Information processing method and device based on user multi-source data and medium

Abstract

The invention provides an information processing method and device based on user multi-source data and a medium, and relates to the technical field of data processing, the method is applied to a first application program, in the method, data from a plurality of data sources are integrated, data feature vectors are generated, multi-level requirements and potential interests of a user can be captured, and the user experience is improved. The intention or purpose of the target user for starting the application program at present can be reflected; determining a model based on the data feature vector and a sorting algorithm, and determining a target sorting algorithm from a plurality of preset sorting algorithms; the accuracy of the determined target sorting algorithm is improved, further, the video display sequence of the to-be-displayed videos is determined by using the target sorting algorithm, and the to-be-displayed videos are displayed to the target user according to the video display sequence; in this way, the to-be-displayed video with higher correlation and higher matching degree is preferentially presented to the target user, and the user experience is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information processing, and in particular to an information processing method based on user multi-source data, an information processing device and a medium. BACKGROUND

[0002] With the explosive growth of Internet content, for example: millions of new contents are added to short video platforms every day, the cost of manual screening of required information by users increases significantly, and therefore personalized recommendation is needed, irrelevant or low-relevance content is filtered through an algorithm, and only content highly matching the interests and needs of users is displayed to the users, thereby improving user experience; in the prior art, a personalized recommendation method often depends on a single data source for recommendation sorting, for example: based on historical operation behaviors (such as clicking, browsing, liking, sharing, etc.) of a user in an application program, interest preferences of the user are predicted, a recommendation sorting is determined based on the predicted interest preferences, and a plurality of contents to be displayed are displayed to the user according to the recommendation sorting.

[0003] However, the above method has the following technical problems:

[0004] Only relying on historical operation behaviors in an application program to predict interest preferences of a user, for a new user or a user who uses the application program infrequently, it is difficult to collect enough behavior data to predict interest preferences; and operation of a user in other application programs may imply potential interest preferences, the above method ignores cross-application behavior operation information, in addition, in different situations, an intention or purpose of a user to start an application program may be different, only relying on historical operation behaviors in an application program cannot predict a real interest state of the user at present, which can also be understood as an intention or purpose of the user to start the application program at present, therefore, the accuracy of interest preferences predicted based on the above method is low, and a real interest state of the user at present cannot be predicted, and further, the accuracy of a recommendation order determined based on the above method is low, which may affect user experience. SUMMARY

[0005] In view of the above technical problems, the technical solution adopted by the present application is an information processing method based on user multi-source data, an information processing device and a medium.

[0006] According to a first aspect of the present application, an information processing method based on user multi-source data is provided, the method is applied to a first application program, and the method comprises the following steps:

[0007] S1, in response to a target user starting a first application program, acquiring multi-source data of the target user; the multi-source data comprises: personal basic attribute information data R1 of the target user, operation behavior data R2 of the target user to the first application program and second application program operation data R3 of a target device; wherein R3 comprises application program types and foreground staying time lengths of each second application program that is run in the foreground of the target device in a target time period; the first application program is used for displaying a video; the second application program is an application program other than the first application program in the target device; the target device is a device where the first application program is located; an ending time point of the target time period is a current time point, and a time length of the target time period is a preset time length.

[0008] S2, acquiring a data feature vector T based on the multi-source data of the target user, T=(A, B, C); A is a basic attribute feature obtained based on R1, B is a first operation behavior feature obtained based on R2, and C is a second operation behavior feature obtained based on R3.

[0009] S3, determining a model based on T and a sorting algorithm, and determining a target sorting algorithm from a plurality of preset sorting algorithms.

[0010] S4, determining a video display order of a plurality of to-be-displayed videos by using the target sorting algorithm, and displaying the plurality of to-be-displayed videos to the target user according to the video display order.

[0011] According to a second aspect of the present application, a non-transitory computer readable storage medium is provided, the storage medium storing a computer program, the computer program being loaded and executed by a processor to implement the method described above.

[0012] According to a third aspect of the present application, an electronic device is provided, comprising: a processor, a memory and a computer program stored on the memory and executable on the processor, the processor executing the computer program to implement the method described above.

