Multimedia resource data release method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a multimedia resource data release method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining user behavior data in a preset time period; generating behavior path data according to the user behavior data, and determining target industry data corresponding to the behavior path data; inputting the behavior path data corresponding to the target industry data into a Markov model, and obtaining a transfer matrix corresponding to the target industry data output by the Markov model; determining removal effect data corresponding to the target industry data according to the transfer matrix; and according to the removal effect data, determining a delivery mode of multimedia resource data corresponding to the target industry data, and delivering the multimedia resource data according to the delivery mode. By adopting the method, the utilization rate of the multimedia resource data can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for delivering multimedia resource data. Background Art

[0002] Multimedia resource data is a way of presenting information in a variety of forms, including text, images, audio, and video. The rationality of multimedia resource data placement can enhance the influence of the publisher, so the rationality of multimedia resource data placement is particularly important.

[0003] In related technologies, the Markov model can be used to attribute the user's touch point behavior, obtain the attribution result, and guide the delivery of multimedia resource data based on the attribution result. However, the attribution result obtained directly using the Markov model is relatively general, resulting in unreasonable delivery of multimedia resource data and waste of multimedia resources. Summary of the invention

[0004] Based on this, it is necessary to provide a multimedia resource data delivery method, device, computer equipment, computer-readable storage medium and computer program product that can improve the utilization rate of multimedia resource data in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for delivering multimedia resource data, comprising:

[0006] Obtain user behavior data for a preset time period;

[0007] Generate behavior path data based on user behavior data, and determine the target industry data corresponding to the behavior path data;

[0008] Input the behavior path data corresponding to the target industry data into the Markov model, and obtain the transfer matrix corresponding to the target industry data output by the Markov model;

[0009] According to the transfer matrix, determine the removal effect data corresponding to the target industry data;

[0010] Based on the removal effect data, determine the delivery method of the multimedia resource data corresponding to the target industry data, and deliver the multimedia resource data according to the delivery method.

[0011] In one embodiment, behavior path data is generated based on user behavior data, including: determining a user identifier corresponding to the user behavior data, and classifying the user behavior data based on the user identifier to obtain a user behavior data set corresponding to the user identifier; obtaining the behavior occurrence time corresponding to each user behavior data in the user behavior data set; and sorting each user behavior data in the user behavior data set according to the order of the behavior occurrence time to generate behavior path data.

[0012] In one embodiment, the behavior path data includes first behavior path data and second behavior path data, and the user behavior data in the user behavior data set are sorted according to the order of the behavior occurrence time to generate the behavior path data, including: obtaining the first user behavior data, the second user behavior data, and the third user behavior data from the user behavior data set; wherein the first user behavior data is the user behavior data with the earliest behavior occurrence time; the second user behavior data is the user behavior data with the latest behavior occurrence time; the third user behavior data is the user behavior data with the behavior occurrence time between the earliest and the latest behavior occurrence time; when the third user behavior data is jump behavior data, obtaining the first user behavior data; four user behavior data and fifth user behavior data; wherein the fourth user behavior data is a behavior occurring time between the behavior occurring time of the first user behavior data and the behavior occurring time of the third user behavior data; the fifth user behavior data is the next user behavior data of the third user behavior data; the first user behavior data is taken as the starting point of the first behavior path data, the third user behavior data is taken as the end point of the first behavior path data, and the fourth user behavior data is sorted between the first user behavior data and the third user behavior data in the order of the behavior occurring time to generate the first behavior path data; the second behavior path data is generated according to the fifth user behavior data and the second user behavior data.

[0013] In an optional embodiment, second behavior path data is generated based on fifth user behavior data and second user behavior data, including: obtaining sixth user behavior data, wherein the behavior occurrence time of the sixth user behavior data is between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the second user behavior data; determining the time interval between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the sixth user behavior data; when the time interval is greater than a preset time interval, taking the seventh user behavior data corresponding to the time interval greater than the preset time interval as the end point of the second behavior path data, taking the fifth user behavior data as the starting point of the second behavior path data, and sorting other user behavior data between the fifth user behavior data and the seventh user behavior data in the order of the behavior occurrence time between the fifth user behavior data and the seventh user behavior data, so as to generate second behavior path data.

[0014] In one embodiment, after determining the time interval between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the sixth user behavior data, the method also includes: when the time interval is less than or equal to the preset time interval, taking the second user behavior data as the end point of the second behavior path data, taking the fifth user behavior data as the starting point of the second behavior path data, and sorting other user behavior data between the fifth user behavior data and the second user behavior data in the order of the behavior occurrence time between the fifth user behavior data and the second user behavior data to generate second behavior path data.

[0015] In one of the embodiments, determining the target industry data corresponding to the behavior path data includes: obtaining the last user behavior data in the behavior path data; determining the industry data corresponding to the last user behavior data, and using the industry data corresponding to the last user behavior data as the target industry data corresponding to the behavior path data.

