, and the AUC of the click behavior and content score, and the Pearson correlation coefficient of the user viewing time and the content score are calculated for each combination. The AUC is multiplied by the Pearson correlation coefficient to represent the correlation strength, and the candidate method and candidate value used by the combination with the largest correlation strength are selected as the value of the target parameter and substituted into the content scoring algorithm. This method eliminates the need to manually set the values ​​and methods in the target parameters, and can achieve automatic update adaptation.

[0051] In some embodiments of the present disclosure, the content scoring algorithm includes: predicted values ​​of at least two types of user behavior data. In some embodiments, if the content score is calculated based on only a single type of user behavior data, such as only calculating the content score based on likes, the estimated distribution of different content will vary greatly. The content score of some extreme content is completely outliers in the distribution, and the ranking may be greatly improved due to a single behavior data. Therefore, in some embodiments of the present disclosure, the content score will be calculated based on the predicted values ​​of multiple user behavior data. For example, the predicted values ​​of multiple user behavior data include: user click probability, user reading time, user attention probability, etc. By integrating different types of user behavior data, the effect of recommended content can be improved.

[0052] In some embodiments of the present disclosure, the content scoring algorithm includes: the ranking of the candidate content calculated among all candidate content according to the predicted value of the user's behavior data. In some embodiments, for example, if the predicted user's behavior data includes the probability of a like, then after sorting the candidate content according to the probability of a like, the candidate content currently calculating the content score will also be ranked among the candidate content according to the probability of a like. Not only the predicted value of the predicted user's behavior data is concerned, but also the predicted ranking is concerned.

[0053] In some embodiments of the present disclosure, the following formula is used as the content scoring algorithm:

[0054]

[0055] Among them, score is the content score, a n For p n The weight, p n is the predicted value of the user’s nth behavior data, p n_ Rank is the calculated candidate content according to p n The ranking among all candidate contents, f is the transformation function, M is the number of types of user behavior data; the target parameters include: the weight and the transformation function.

[0056] In some embodiments, a1, a2, ... a M is the weight value that needs to be determined by the user's historical behavior data, which is a value between 0 and 1, and the sum can be 1 to achieve normalization. f is the transformation function that needs to be determined by the user's historical behavior data, p1, p2...p M It is the predicted value of the user's behavior data, such as the predicted click rate, predicted like probability, predicted follow probability, etc. 1_ rank,p 2_ rank,……p M_ The ranks are p1, p2, ... p M After the candidate contents are sorted, the ranking of the candidate contents whose content scores are currently being calculated in the total candidate contents. For example, the rankings are 1, 2, 3, etc. In the above formula, the multiplication term of a category of user behavior data is obtained using the predicted value of the predicted user behavior data and the ranking determined based on the predicted value, and the multiplication terms of each category of user behavior data are weighted so that the generated content score is related to each category of user behavior data.

[0057] In some embodiments of the present disclosure, the transformation function is a reciprocal transformation function, a uniform transformation function, or a normalized sine transformation function.

[0058] In some embodiments, the inverse transformation function is f(pn_ rank)=1÷(1+p n_ rank) β1 , where β1 is the first index. In some embodiments, β1 specifically refers to the target parameter that needs to be determined based on the user's historical behavior data. The inverse transformation function tends to improve the score discrimination of the head, making it easier for the top-ranked content of a single type of user behavior data to be ranked up, and evenly distributes while maintaining the discrimination of the head, while enhancing the discrimination of the tail content, making it easier for the content with a low ranking in a single type of user behavior data to be suppressed.

[0059] In some embodiments, the uniform transformation function is f(p n _rank)=1÷(1-p n _rank / N) β2 , where β2 is the second exponent;

[0060] In some embodiments, the normalized sine transform function is Among them, b and a are control parameters, which are the values ​​in the target parameters that need to be determined based on the user's historical behavior data, uniform is a uniform transformation function, uniform(x) = 1-(x×2) / N, x is the input value, N is the total number of candidate content, min-value = b a ×uniform(N-1) -b -a×uniform(N-1) , max-value = b a×uniform(0) -b -a×uniform(0) The normalized sine transformation function has the characteristic of strong discrimination at both ends. By using different transformation functions, it can be applied to different business scenarios and meet different needs.