[0013] The present application has at least the following beneficial effects:

[0014] The application provides a user multi-source data-based information processing method and device and a medium. The application integrates data from multiple data sources, that is, generates a data feature vector by fusing the personal basic attribute information data of the target user, the operation behavior data of the target user on the first application program, and the second application program operation data of the target device, which helps to capture the multi-level requirements and potential interests of the user, that is, even if the target user is a new user or a user who uses the first application program at a low frequency, the multi-level requirements and potential interests of the target user can also be captured; and the second application program operation data includes the application program type and foreground stay duration of each second application program that is run in the foreground of the target device within a target time period; the end time point of the target time period is the current time point; therefore, the second application program operation data can reflect the intention or purpose of the target user for starting the application program currently, so that the data feature vector can reflect the intention or purpose of the target user for starting the application program currently; further, the target sorting algorithm is determined from the plurality of preset sorting algorithms based on the data feature vector and the sorting algorithm determination model, which is beneficial to improving the accuracy of the determined target sorting algorithm; further, the video display order of the plurality of to-be-displayed videos is determined by using the target sorting algorithm, and the plurality of to-be-displayed videos are displayed to the target user according to the video display order; so that the to-be-displayed videos with higher relevance and stronger matching degree are preferentially presented to the target user, which is beneficial to improving the user experience. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0016] Figure 1 A flowchart of a user multi-source data-based information processing method provided by the application is shown in the figure. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] It should be noted that the terms "first," "second," etc., in the technical solutions of this invention and the above-described drawings are used to distinguish similar tasks and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0019] Embodiments of the present invention provide an information processing method based on multi-source user data. The method is applied to a first application and includes the following steps: Figure 1 As shown:

[0020] S1. In response to the target user launching the first application, acquire the target user's multi-source data; the multi-source data includes: the target user's basic personal attribute information data R1, the target user's operation behavior data for the first application R2, and the target device's second application operation data R3; wherein, R3 includes the application type and foreground dwell time of each second application that has been run in the foreground of the target device within the target time period; the first application is used to display video; the second application is an application other than the first application in the target device, and the target device is the device where the first application is located; the end time of the target time period is the current time point, and the duration of the target time period is a preset duration.

[0021] In a preferred embodiment, when the target user launches the first application, the multi-source data of the target user is obtained and the process proceeds to step S2; this enables the video display order of several videos to be displayed to be determined as quickly as possible, and the several videos to be displayed to the target user according to the video display order; this is beneficial to improving the user experience.

[0022] Specifically, the preset time length is a pre-set time length, for example, 10 minutes, 20 minutes, and details are not repeated here. Through the pre-set time length, the short-term interest change of the user can be captured in real time, and the timeliness and relevance of the video display order of the determined several to-be-displayed videos can be improved.

[0023] Specifically, the target user is a user corresponding to an account associated with the first application program.

[0024] In a specific embodiment, R1 at least includes the age, gender, height, current location, and hometown of the target user.

[0025] In a specific embodiment, R2 at least includes data reflecting the operation behavior of the target user when watching videos using the first application program in the historical time period, for example, the completion rate of each type of video, the 50% play completion rate, etc.

[0026] Specifically, the historical time period is a time period before the current time point.

[0027] Further, the end time point of the historical time period is earlier than the current time point, and the length of the historical time period is greater than the preset time length.

[0028] In a specific embodiment, the foreground stay time length of the second application program that has run in the foreground of the target device in the target time period; it can be understood that the foreground stay time length of the second application program is the time length between the time point when the second application program starts running in the foreground of the target device this time and the time point when the second application program ends running in the foreground of the target device this time; for example, if the target time period is from 8 o'clock to 9 o'clock, and the second application program runs in the foreground of the target device from 7:40 to 8:10, then the second application program belongs to the second application program that has run in the foreground of the target device in the target time period, and the foreground stay time length of the second application program is 30 minutes; if the target time period is from 8 o'clock to 9 o'clock, and the second application program runs in the foreground of the target device from 8:20 to 8:30, then the second application program belongs to the second application program that has run in the foreground of the target device in the target time period, and the foreground stay time length of the second application program is 10 minutes.

[0029] Optionally, the first application program is a short video application program.

[0030] S2, obtaining a data feature vector T based on the multi-source data of the target user, T=(A, B, C); A is a basic attribute feature obtained based on R1, B is a first operation behavior feature obtained based on R2, and C is a second operation behavior feature obtained based on R3.