[0016] In a second aspect, the present application also provides a multimedia resource data delivery device, including:

[0017] A behavior data acquisition module, used to acquire user behavior data for a preset time period;

[0018] An industry data determination module is used to generate behavior path data based on user behavior data, and determine target industry data corresponding to the behavior path data;

[0019] The transfer matrix acquisition module is used to input the behavior path data corresponding to the target industry data into the Markov model and obtain the transfer matrix output by the Markov model;

[0020] A transfer effect determination module, used for determining removal effect data according to a transfer matrix;

[0021] The delivery module is used to determine the delivery method of the multimedia resource data according to the migration effect data, and deliver the multimedia resource data according to the delivery method.

[0022] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method embodiments when executing the computer program.

[0023] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned method embodiments when the computer program is executed by a processor.

[0024] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned method embodiments when executed by a processor.

[0025] The above-mentioned multimedia resource data delivery method, device, computer equipment, computer-readable storage medium and computer program product, in the above-mentioned multimedia resource data delivery method, based on user behavior data, behavior path data is generated according to the user behavior data, and the target industry data corresponding to the behavior path data is determined according to the behavior path data, and the behavior path data corresponding to the target industry data is further input into the Markov model, and the removal effect data is determined based on the transfer matrix output by the Markov model, so that the multimedia resource data is delivered according to the removal effect data, and targeted processing of the target industry data can be achieved, so that the obtained removal effect data is clear and accurate, thereby effectively improving the rationality and accuracy of the multimedia resource data delivery, and thus improving the utilization rate of multimedia resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 A diagram of an application environment of a multimedia resource data delivery method in an embodiment;

[0028] Figure 2 A schematic diagram of a process of delivering multimedia resource data in one embodiment;

[0029] Figure 3 A flowchart of a multimedia resource data delivery method according to another embodiment;

[0030] Figure 4 It is a structural block diagram of a multimedia resource data delivery device in one embodiment;

[0031] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0033] The multimedia resource data delivery method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains the user behavior data of the preset time period transmitted by the terminal 102; generates behavior path data according to the user behavior data, and determines the target industry data corresponding to the behavior path data; inputs the behavior path data corresponding to the target industry data into the Markov model, and obtains the transfer matrix corresponding to the target industry data output by the Markov model; according to the transfer matrix, determines the removal effect data corresponding to the target industry data; according to the removal effect data, determines the delivery method of the multimedia resource data corresponding to the target industry data, and delivers the multimedia resource data according to the delivery method. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and the Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head mounted device may be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0034] In an exemplary embodiment, Figure 2 As shown, a multimedia resource data delivery method is provided, and the method is applied to Figure 1 The server in the example is used to illustrate, including the following steps 202 to 210. Among them:

[0035] Step 202: Obtain user behavior data for a preset time period.

[0036] The preset time period is used to represent the time period for obtaining user behavior data. For example, the preset time period can be half a month before the current time, or other time periods that are desired to be analyzed, which are not limited.

[0037] The user behavior data is used to characterize the action data generated by the user during the network interaction process. Optionally, the user behavior data may include but is not limited to the user's browsing, clicking, purchasing, commenting and other behaviors on websites, APPs (applications) and other platforms.

[0038] In one of the embodiments, the terminal records the user action data of the user when performing network interaction, and transmits the obtained user action data to the server, which processes the user behavior data.

[0039] Step 204, generating behavior path data based on the user behavior data, and determining target industry data corresponding to the behavior path data.

[0040] Among them, behavioral path data is used to characterize the user's access path in the website or APP.

[0041] In one embodiment, the behavior path data may be one or more. Optionally, the behavior path data corresponding to each user identification may be one or more. Exemplarily, the behavior path data includes first behavior path data and second behavior path data.

[0042] In one embodiment, the behavior occurrence time of the user behavior data is obtained, and the user behavior data is sorted according to the behavior occurrence time of the user behavior data to generate behavior path data.

[0043] In one of the embodiments, a user identifier corresponding to user behavior data is determined, and the user behavior data is classified according to the user identifier to obtain a user behavior data set corresponding to the user identifier; the behavior occurrence time corresponding to each user behavior data in the user behavior data set is obtained; and each user behavior data in the user behavior data set is sorted according to the order of the behavior occurrence time to generate behavior path data.

[0044] The user ID is used to distinguish different users so as to distinguish the user to which the user behavior data belongs.

[0045] The behavior occurrence time is used to represent the time information of the user behavior data. For example, if the user triggers the APP at a certain time on a certain day of a certain month, then the behavior occurrence time corresponding to the user behavior data that triggers the APP can be considered to be a certain time on a certain day of a certain month.

[0046] Optionally, corresponding user behavior data can be obtained according to the user identifier, and user behavior data with the same user identifier can be classified to obtain a user behavior data set corresponding to the user identifier, so that the user behavior data in the user behavior data set belong to the same user identifier, and the generation of behavior path data can be realized based on this.

[0047] Exemplarily, as shown in the following Table 1, Table 1 is a first user behavior data table.

[0048] Table 1 The first user behavior data table

[0049]

[0050] Optionally, user identifiers, such as User_01 and User_02, are obtained from the collected user behavior data, and user behavior data sets corresponding to the user identifiers are generated based on the user identifiers.