[0061] In some embodiments, the predicted value of the user's behavior data includes one or more of the following: predicted click-through rate, predicted viewing time, and predicted like rate.

[0062] In some embodiments of the present disclosure, weights and transformation functions of multiple types of user behavior data are adaptively adjusted to better match target parameters to users and avoid bias in content recommendation based on a single type of user behavior data.

[0063] In some embodiments of the present disclosure, a content recommendation device is provided, including:

[0064] An acquisition unit, configured to acquire a content scoring algorithm, wherein the content scoring algorithm includes a target parameter and the content scoring algorithm is used to calculate a content score;

[0065] a control unit, configured to calculate the strength of correlation between the content score calculated by the content scoring algorithm and the user's historical behavior data when the value of the target parameter is different candidate values;

[0066] The control unit is further used to: use the candidate value corresponding to the maximum value of the correlation strength as the value of the target parameter to calculate the content score of the candidate content;

[0067] The recommendation unit is used to recommend content according to the content score of the candidate content.

[0068] In some embodiments, determining the value of the target parameter according to the historical behavior data of the user includes:

[0069] the strength of the correlation between the content score calculated by the content scoring algorithm and the user's historical behavior data when the value of the target parameter is calculated as different candidate values;

[0070] The candidate value corresponding to the maximum value of the correlation strength is used as the value of the target parameter.

[0071] In some embodiments, when calculating the value of the target parameter as different candidate values, the strength of the correlation between the content score calculated by the content scoring algorithm and the user's historical behavior data includes:

[0072] When calculating the value of the target parameter as different candidate values, the AUC (Area Under Curve) between the first behavior data and the content score calculated by the content scoring algorithm, and the Pearson correlation coefficient between the second behavior data and the content score calculated by the content scoring algorithm;

[0073] The product of the AUC and the Pearson correlation coefficient is used as the correlation strength;

[0074] The historical behavior data includes the first behavior data and the second behavior data.

[0075] In some embodiments, the first behavior data and the second behavior data are the data that the user sets as the data that the user is most concerned about.

[0076] In some embodiments, the first behavior data is click behavior data, and the second behavior data is viewing time data.

[0077] In some embodiments, the content scoring algorithm includes: predicted values ​​of at least two types of user behavior data; in some embodiments, the content scoring algorithm includes: a ranking of the candidate content calculated among all candidate content according to the predicted values ​​of the user's behavior data.

[0078] In some embodiments, the following formula is used as the content scoring algorithm:

[0079]

[0080] Among them, score is the content score, a n For p n The weight, p n is the predicted value of the user’s nth behavior data, p n _rank is the calculated candidate content according to p n The ranking among all candidate contents, f is the transformation function, and M is the number of types of user behavior data;

[0081] The target parameters include: the weight and the transformation function.

[0082] In some embodiments, the transformation function is a reciprocal transformation function, a uniform transformation function, or a normalized sine transformation function;

[0083] The inverse transformation function is f(p n _rank)=1÷(1+p n _rank) β1 , where β1 is the first exponent;

[0084] The uniform transformation function is f(p n _rank)=1÷(1-p n _rank / N) β2 , where β2 is the second exponent;

[0085] The normalized sine transform function is

[0086] Among them, b and a are control parameters, uniform is the uniform transformation function,

[0087] uniform(x)=1-(x×2) / N, where N is the total number of candidate contents.

[0088] min-value=b a×uniform(N-1) -b -a×uniform(N-1) ,

[0089] max-value=b a×uniform(0) -b -a×uniform(0) .

[0090] For the embodiments of the device, since they basically correspond to the method embodiments, the relevant parts refer to the partial description of the method embodiments. The device embodiments described above are merely illustrative, wherein the modules described as separation modules may or may not be separated. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of the present embodiment. Those of ordinary skill in the art can understand and implement without paying creative work.

[0091] The method and device of the present disclosure are described above based on the embodiments and application examples. In addition, the present disclosure also provides an electronic device and a computer-readable storage medium, which are described below.