[0031] Specifically, step S2 includes steps S21-S22 as follows:

[0032] S21, obtain foreground application related data list G=(G1, G2, …, Gm) from R3; G1, G2, …, Gm are foreground application related data groups, 1≤i≤m, m is a preset number of foreground application related data groups; G1 is an application type of an i-th foreground application after sorting all foreground applications in a descending order according to a time point when the foreground applications start running in the foreground of a target device; the foreground application is a second application running in the foreground of the target device in a target time period; G2 is a foreground stay duration of a foreground application corresponding to G1; G3 is a foreground stay duration of a foreground application corresponding to G2; Gm is a foreground stay duration of a foreground application corresponding to Gm-1. i ,……,G m ),G i =(G i1 ,G i2 );G i is the i-th foreground application related data group, 1≤i≤m, m is a preset number of foreground application related data groups; G i1 is the application type of the i-th foreground application after sorting all foreground applications in a descending order according to a time point when the foreground applications start running in the foreground of a target device; the foreground application is a second application running in the foreground of the target device in a target time period; G i2 is a foreground stay duration of a foreground application corresponding to G i1 ; for example, if the second applications running in the foreground of the target device in the target time period are application 1, application 2 and application 3; wherein, the time point when application 1 starts running in the foreground of the target device is 8 o'clock; the time point when application 2 starts running in the foreground of the target device is 8 o'clock 20 minutes; the time point when application 3 starts running in the foreground of the target device is 8 o'clock 40 minutes; then, application 1, application 2 and application 3 are foreground applications, and application 3 is the application type of the first foreground application after sorting all foreground applications in a descending order according to a time point when the foreground applications start running in the foreground of a target device; application 2 is the application type of the second foreground application after sorting all foreground applications in a descending order according to a time point when the foreground applications start running in the foreground of a target device; application 1 is the application type of the third foreground application after sorting all foreground applications in a descending order according to a time point when the foreground applications start running in the foreground of a target device; that is, G 11 is the application type of application 3, G 12 is the foreground stay duration of application 3; G 21 is the application type of application 2, G 22 is the foreground stay duration of application 2; G 31 is the application type of application 1, G 32 is the foreground stay duration of application 1.

[0033] Specifically, in step S21, if k x1 is NULL, G x2 =0; wherein, k is the number of second applications running in the foreground of the target device in the target time period; G x1The application type of the xth foreground application after all foreground applications are sorted in the order from late to early according to the time point when the foreground applications start running in the foreground of the target device; G x2 G x1 The foreground stay duration of the corresponding foreground application; k+1≤x≤m.

[0034] Through the above steps, when k x1 NULL, G x2 =0, to avoid errors or exceptions in the foreground application related data group.

[0035] S22, input G into the RNN feature extraction module to obtain C; C=(C1, C2, …, C g , …, C h) , C g Cg is the gth second operation behavior feature value in C, 1≤g≤h, and h is the number of second operation behavior feature values in C.

[0036] In one specific embodiment, other feature extraction modules capable of capturing time dynamics and context information in sequence data can be used instead of the RNN feature extraction module in step S22 to obtain C.

[0037] Through the above steps, since there is a time dependency relationship between each foreground application related data group in the foreground application related data list, an RNN feature extraction module capable of capturing time dynamics and context information in sequence data is required to obtain the second operation behavior feature, so that the second operation behavior feature can more accurately reflect the characteristics of each foreground application related data group in the foreground application related data list.

[0038] In one specific embodiment, step S2 further includes:

[0039] Input R1 into the first feature extraction module to obtain A.

[0040] Specifically, the first feature extraction module is a module capable of extracting features from personal basic attribute information data. Those skilled in the art can select a suitable feature extraction module as the first feature extraction module according to the technical purpose of the present scheme; for example, a feature extraction module capable of performing text feature extraction, such as a feature extraction module in an LSTM model, as an initial module and obtaining the first feature extraction module through training.

[0041] In a specific embodiment, step S2 further comprises:

[0042] R2 is input into the second feature extraction module to obtain B.

[0043] Specifically, the second feature extraction module is a module capable of extracting features from operation behavior feature data. Those skilled in the art can select a suitable feature extraction module as the second feature extraction module according to the technical purpose of the present solution. For example, a feature extraction module capable of behavior feature extraction, such as a feature extraction module in an LSTM model, is used as an initial module and is trained to obtain the second feature extraction module.

[0044] Specifically, A = (A1, A2, …, An), An is the jth basic attribute feature value in A, 1≤j≤n, and n is the number of basic attribute feature values in A. j n j is the jth basic attribute feature value in A, 1≤j≤n, and n is the number of basic attribute feature values in A.

[0045] Specifically, B = (B1, B2, …, Bf), Bf is the e th first operation behavior feature value in B, 1≤e≤f, and f is the number of first operation behavior feature values in B. e f e is the e th first operation behavior feature value in B, 1≤e≤f, and f is the number of first operation behavior feature values in B.