[0051] For example, for a user identified as User_01, the acquired data may be the data of the 1st, 2nd and 4th rows in the above Table 1. By extracting the data of the 1st, 2nd and 4th rows, the user behavior data set of the user identified as User_01 can be obtained. For a user identified as User_02, the acquired data may be the data of the 3rd and 5th rows in the above Table 1. By extracting the data of the 3rd and 5th rows, the user behavior data set of the user identified as User_02 can be obtained.

[0052] In one embodiment, the behavior occurrence time of each user behavior data in the user behavior data set is obtained, and the user behavior data is sorted according to the behavior occurrence time, so as to generate behavior path data.

[0053] Optionally, each user's behavior data may be sorted in the order of the time when the behavior occurred to generate behavior path data.

[0054] In an optional embodiment, first user behavior data, second user behavior data, and third user behavior data are obtained from a user behavior data set; when the third user behavior data is jump behavior data, fourth user behavior data and fifth user behavior data are obtained; the fifth user behavior data is the next user behavior data of the third user behavior data; the first user behavior data is used as the starting point of the first behavior path data, the third user behavior data is used as the end point of the first behavior path data, and the fourth user behavior data is sorted between the first user behavior data and the third user behavior data in chronological order of the behavior occurrence time to generate the first behavior path data.

[0055] Among them, the first user behavior data is the user behavior data with the earliest behavior time; the second user behavior data is the user behavior data with the latest behavior time; the third user behavior data is the user behavior data with a behavior time between the earliest and latest behavior times; the fourth user behavior data is the user behavior time between the behavior time of the first user behavior data and the behavior time of the third user behavior data.

[0056] The jump behavior data is used to characterize the jump of the web page caused by the current user behavior data. For example, when a user opens an APP, a link to another APP is displayed on the APP. The user triggers the link, and the behavior of triggering the link can be regarded as the jump behavior data.

[0057] In one embodiment, after obtaining a user behavior data set corresponding to a user identifier, the behavior occurrence time of the user behavior data included in the user behavior data set can be determined, and the first user behavior data corresponding to the earliest behavior occurrence time, the second user behavior data with the latest behavior occurrence time, and the third user behavior data with a behavior occurrence time between the behavior occurrence time of the first user behavior data and the behavior occurrence time of the second user behavior data can be determined, and behavior path data is generated based on the obtained first user behavior data, second user behavior data, and third user behavior data.

[0058] Exemplarily, the user behavior data corresponding to User_01 as shown in Table 1 above may be the data of the 1st row, the 2nd row, and the 4th row. It is determined that the behavior occurrence time of the user behavior data in the 1st row is 2024-04-24 16:37:52, the behavior occurrence time of the user behavior data in the 2nd row is 2024-04-24 16:39:04, and the behavior occurrence time of the user behavior data in the 4th row is 2024-04-24 16:45:20. By comparing the behavior occurrence time of the user behavior data in the 1st row, the behavior occurrence time of the user behavior data in the 2nd row, and the behavior occurrence time of the user behavior data in the 4th row, it can be concluded that the behavior occurrence time of the user behavior data in the 1st row is the earliest, and the user behavior data can be set as the first user behavior data, that is, Baidu opening screen is set as the first user behavior data.

[0059] Optionally, if the behavior of the user behavior data in the 4th row occurs the latest, the user behavior data in the 4th row is set as the second user behavior data, that is, Baidu search is set as the second user behavior data.

[0060] Optionally, the behavior occurrence time of the user behavior data in the second row is between the behavior occurrence time of the first user behavior data and the behavior occurrence time of the second user behavior data.

[0061] In one embodiment, the first user behavior data is taken as the starting point, the second user behavior data is taken as the end point, and the third user behavior data is sorted between the first user behavior data and the second user behavior data to form behavior path data. For example, the formed behavior path data may be Baidu opening screen → Baidu information flow → Baidu search.

[0062] In one embodiment, it is also possible to first determine whether the third user behavior data is jump data, and when the third user behavior data is jump data, the third user behavior data can be set as the end point of the behavior path data. Optionally, when the third user behavior data is jump data, the fourth user behavior data is obtained, the first user behavior data can be used as the starting point of the behavior path data, and the fourth user behavior data is obtained, and the fourth user behavior data is placed between the first user behavior data and the third user behavior data to generate the behavior path data.

[0063] Optionally, when there are multiple fourth user behavior data, when sorting the fourth user behavior data between the first user behavior data and the third user behavior data, the fourth user behavior data can be sorted in the order of the time when the behavior occurs to generate behavior path data.

[0064] For example, as shown in Table 2 below, Table 2 is a second user behavior data table.

[0065] Table 2 Second user behavior data table

[0066]

[0067] Optionally, at this time, the user behavior data in the table all correspond to the user identifier User_01.

[0068] Optionally, the user behavior data in the first row can be set as the first user behavior data, the user behavior data in the fifth row can be set as the second user behavior data, and the user behavior data in the second, third and fourth rows can be collectively referred to as the third user behavior data.

[0069] In one embodiment, assuming that the user behavior data in the 4th row is jump behavior data, the user behavior data in the 4th row is set as the end point of the behavior path data, that is, Baidu search is taken as the end point of the behavior path data. Optionally, the user behavior data in the 2nd and 3rd rows can be set as the fourth user behavior data.