[0092] Reference below Figure 2 , which shows a schematic diagram of the structure of an electronic device (such as a terminal device or a server) 800 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. The electronic device shown in the figure is only an example and should not bring any limitation to the functions and scope of use of the embodiment of the present disclosure.

[0093] The electronic device 800 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 are also stored. The processing device 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0094] Typically, the following devices may be connected to the I / O interface 805: input devices 806 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 808 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 809. The communication device 809 may allow the electronic device 800 to communicate with other devices wirelessly or by wire to exchange data. Although the electronic device 800 with various devices is shown in the figure, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively.

[0095] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by the processing device 801, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0096] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0097] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0098] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0099] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method of the present disclosure.

[0100] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0101] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0102] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0103] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0104] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0105] According to one or more embodiments of the present disclosure, a content recommendation method is provided, comprising:

[0106] Acquire a content scoring algorithm, wherein the content scoring algorithm includes a target parameter and the content scoring algorithm is used to calculate a content score;

[0107] Determine the value of the target parameter according to the user's historical behavior data;

[0108] Calculating the content score of the candidate content using the content scoring algorithm according to the determined value of the target parameter;

[0109] Content recommendation is performed according to the content scores of the candidate content.

[0110] According to one or more embodiments of the present disclosure, a content recommendation method is provided, which determines the value of the target parameter according to the historical behavior data of the user, including:

[0111] the strength of the correlation between the content score calculated by the content scoring algorithm and the user's historical behavior data when the value of the target parameter is calculated as different candidate values;

[0112] The candidate value corresponding to the maximum value of the correlation strength is used as the value of the target parameter.

[0113] According to one or more embodiments of the present disclosure, a content recommendation method is provided, wherein when calculating the value of the target parameter as different candidate values, the correlation strength between the content score calculated by the content scoring algorithm and the user's historical behavior data includes:

[0114] When calculating the value of the target parameter as different candidate values, the AUC (Area Under Curve) between the first behavior data and the content score calculated by the content scoring algorithm, and the Pearson correlation coefficient between the second behavior data and the content score calculated by the content scoring algorithm;

[0115] The product of the AUC and the Pearson correlation coefficient is used as the correlation strength;

[0116] The historical behavior data includes the first behavior data and the second behavior data.

[0117] According to one or more embodiments of the present disclosure, a content recommendation method is provided, wherein the first behavior data and the second behavior data are the data that the user sets as the data that the user pays most attention to;

[0118] And / or; the first behavior data is click behavior data, and the second behavior data is viewing time data.

[0119] According to one or more embodiments of the present disclosure, a content recommendation method is provided, wherein the content scoring algorithm includes: predicted values ​​of at least two types of user behavior data; and / or;

[0120] The content scoring algorithm includes: calculating the ranking of the candidate content among all candidate content according to the predicted value of the user's behavior data.

[0121] According to one or more embodiments of the present disclosure, a content recommendation method is provided, which uses the following formula as the content scoring algorithm:

[0122]

[0123] Among them, score is the content score, a n For p n The weight, p n is the predicted value of the user’s nth behavior data, p n _rank is the calculated candidate content according to p n The ranking among all candidate contents, f is the transformation function, and M is the number of types of user behavior data;

[0124] The target parameters include: the weight and the transformation function.

[0125] According to one or more embodiments of the present disclosure, a content recommendation method is provided, wherein the transformation function is a reciprocal transformation function, a uniform transformation function or a normalized sine transformation function;

[0126] The inverse transformation function is f(p n _rank)=1÷(1+p n _rank) β1 , where β1 is the first exponent;

[0127] The uniform transformation function is f(p n _rank)=1÷(1-p n _rank / N) β2 , where β2 is the second exponent;

[0128] The normalized sine transform function is

[0129] Among them, b and a are control parameters, uniform is the uniform transformation function,

[0130] uniform(x)=1-(x×2) / N, where N is the total number of candidate contents.

[0131] min-value=b a×uniform(N-1) -b-a×uniform(N-1) ,

[0132] max-value=b a×uniform(0) -b -a×uniform(0) .