[0046] Specifically, the data formats of A j , B e and C g are numerical types, indicating that A j , B e and C g can participate in mathematical operations.

[0047] S3, determining a model based on T and a sorting algorithm, determining a target sorting algorithm from a plurality of preset sorting algorithms.

[0048] Specifically, step S3 comprises steps S31-S35 as follows:

[0049] S31, input G into the target linear regression model to obtain the intent influence weight β corresponding to C; wherein 0≤β≤1.

[0050] Specifically, the target linear regression model is a linear regression model trained in advance by relevant personnel using relevant data, which is used to determine the influence of the operation of the target user on the second application program before starting the first application program on the current video watching intent of the target user. Those skilled in the art can determine the specific training method according to the needs, which is not limited in the present embodiment.

[0051] ​​​​Specifically, β is used to measure the impact of the target user's actions on the second application before launching the first application on the target user's current video viewing intention; the larger β is, the greater the impact of the target user's actions on the second application before launching the first application on the target user's current video viewing intention; and vice versa.

[0052] S32. Based on β, obtain the preset influence weight α corresponding to A and the preset influence weight γ corresponding to B, where α and γ meet the following conditions:

[0053] α=γ=(1-β) / 2.

[0054] S33, Let A j =A j ×α、B e =B e ×γ、C g =C g ×β is used to update T and use the updated T as the target feature vector MT.

[0055] S34. Input MT into the ranking algorithm determination model to obtain the target ranking algorithm label D corresponding to the target user's current video viewing intention; D∈(P1, P2, ..., P... r ..., P s ), P r Let be the sorting algorithm label for the r-th preset sorting algorithm, where 1 ≤ r ≤ s, and s is the number of preset sorting algorithms.

[0056] Specifically, the target user's current video viewing intent can be understood as: the purpose for which the target user is currently watching the video, such as shopping, relaxing, learning, etc.

[0057] Specifically, the ranking algorithm determines the model as a neural network model trained for the target ranking algorithm label acquisition task.

[0058] Specifically, the preset sorting algorithm is a pre-set sorting algorithm. Different preset sorting algorithms have different operation logic and parameters, which will not be elaborated here.

[0059] S35. Use the preset sorting algorithm corresponding to D as the target sorting algorithm.

[0060] By the above steps, based on the foreground application related data list and the target linear regression model, the intention influence weight corresponding to the second operation behavior feature is obtained, wherein the intention influence weight is used to measure the influence size of the operation of the target user on the second application before starting the first application on the current video watching intention of the target user; based on the intention influence weight, the preset influence weight corresponding to the basic attribute feature and the first operation behavior feature is obtained, the data feature vector is updated based on the intention influence weight corresponding to the second operation behavior feature and the preset influence weight corresponding to the basic attribute feature and the first operation behavior feature, and the updated data feature vector is taken as the target feature vector, which comprehensively considers the influence of the second operation behavior feature, the basic attribute feature and the first operation behavior feature on the current video watching intention of the target user, and can also be understood as comprehensively considering the influence of the second operation behavior feature, the basic attribute feature and the first operation behavior feature on the current video watching purpose or interest of the target user, which is beneficial to improve the accuracy of the target feature vector; the target feature vector is input into the ranking algorithm determination model to obtain the target ranking algorithm label corresponding to the current video watching intention of the target user, and the preset ranking algorithm corresponding to the target ranking algorithm label is taken as the target ranking algorithm, so as to realize the dynamic selection of the ranking algorithm, which is beneficial to improve the precision of the obtained target ranking algorithm, can improve the recommendation effect of different user groups, and is beneficial to improve the user experience.

[0061] S4, using the target ranking algorithm to determine the video display order of a plurality of to-be-displayed videos, and displaying the plurality of to-be-displayed videos to the target user according to the video display order.