[0070] Optionally, the fourth user behavior data is sorted between the first user behavior data and the third user behavior data to generate the first behavior path data. For example, Baidu opening screen → Baidu information flow → WeChat public account → Baidu search.

[0071] In one embodiment, assuming that the user behavior data in the third row is jump behavior data, the user behavior data in the third row is set as the end point of the behavior path data, that is, the WeChat public account is taken as the end point of the behavior path data. Optionally, the fourth user behavior data at this time is the user behavior data in the second row, and the first behavior path data formed at this time can be Baidu opening screen → Baidu information flow → WeChat public account.

[0072] In an optional embodiment, when the third user behavior data is jump behavior data, the fifth user behavior data can be obtained, and the fifth user behavior data is used as the starting point of the new behavior path data. Optionally, the sixth user behavior data is obtained; the time interval between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the sixth user behavior data is determined; when the time interval is greater than the preset time interval, the seventh user behavior data corresponding to the time interval greater than the preset time interval is used as the end point of the second behavior path data, the fifth user behavior data is used as the starting point of the second behavior path data, and other user behavior data between the fifth user behavior data and the seventh user behavior data are sorted between the fifth user behavior data and the seventh user behavior data in the order of the behavior occurrence time to generate the second behavior path data.

[0073] In an optional embodiment, when the time interval is less than or equal to the preset time interval, the second user behavior data is used as the end point of the second behavior path data, the fifth user behavior data is used as the starting point of the second behavior path data, and other user behavior data between the fifth user behavior data and the second user behavior data are sorted between the fifth user behavior data and the second user behavior data in the order of the time when the behavior occurs, so as to generate the second behavior path data.

[0074] The behavior occurrence time of the sixth user behavior data is between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the second user behavior data.

[0075] Optionally, the preset time interval can be set as needed, and there is no limitation on this. For example, the preset time interval can be 24 hours.

[0076] Exemplarily, as shown in Table 3 below, Table 3 is a user behavior data table.

[0077] Table 3 User behavior data table

[0078]

[0079] Optionally, the user behavior data in the first row of Table 3 above may be identified as the fifth user behavior data, that is, "Baidu opening screen" may be identified as the fifth user behavior data.

[0080] Optionally, the user behavior data in the fourth row in the above Table 3 is identified as the second user behavior data, that is, "Baidu search" is identified as the second user behavior data.

[0081] Optionally, the user behavior data in the 2nd and 3rd rows in the above Table 3 are collectively referred to as sixth user behavior data, that is, "Baidu information flow" and "WeChat public account" are collectively referred to as sixth user behavior data.

[0082] In one embodiment, the behavior occurrence time of the fifth user behavior data is 2024-04-24 16:37:52, and the behavior occurrence time of the sixth user behavior data is 2024-04-24 16:39:04 and 2024-04-25 16:42:35. By comparing the time interval between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the sixth user behavior data, it can be 2024-04-24 16:37:52-2024-04-24 16:39:04, and 2024-04-24 16:37:52-2024-04-25 16:42:35. It can be seen that the time interval between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the user behavior data in the third row in the above Table 3 exceeds the preset time interval, and the user behavior data in the third row is identified as the end point of the new behavior path data.

[0083] Optionally, the fifth user behavior data is used as the starting point, the sixth user behavior data involved in the third row is used as the end point, and the seventh user behavior data whose behavior occurs between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the sixth user behavior data is sorted between the fifth user behavior data and the sixth user behavior data to generate the second behavior path data. Exemplarily, the second behavior path data can be Baidu opening screen → Baidu information flow → WeChat public account.

[0084] In one embodiment, if there are multiple seventh user behavior data, the seventh user behavior data may be sorted between the fifth user behavior data and the sixth user behavior data according to the chronological order of the behavior occurrence time.

[0085] In an optional embodiment, if the time interval between the behavior occurrence time of the sixth user behavior data and the behavior occurrence time of the fifth user behavior data is less than or equal to the preset time interval, the second user behavior data is used as the end point of the second behavior path data.

[0086] Exemplarily, as shown in the following Table 4, Table 4 is a fourth user behavior data table.

[0087] Table 4 Fourth user behavior data table

[0088]

[0089] The behavior occurrence time of the fifth user behavior data is 2024-04-24 16:37:52, and the behavior occurrence time of the sixth user behavior data is 2024-04-24 16:39:04 and 2024-04-24 16:42:35. By comparing the time interval between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the sixth user behavior data, it can be 2024-04-24 16:37:52-2024-04-24 16:39:04, and 2024-04-24 16:37:52-2024-04-24 16:42:35. It can be seen that the time interval between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the sixth user behavior data is less than or equal to the preset time interval. The second user behavior data is taken as the end point of the second behavior path data, and the sixth user behavior data is sorted between the fifth user behavior data and the second user behavior data to generate the second behavior path data. Exemplarily, the second behavior path data formed may be Baidu opening screen→Baidu information flow→WeChat public account→Baidu search.

[0090] In an optional embodiment, when there are multiple sixth user behavior data, they can be sorted in the fifth user behavior data and the second user behavior data according to the chronological order of the time when the behavior of the sixth user behavior data occurs.