[0133] According to one or more embodiments of the present disclosure, a content recommendation device is provided, including:

[0134] An acquisition unit, configured to acquire a content scoring algorithm, wherein the content scoring algorithm includes a target parameter and the content scoring algorithm is used to calculate a content score;

[0135] A control unit, configured to determine the value of the target parameter according to the historical behavior data of the user;

[0136] The control unit is further configured to calculate the content score of the candidate content using the content score algorithm according to the determined value of the target parameter;

[0137] The recommendation unit is used to recommend content according to the content score of the candidate content.

[0138] According to one or more embodiments of the present disclosure, there is provided an electronic device, including: at least one memory and at least one processor;

[0139] The at least one memory is used to store program codes, and the at least one processor is used to call the program codes stored in the at least one memory to execute any one of the above methods.

[0140] According to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium is used to store program code, and when the program code is executed by a processor, the processor is prompted to execute the above method.

[0141] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0142] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0143] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A content recommendation method, characterized in that: include: Acquire a content scoring algorithm, wherein the content scoring algorithm includes a target parameter and the content scoring algorithm is used to calculate a content score; Determine the value of the target parameter according to the user's historical behavior data; Calculating the content score of the candidate content using the content score algorithm according to the determined value of the target parameter; Content recommendation is performed according to the content scores of the candidate content.

2. The method according to claim 1, characterized in that Determining the value of the target parameter according to the historical behavior data of the user includes: the strength of the correlation between the content score calculated by the content scoring algorithm and the user's historical behavior data when the value of the target parameter is calculated as different candidate values; The candidate value corresponding to the maximum value of the correlation strength is used as the value of the target parameter.

3. The method according to claim 2, characterized in that When calculating the value of the target parameter as different candidate values, the strength of the correlation between the content score calculated by the content scoring algorithm and the user's historical behavior data includes: When calculating the value of the target parameter as different candidate values, the AUC (Area Under Curve) between the first behavior data and the content score calculated by the content scoring algorithm, and the Pearson correlation coefficient between the second behavior data and the content score calculated by the content scoring algorithm; The product of the AUC and the Pearson correlation coefficient is used as the correlation strength; The historical behavior data includes the first behavior data and the second behavior data.

4. The method according to claim 3, characterized in that The first behavior data and the second behavior data are data set by the user that the user is most concerned about; and / or; The first behavior data is click behavior data, and the second behavior data is viewing time data.

5. The method according to claim 1, characterized in that The content scoring algorithm includes: predicted values ​​of at least two types of user behavior data; and / or; The content scoring algorithm includes: calculating the ranking of the candidate content among all candidate content according to the predicted value of the user's behavior data.

6. The method according to claim 1, characterized in that The following formula is used as the content scoring algorithm: Among them, score is the content score, a n For p n The weight, p n is the predicted value of the user’s nth behavior data, p n_ Rank is the calculated candidate content according to p n The ranking among all candidate contents, f is the transformation function, and M is the number of types of user behavior data; The target parameters include: the weight and the transformation function.

7. The method according to claim 6, characterized in that The transformation function is a reciprocal transformation function, a uniform transformation function or a normalized sine transformation function; The inverse transformation function is Where β1 is the first index; The uniform transformation function is Where β2 is the second index; The normalized sine transform function is Among them, b and a are control parameters, uniform is the uniform transformation function, uniform(x)=1-(x×2) / N, where N is the total number of candidate contents. min-value=b a×uniform(N-1) -b -a×uniform(N-1) , max-value=b a×uniform(0) -b -a×uniform(0) 。 8. A content recommendation device, characterized in that: include: An acquisition unit, configured to acquire a content scoring algorithm, wherein the content scoring algorithm includes a target parameter and the content scoring algorithm is used to calculate a content score; A control unit, configured to determine the value of the target parameter according to the historical behavior data of the user; The control unit is further configured to calculate the content score of the candidate content using the content score algorithm according to the determined value of the target parameter; The recommendation unit is used to recommend content according to the content score of the candidate content.

9. An electronic device, comprising: at least one memory and at least one processor; The at least one memory is used to store program code, and the at least one processor is used to call the program code stored in the at least one memory to execute the method according to any one of claims 1 to 7. 10 . A computer-readable storage medium, wherein the computer-readable storage medium is used to store program codes, wherein when the program codes are executed by a processor, the processor is prompted to execute the method according to claim 1 .