[0062] By the above steps, in response to the target user starting the first application program, the multi-source data of the target user is acquired; the multi-source data includes: personal basic attribute information data of the target user, operation behavior data of the target user on the first application program and second application program operation data of the target device; wherein the second application program operation data includes application program types and foreground staying time lengths of each second application program running in the foreground of the target device in a target time period; a data feature vector is acquired based on the multi-source data of the target user; by integrating data from multiple data sources, that is, generating a data feature vector by fusing the personal basic attribute information data of the target user, the operation behavior data of the target user on the first application program and the second application program operation data of the target device, the multi-level demand and potential interest of the user can be captured, even if the target user is a new user or a user who uses the first application program at a low frequency, the multi-level demand and potential interest of the target user can also be captured; and the second application program operation data includes application program types and foreground staying time lengths of each second application program running in the foreground of the target device in a target time period; and the end time point of the target time period is the current time point; therefore, the second application program operation data can reflect the intention or purpose of the target user for starting the application program currently, so that the data feature vector can reflect the intention or purpose of the target user for starting the application program currently; a model is determined based on the data feature vector and a sorting algorithm, and a target sorting algorithm is determined from a plurality of preset sorting algorithms; the sorting algorithm can be dynamically selected, which is beneficial to improving the accuracy of the target sorting algorithm obtained; further, the video display order of a plurality of to-be-displayed videos is determined using the target sorting algorithm, and the plurality of to-be-displayed videos are displayed to the target user according to the video display order; so that the to-be-displayed videos with higher relevance and stronger matching degree are preferentially presented to the target user, which is beneficial to improving user experience.

[0063] The embodiments of the present application also provide a non-transitory computer readable storage medium, which can be arranged in an electronic device to save a computer program related to a method in the method embodiments, and the computer program is loaded and executed by the processor to implement the method provided by the above embodiments.

[0064] The embodiments of the present application also provide an electronic device, which comprises a processor, a memory and a computer program stored in the memory and executable on the processor, and the processor implements the method provided by the above embodiments when executing the computer program.

[0065] The embodiments of the present application also provide a computer program product, which comprises program codes for causing an electronic device to perform the steps of the method according to the various exemplary embodiments of the present application described in the specification when the program product is executed on the electronic device.

[0066] The application provides a user multi-source data-based information processing method and device and a medium, and the method is applied to a first application program, and in the method, multi-source data of a target user is acquired in response to the target user starting the first application program; the multi-source data comprises personal basic attribute information data of the target user, operation behavior data of the target user on the first application program and second application program operation data of a target device; the second application program operation data comprises application program types of each second application program that is run in the foreground of the target device in a target time period and foreground stay time lengths; a data feature vector is acquired based on the multi-source data of the target user; a model is determined based on the data feature vector and a sorting algorithm, and a target sorting algorithm is determined from a plurality of preset sorting algorithms; a video display order of a plurality of to-be-displayed videos is determined using the target sorting algorithm, and the plurality of to-be-displayed videos are displayed to the target user according to the video display order. It can be known that the application integrates data from a plurality of data sources, that is, the personal basic attribute information data of the target user, the operation behavior data of the target user on the first application program and the second application program operation data of the target device are fused to generate the data feature vector, which is helpful for capturing multi-level requirements and potential interests of the user, that is, even if the target user is a new user or a user who uses the first application program at a low frequency, the multi-level requirements and potential interests of the target user can also be captured; and the second application program operation data comprises the application program types of each second application program that is run in the foreground of the target device in the target time period and the foreground stay time lengths; and an end time point of the target time period is a current time point; therefore, the second application program operation data can reflect the intention or purpose of the target user for starting the application program currently, so that the data feature vector can reflect the intention or purpose of the target user for starting the application program currently; furthermore, the model is determined based on the data feature vector and the sorting algorithm, the target sorting algorithm is determined from the plurality of preset sorting algorithms, which is helpful for improving the accuracy of the determined target sorting algorithm, further, the video display order of the plurality of to-be-displayed videos is determined using the target sorting algorithm, and the plurality of to-be-displayed videos are displayed to the target user according to the video display order; so that the to-be-displayed videos with higher relevance and stronger matching degree are preferentially presented to the target user, which is helpful for improving user experience.

[0067] Although some specific embodiments of the application have been described in detail by way of example with reference to the drawings, it is to be understood that the examples are for illustrative purposes only and are not to be construed as limiting the scope of the application. It will be appreciated by persons skilled in the art that various modifications can be made to the embodiments described without departing from the scope and spirit of the application.

Claims

1. A method for processing information based on multi-source data of a user, the method being applied to a first application program, characterized in that, The method comprises the following steps: S1, in response to a target user starting a first application program, acquiring multi-source data of the target user; the multi-source data comprises: personal basic attribute information data R1 of the target user, operation behavior data R2 of the target user on the first application program, and second application program operation data R3 of a target device; wherein R3 comprises an application program type and a foreground stay duration of each second application program that has been run in the foreground of the target device in a target time period; the first application program is used to display a video; the second application program is an application program other than the first application program in the target device; the target device is a device where the first application program is located; an end time point of the target time period is a current time point, and a duration of the target time period is a preset duration; S2, acquiring a data feature vector T based on the multi-source data of the target user, T=(A, B, C); A is a basic attribute feature obtained based on R1, B is a first operation behavior feature obtained based on R2, and C is a second operation behavior feature obtained based on R3; S3, determining a model based on T and a sorting algorithm, and determining a target sorting algorithm from a plurality of preset sorting algorithms; S4, determining a video display order of a plurality of to-be-displayed videos using the target sorting algorithm, and displaying the plurality of to-be-displayed videos to the target user according to the video display order.