[0091] In one embodiment, after obtaining the user behavior data set, the time interval between the user behavior data with the earliest behavior occurrence time and other user behavior data can also be determined based on the behavior occurrence time of each user behavior data in the user behavior data set, and the user behavior data exceeding the preset time interval is used as the end point of the behavior path data. Optionally, the next user behavior data of the user behavior data exceeding the preset time interval is used as the starting point of the new behavior path data, and the above steps of determining the time interval to determine the end point of the new behavior path data are repeated to generate new behavior path data, and further determine the next user behavior data of the end point of the new behavior path data as the starting point of the next behavior path data, until the user behavior data in the user behavior data set has been traversed.

[0092] In one of the embodiments, in the case where the behavior path data is first generated based on the time interval between the behavior occurrence moments of each user behavior data, the formed behavior path data can be further detected on the basis of the generated behavior path data whether the user behavior data jumps or not. When the user behavior data included in the behavior path data is jump behavior data, the corresponding behavior path data can be split, and the user behavior data that is the jump behavior data is taken as the end point, and the starting point of the behavior path data is taken as the starting point of sub-behavior path data to generate sub-behavior path data, and the next user behavior data of the jump behavior data is taken as the starting point of the next sub-behavior path data, and the end point of the behavior path data is taken as the end point of the next sub-behavior path data to generate the next sub-behavior path data.

[0093] Optionally, when the behavior path data is split using the user behavior data as the jump behavior data, the sorting order of the user behavior data in each sub-behavior path data obtained by the splitting is the same as the sorting order of the behavior path data.

[0094] In an optional embodiment, the time interval between user behavior data can also be detected, and whether the user behavior data is jump behavior data can be detected at the same time, and after detecting the time interval and the jump behavior data, the user behavior data in the user data set can be divided based on the detected time interval result and the jump behavior data result to obtain behavior path data. Optionally, the user behavior data included in the divided behavior path data is sorted in the order of the behavior occurrence time.

[0095] In one embodiment, each user identification may be processed separately to obtain each behavior path data corresponding to each user identification, and further processing may be performed based on each behavior path data corresponding to each user identification.

[0096] In one embodiment, industry data of each behavior path data may be obtained and processed based on the industry data.

[0097] Optionally, obtain the last user behavior data in the behavior path data; determine the industry data corresponding to the last user behavior data, and use the industry data corresponding to the last user behavior data as the target industry data corresponding to the behavior path data.

[0098] In an optional embodiment, industry data corresponding to the user behavior data may be generated in advance, so that when needed, the user behavior data may be used to determine the corresponding industry data, and the determined industry data corresponding to the user behavior data may be used as target industry data.

[0099] In one embodiment, after determining the target industry data corresponding to each behavior path data, the behavior path data corresponding to the same target industry data can be clustered based on the target industry data to form a behavior path data set corresponding to the target industry data, and the behavior path data set is processed based on the behavior path data set. Exemplarily, the behavior path data obtained based on the industry data, the number corresponding to the behavior path data, and the proportion occupied in the total data can be clearly determined, as shown in Table 5 below. Among them, Table 5 is an industry data table.

[0100] Table 5 Industry data table

[0101] Serial number Industry data quantity Proportion 0 figure 3761 18.3885 1 Education and Training 3023 14.7802 2 Travel 2748 13.4357 3 Film and TV Animation 2253 11.0155 4 Life and emotions 1761 8.6100 …… …… …… ……

[0102] Optionally, after obtaining the user behavior data, you can also obtain label information corresponding to the user behavior data, input the label information into the industry data generation model, and obtain industry data corresponding to the user behavior data output by the industry data generation model.

[0103] In one embodiment, the industry data generation model can be pre-generated and trained using training data. Optionally, the training data includes training label data and corresponding training industry data.

[0104] Step 206: input the behavior path data corresponding to the target industry data into the Markov model, and obtain the transfer matrix corresponding to the target industry data output by the Markov model.

[0105] Step 208: Determine the removal effect data corresponding to the target industry data according to the transfer matrix.

[0106] The Markov model is a mathematical model used to calculate a transfer matrix based on the behavior path data corresponding to the target industry data. Optionally, the Markov model is a prior art and will not be described in detail here.

[0107] Among them, the transfer matrix is ​​used to store the transfer efficiency data, and the transfer effect data is used to describe the probability of the system transferring from one state to another.

[0108] Among them, the removal effect data is used to characterize the impact on the system state transition probability after removing certain elements in a certain state.

[0109] In one embodiment, after generating a behavior path data set corresponding to the target industry data, each behavior path data in the behavior path data set is input into a Markov model, and a transfer matrix output by the Markov model is obtained.

[0110] For example, taking "travel" as an example, there are a total of 2748 behavioral path data, which can be input into the Markov model to obtain the contribution values ​​of different user behavior data. For example, as shown in Table 6 below, [0.5, 0.5] in the first row is used to characterize the contribution values ​​of the two touch points in the user behavior path "WeChat Official Account > WeChat Official Account". Among them, Table 6 shows the contribution values ​​of user behavior data in the behavior path data.

[0111] Table 6 Contribution value of user behavior data in behavior path data

[0112] 0 [0.5，0.5] 1 [0.5，0.5] 2 [0.08844385449925324，0.08844385449925324，0.1…] 3 [0.654957136847219，0.34504286315278093] 4 [1.0] …… …… 2743 [1.0] 2744 [0.07289361999915586，0.42629578148855773，0.4] 2745 [1.0] 2746 [1.0] 2747 [0.1853293066457793，0.11412034695678124，0.18…]

[0113] In one embodiment, the contribution of user behavior data in the target industry data may also be output, as shown in the following Table 7. Table 7 is a user behavior data contribution value table.

[0114] Table 7 User behavior data contribution value table

[0115] 0 Tik Tok 173.556336 1 Baidu Information Flow 184.689355 2 WeChat Official Account 1056.599156 3 Zhihu 159.101858 4 Baidu Search 650.622745 5 Weibo 180.671122 6 Baidu opening screen 342.759430 …… …… ……

[0116] In one embodiment, as shown in Table 8, the transition matrix may be displayed in a table form to clearly determine the transition probability when converting between the user behavior data. Table 8 is a transition matrix table.

[0117] Table 8 Transfer matrix

[0118]

[0119] In an optional embodiment, after the transfer matrix is ​​obtained, removal effect data may be generated based on the transfer matrix. The specific calculation process is prior art and will not be described in detail herein.

[0120] Exemplarily, the calculated removal effect data may be as shown in the following Table 9, wherein Table 9 is a removal effect data table.

[0121] Table 9 Removal effect data table

[0122]

[0123] Step 210, determining a delivery method of the multimedia resource data corresponding to the target industry data according to the removal effect data, and delivering the multimedia resource data according to the delivery method.

[0124] Among them, multimedia resource data is used to represent information resources that combine multiple media forms such as text, graphics, images, sounds, videos, and animations.

[0125] The delivery mode is used to characterize the specific method and strategy of delivering multimedia resource data.

[0126] In one embodiment, after the removal effect data is acquired, the multimedia resource data is delivered according to the removal effect data.

[0127] For example, for the tourism industry, the removal effect data corresponding to the user behavior data of "WeChat Official Account" is relatively large, the removal effect data corresponding to the user behavior data of "Baidu Search" is the second largest, the removal effect data corresponding to the user behavior data of "Baidu Open Screen" is the third largest, "Weibo" and "Baidu Information Flow" are the fourth, "Tik Tok" is the fifth, and "Zhihu" is the sixth. When multimedia data is delivered based on the tourism industry, it can be mainly delivered on WeChat Official Account, followed by Baidu Search, and if there is still room for delivery, it can be delivered on Baidu Open Screen.

[0128] In the above-mentioned multimedia resource data delivery method, user behavior data is used as a basis, behavior path data is generated according to the user behavior data, and target industry data corresponding to the behavior path data is determined according to the behavior path data. The behavior path data corresponding to the target industry data is further used as input and input into the Markov model, and the removal effect data is determined based on the transfer matrix output by the Markov model, so that the multimedia resource data is delivered according to the removal effect data. Targeted processing of the target industry data can be achieved, so that the obtained removal effect data is clear and accurate, thereby effectively improving the accuracy of multimedia resource data delivery, and thus improving the utilization rate of multimedia resources.

[0129] In an exemplary embodiment, Figure 3 As shown, a multimedia resource data delivery method is provided, and the method is applied to Figure 1 The server in the example is used to illustrate, including the following steps 302 to 334. Among them:

[0130] Step 302: Obtain user behavior data for a preset time period.

[0131] Step 304: determine the user identification corresponding to the user behavior data, and classify the user behavior data according to the user identification to obtain a user behavior data set corresponding to the user identification.

[0132] Step 306, obtaining the behavior occurrence time corresponding to each user behavior data in the user behavior data set.

[0133] Step 308: Obtain first user behavior data, second user behavior data, and third user behavior data from the user behavior data set.

[0134] Among them, the first user behavior data is the user behavior data with the earliest behavior occurrence time; the second user behavior data is the user behavior data with the latest behavior occurrence time; and the third user behavior data is the user behavior data with a behavior occurrence time between the earliest and latest behavior occurrence times.

[0135] Step 310 , determining whether the third user behavior data is jump behavior data, if so, executing step 312 , if not, executing step 316 .

[0136] Step 312, obtaining the fourth user behavior data and the fifth user behavior data.

[0137] Among them, the fourth user behavior data is the behavior occurrence time between the behavior occurrence time of the first user behavior data and the behavior occurrence time of the third user behavior data; the fifth user behavior data is the next user behavior data of the third user behavior data.

[0138] Step 314, taking the first user behavior data as the starting point of the first behavior path data, taking the third user behavior data as the end point of the first behavior path data, and sorting the fourth user behavior data between the first user behavior data and the third user behavior data in the order of the time when the behavior occurred, so as to generate the first behavior path data.

[0139] Step 316, obtaining sixth user behavior data.

[0140] The behavior occurrence time of the sixth user behavior data is between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the second user behavior data.

[0141] Step 318: determine the time interval between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the sixth user behavior data.

[0142] Step 320 , determining whether the time interval is greater than a preset time interval, if so, executing step 322 , if not, executing step 324 .