2. The information processing method based on user multi-source data according to claim 1, characterized in that, In step S2, the following steps S21-S22 are included: S21, obtaining foreground application related data list G=(G1, G2, …, Gm) from R3; G1, G2, …, Gm are foreground application related data groups, and m is a preset number of foreground application related data groups; G1, G2, …, Gm are application types of foreground applications in a descending order of starting time of the foreground applications in the target device; the foreground applications are second applications running in the foreground of the target device in a target time period; and G1, G2, …, Gm are foreground stay durations of the foreground applications corresponding to G1, G2, …, Gm, respectively. i m i i1 i2 i i1 i2 i1 ​​​​​​​​​ S22, input G into the RNN feature extraction module to obtain C; C=(C1, C2, …, C g , …, C h) , C g is the gth second operation behavior feature value in C, 1≤g≤h, h is the number of second operation behavior feature values in C. 3.The information processing method based on user multi-source data according to claim 2, characterized in that, A = (A1, A2,..., An), n is the number of basic attribute characteristic values in A. j ,..., An), n is the number of basic attribute characteristic values in A. n ,..., An), n is the number of basic attribute characteristic values in A. j Aj is the jth basic attribute characteristic value in A, 1≤j≤n.

4. The information processing method based on user multi-source data according to claim 3, characterized in that, B = (B1, B2,..., Bf), B1, B2,..., Bf are the first operation behavior characteristic values of B, 1≤f≤n, f is the number of the first operation behavior characteristic values of B. e ,..., B f ), B e is the e-th first operation behavior characteristic value in B, 1≤e≤f, f is the number of the first operation behavior characteristic values in B.

5. The information processing method based on user multi-source data according to claim 4, characterized in that, In step S3, the following steps S31-S35 are included: S31, inputting G into a target linear regression model to obtain an intention influence weight β corresponding to C; wherein 0≤β≤1; S32, based on β, acquiring a preset influence weight α corresponding to A and a preset influence weight γ corresponding to B, α and γ satisfy the following conditions: α=γ=(1-β) / 2; S33, let A j = A j × α, B e = B e × γ, C g = C g × β so that T is updated and the updated T is taken as the target feature vector MT; S34, input the MT into the ranking algorithm determination model to obtain a target ranking algorithm label D corresponding to the current video watching intention of the target user; D e (P1, P2, …, Ps) r , …, Ps s ), Pr is the ranking algorithm label of the rth preset ranking algorithm, 1≤r≤s, and s is the number of preset ranking algorithms; r ​ S35, taking a preset sorting algorithm corresponding to D as the target sorting algorithm. 6.The information processing method based on user multi-source data according to claim 2, characterized in that, In step S21, if k x1 is NULL, G x2 = 0; wherein k is the number of second application programs that are run in the foreground of the target device in the target time period; G x1 is the application program type of the xth foreground application program after all foreground application programs are sorted in descending order of the time points at which the foreground application programs start running in the foreground of the target device; G x2 is the application program type of the kth foreground application program; G x1 is the foreground stay duration of the corresponding foreground application program; k+1≤x≤m. 7.The information processing method based on user multi-source data according to claim 1, characterized in that, R1 at least comprises age, gender, height, current location, and hometown of the target user. 8.The information processing method based on user multi-source data according to claim 5, characterized in that, β is used to measure the influence of the operation of the target user on the second application program before starting the first application program on the current video watching intention of the target user. The greater β is, the greater the influence of the operation of the target user on the second application program before starting the first application program on the current video watching intention of the target user.

9. A non-transitory computer-readable storage medium, comprising: The storage medium has a computer program stored therein, the computer program is loaded and executed by the processor to implement the information processing method based on multi-source data of a user according to any one of claims 1-8.

10. An electronic device comprising: The processor, the memory, and the computer program stored on the memory and executable on the processor, wherein the processor implements the information processing method based on multi-source data of a user according to any one of claims 1-8 when executing the computer program.

Images