[0143] Step 322, taking the seventh user behavior data corresponding to a time interval greater than the preset time interval as the end point of the second behavior path data, taking the fifth user behavior data as the starting point of the second behavior path data, and sorting the other user behavior data between the fifth user behavior data and the seventh user behavior data in the order of the time when the behavior occurred between the fifth user behavior data and the seventh user behavior data, so as to generate the second behavior path data.

[0144] Step 324, taking the second user behavior data as the end point of the second behavior path data, taking the fifth user behavior data as the starting point of the second behavior path data, and sorting the other user behavior data between the fifth user behavior data and the second user behavior data in the order of the time when the behavior occurred between the fifth user behavior data and the second user behavior data, so as to generate the second behavior path data.

[0145] Step 326, obtaining the last user behavior data in the first behavior path data and / or the second behavior path data.

[0146] Step 328, determine the industry data corresponding to the last user behavior data, and use the industry data corresponding to the last user behavior data as the target industry data corresponding to the behavior path data.

[0147] Step 330: input the behavior path data corresponding to the target industry data into the Markov model, and obtain the transfer matrix corresponding to the target industry data output by the Markov model.

[0148] Step 332, determining the removal effect data corresponding to the target industry data according to the transfer matrix.

[0149] Step 334, determining a delivery method of the multimedia resource data corresponding to the target industry data according to the removal effect data, and delivering the multimedia resource data according to the delivery method.

[0150] In the above-mentioned multimedia resource data delivery method, user behavior data is used as a basis, behavior path data is generated according to the user behavior data, and target industry data corresponding to the behavior path data is determined according to the behavior path data. The behavior path data corresponding to the target industry data is further used as input and input into the Markov model, and the removal effect data is determined based on the transfer matrix output by the Markov model, so that the multimedia resource data is delivered according to the removal effect data. Targeted processing of the target industry data can be achieved, so that the obtained removal effect data is clear and accurate, thereby effectively improving the accuracy of multimedia resource data delivery, and thus improving the utilization rate of multimedia resources.

[0151] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0152] Based on the same inventive concept, the embodiment of the present application also provides a multimedia resource data delivery device for implementing the multimedia resource data delivery method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more multimedia resource data delivery device embodiments provided below can refer to the limitations of the multimedia resource data delivery method above, and will not be repeated here.

[0153] In an exemplary embodiment, Figure 4 As shown, a multimedia resource data delivery device is provided, including: a behavior data acquisition module 402, an industry data determination module 404, a transfer matrix acquisition module 406, a transfer effect determination module 408 and a delivery module 410, wherein:

[0154] Behavior data acquisition module 402, used to acquire user behavior data in a preset time period;

[0155] The industry data determination module 404 is used to generate behavior path data according to the user behavior data, and determine the target industry data corresponding to the behavior path data;

[0156] The transfer matrix acquisition module 406 is used to input the behavior path data corresponding to the target industry data into the Markov model and obtain the transfer matrix output by the Markov model;

[0157] A transfer effect determination module 408 is used to determine removal effect data according to the transfer matrix;

[0158] The delivery module 410 is used to determine a delivery method of the multimedia resource data according to the migration effect data, and deliver the multimedia resource data according to the delivery method.

[0159] In one embodiment, the industry data determination module is also used to determine the user identifier corresponding to the user behavior data, and classify the user behavior data according to the user identifier to obtain a user behavior data set corresponding to the user identifier; obtain the behavior occurrence time corresponding to each user behavior data in the user behavior data set; and sort each user behavior data in the user behavior data set according to the order of the behavior occurrence time to generate behavior path data.

[0160] In one embodiment, the behavior path data includes first behavior path data and second behavior path data, and the industry data determination module is further used to obtain first user behavior data, second user behavior data and third user behavior data from the user behavior data set; wherein the first user behavior data is the user behavior data with the earliest behavior occurrence time; the second user behavior data is the user behavior data with the latest behavior occurrence time; the third user behavior data is the user behavior data with the behavior occurrence time between the earliest and latest behavior occurrence times; when the third user behavior data is jump behavior data, obtain fourth user behavior data and fifth user behavior data; wherein the fourth user behavior data is the behavior occurrence time between the behavior occurrence time of the first user behavior data and the behavior occurrence time of the third user behavior data; the fifth user behavior data is the next user behavior data of the third user behavior data; the first user behavior data is used as the starting point of the first behavior path data, the third user behavior data is used as the end point of the first behavior path data, and the fourth user behavior data is sorted between the first user behavior data and the third user behavior data in the order of the behavior occurrence time to generate the first behavior path data; the second behavior path data is generated according to the fifth user behavior data and the second user behavior data.

[0161] In one embodiment, the industry data determination module is also used to obtain sixth user behavior data, wherein the behavior occurrence time of the sixth user behavior data is between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the second user behavior data; determine the time interval between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the sixth user behavior data; when the time interval is greater than the preset time interval, use the seventh user behavior data corresponding to the time interval greater than the preset time interval as the end point of the second behavior path data, use the fifth user behavior data as the starting point of the second behavior path data, and sort other user behavior data between the fifth user behavior data and the seventh user behavior data in the order of the behavior occurrence time between the fifth user behavior data and the seventh user behavior data to generate the second behavior path data.

[0162] In an optional embodiment, the industry data determination module is also used to, when the time interval is less than or equal to a preset time interval, use the second user behavior data as the end point of the second behavior path data, use the fifth user behavior data as the starting point of the second behavior path data, and sort other user behavior data between the fifth user behavior data and the second user behavior data in the order of the time when the behavior occurred between the fifth user behavior data and the second user behavior data, so as to generate the second behavior path data.

[0163] In one embodiment, the industry data determination module is also used to obtain the last user behavior data in the behavior path data; determine the industry data corresponding to the last user behavior data, and use the industry data corresponding to the last user behavior data as the target industry data corresponding to the behavior path data.

[0164] Each module in the multimedia resource data delivery device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0165] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for delivering multimedia resource data is implemented.

[0166] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0167] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0168] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0169] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0170] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0171] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0172] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0173] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A multimedia resource data delivery method, characterized in that: The method comprises: Obtain user behavior data for a preset time period; Generate behavior path data according to the user behavior data, and determine the target industry data corresponding to the behavior path data; Inputting the behavior path data corresponding to the target industry data into the Markov model, and obtaining the transfer matrix corresponding to the target industry data output by the Markov model; Determine the removal effect data corresponding to the target industry data according to the transfer matrix; According to the removal effect data, a delivery method of the multimedia resource data corresponding to the target industry data is determined, and the multimedia resource data is delivered according to the delivery method.

2. The method according to claim 1, characterized in that The generating behavior path data according to the user behavior data includes: Determine a user identifier corresponding to the user behavior data, and classify the user behavior data according to the user identifier to obtain a user behavior data set corresponding to the user identifier; Obtaining the behavior occurrence time corresponding to each user behavior data in the user behavior data set; According to the order of the behavior occurrence time, each user behavior data in the user behavior data set is sorted to generate behavior path data.

3. The method according to claim 2, characterized in that The behavior path data includes first behavior path data and second behavior path data, and the user behavior data in the user behavior data set are sorted according to the order of the behavior occurrence time to generate the behavior path data, including: Acquire first user behavior data, second user behavior data, and third user behavior data from the user behavior data set; wherein the first user behavior data is the user behavior data with the earliest behavior occurrence time; the second user behavior data is the user behavior data with the latest behavior occurrence time; and the third user behavior data is the user behavior data with the behavior occurrence time between the earliest and the latest behavior occurrence time; When the third user behavior data is jump behavior data, fourth user behavior data and fifth user behavior data are obtained; wherein the fourth user behavior data is a behavior occurring at a time between the behavior occurring at the first user behavior data and the behavior occurring at the third user behavior data; and the fifth user behavior data is the next user behavior data of the third user behavior data; Taking the first user behavior data as the starting point of the first behavior path data, taking the third user behavior data as the end point of the first behavior path data, and sorting the fourth user behavior data between the first user behavior data and the third user behavior data in the order of the behavior occurrence time, so as to generate the first behavior path data; The second behavior path data is generated according to the fifth user behavior data and the second user behavior data.

4. The method according to claim 3, characterized in that The step of generating the second behavior path data according to the fifth user behavior data and the second user behavior data includes: Acquire sixth user behavior data, wherein the behavior occurrence time of the sixth user behavior data is between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the second user behavior data; Determine a time interval between a time when the behavior of the fifth user behavior data occurs and a time when the behavior of the sixth user behavior data occurs; When the time interval is greater than the preset time interval, the seventh user behavior data corresponding to the time interval greater than the preset time interval is used as the end point of the second behavior path data, the fifth user behavior data is used as the starting point of the second behavior path data, and other user behavior data between the fifth user behavior data and the seventh user behavior data are sorted between the fifth user behavior data and the seventh user behavior data in the order of the time when the behavior occurs, so as to generate the second behavior path data.

5. The method according to claim 4, characterized in that After determining the time interval between the behavior occurrence time of the fifth user behavior data and the behavior occurrence time of the sixth user behavior data, the method further includes: When the time interval is less than or equal to the preset time interval, the second user behavior data is taken as the end point of the second behavior path data, the fifth user behavior data is taken as the starting point of the second behavior path data, and other user behavior data between the fifth user behavior data and the second user behavior data are sorted between the fifth user behavior data and the second user behavior data in the order of the time when the behavior occurs, so as to generate the second behavior path data.

6. The method according to any one of claims 1 to 5, characterized in that: The determining of the target industry data corresponding to the behavior path data includes: Obtain the last user behavior data in the behavior path data; Determine the industry data corresponding to the last user behavior data, and use the industry data corresponding to the last user behavior data as the target industry data corresponding to the behavior path data.

7. A multimedia resource data delivery device, characterized in that: The device comprises: A behavior data acquisition module, used to acquire user behavior data for a preset time period; An industry data determination module, used to generate behavior path data according to the user behavior data, and determine the target industry data corresponding to the behavior path data; A transfer matrix acquisition module, used to input the behavior path data corresponding to the target industry data into the Markov model, and obtain the transfer matrix output by the Markov model; A transfer effect determination module, used to determine removal effect data according to the transfer matrix; The delivery module is used to determine a delivery method of the multimedia resource data according to the removal effect data, and deliver the multimedia resource data according to the delivery method.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images