User behavior analysis method, device, equipment and medium based on large-screen TV

Abstract

The present invention discloses a user behavior analysis method, device, computer equipment and storage medium based on a large-screen television. The method is implemented by: obtaining the click behavior data of the user during the viewing process, which includes the click position and click time; encoding the click position to obtain the click position code; arranging the click position code based on the click time to obtain a user behavior conversation sequence; based on the user behavior conversation sequence, generating a user behavior dynamic line diagram, which is used to display the flow path and traffic distribution between pages of each level; based on the user behavior dynamic line diagram, user behavior modeling is performed to predict user behavior to perform corresponding operations. By collecting the click behavior data of the user during the viewing process, constructing the user behavior conversation sequence, and generating the user behavior dynamic line diagram, the user's behavior trajectory and traffic distribution on the large-screen television can be fully and accurately displayed, providing powerful operational decision support for operators.

Description

Technical Field

[0001] The present invention relates to the field of big data analysis and visualization technology, and in particular to a user behavior analysis method, device, computer equipment and storage medium based on a large-screen television. Background Art

[0002] With the popularity of smart TVs and the development of Internet technology, large-screen TVs have become an important channel for home entertainment and information acquisition. However, how to effectively utilize user viewing behavior data on large-screen TVs to optimize content recommendations and improve user experience has become a major challenge facing large-screen TV operators.

[0003] Traditional technologies can only collect partial behavioral data during the user's viewing process, such as play, pause, fast forward, etc., but cannot fully capture all user operations on the TV screen, such as browsing, searching, paying, etc. In addition, the user behavior analysis is not deep enough. When analyzing user viewing behavior, it often stays at the surface level, such as counting viewing time, program type preferences, etc., but lacks the exploration of the deep motivations and needs behind user behavior, making it difficult to accurately reflect the user's behavior patterns and changing trends in different scenarios. Summary of the invention

[0004] Based on this, it is necessary to provide a user behavior analysis method, device, computer equipment and storage medium based on a large-screen TV to address the above technical problems, so as to solve at least one problem existing in the above-mentioned prior art.

[0005] In a first aspect, a user behavior analysis method based on a large-screen TV is provided, comprising:

[0006] Acquire the user's click behavior data during the viewing process, wherein the click behavior data includes the click position and the click time;

[0007] Encoding the click position to obtain a click position code;

[0008] Arranging the click position codes based on the click time to obtain a user behavior session sequence;

[0009] Based on the user behavior session sequence, a user behavior flow chart is generated, wherein the user behavior flow chart is used to display the flow path and traffic distribution between pages at each level;

[0010] User behavior modeling is performed based on the user behavior flow chart to predict user behavior and perform corresponding operations.

[0011] In one embodiment, after obtaining the click behavior data of the user during the viewing process, the method includes:

[0012] Determine whether the current clicked page is the target page;

[0013] If the currently clicked page is a target page, the target page is page-coded.

[0014] In one embodiment, after arranging the click position codes based on the click time to obtain the user behavior session sequence, the method includes:

[0015] Determine whether there are multiple consecutive identical click position codes in the user behavior session sequence, or whether there are consecutive repeated click behavior tracks;

[0016] If so, retain a same click position code or a repeated click behavior track in the user behavior session sequence.

[0017] In one embodiment, after arranging the click position codes based on the click time to obtain the user behavior session sequence, the method includes:

[0018] Determine the page level corresponding to the user behavior session sequence;

[0019] When the page level is greater than a preset number of levels, and the total traffic of each page is less than a preset traffic threshold, the page level corresponding to the user behavior session sequence is set to the preset number of levels.

[0020] In one embodiment, the user behavior modeling is performed based on the user behavior flow chart to predict the user behavior and perform the corresponding operation, including:

[0021] Conducting an in-depth analysis of the user behavior dynamic line diagram to identify the optimal ordering dynamic line, the optimal movie viewing dynamic line, and the order loss dynamic line;

[0022] Based on the optimal ordering route, the optimal movie-watching route, and the order-loss route, an ordering path report, a movie-watching path report, and an order-loss path report are generated respectively;

[0023] Based on the order loss flow, an order path report, a movie viewing path report and an order loss path report are respectively generated to adjust the content recommendation strategy, page layout and operation process.

[0024] In one embodiment, the user behavior dynamic line diagram is deeply analyzed to identify the optimal ordering dynamic line, the optimal movie watching dynamic line, and the order loss dynamic line, including:

[0025] Counting the user behavior paths that generate orders in the user behavior path diagram to determine a plurality of optimal user ordering paths that generate a number of orders greater than a preset number;

[0026] The user behavior moving lines in the user behavior moving line diagram are sorted in descending order according to the movie watching time, so as to determine a plurality of optimal user movie watching moving lines whose movie watching time exceeds a preset time.

[0027] Statistics are collected on the user behavior flow charts in which unsuccessful orders are placed, so as to determine the order loss flow.

[0028] In one embodiment, encoding the click position to obtain the click position code includes:

[0029] Based on the click position, determine the click area and the click page;

[0030] Calling a click position code mapping table corresponding to the click page;

[0031] The click position code corresponding to the click area is searched in the click position code mapping table.

[0032] In a second aspect, a user behavior analysis device based on a large-screen television is provided, the device comprising:

[0033] A click behavior data acquisition unit, used to acquire the click behavior data of the user during the viewing process, wherein the click behavior data includes the click position and the click time;

[0034] A position encoding unit, used for encoding the click position to obtain a click position code;

[0035] A user behavior conversation sequence generating unit, configured to arrange the click position codes based on the click time to obtain a user behavior conversation sequence;

[0036] A user behavior flow chart generating unit, used to generate a user behavior flow chart based on the user behavior session sequence, wherein the user behavior flow chart is used to display the flow path and traffic distribution between pages of each level;

[0037] The user behavior analysis unit is used to perform user behavior modeling based on the user behavior flow chart, predict user behavior, and perform corresponding operations.

[0038] In a third aspect, a computer device is provided, comprising a memory, a processor, and computer-readable instructions stored in the memory and running on the processor, wherein when the processor executes the computer-readable instructions, the user behavior analysis method based on a large-screen TV as described above is implemented.

[0039] In a fourth aspect, a readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the user behavior analysis method based on a large-screen TV as described above is implemented.

[0040] The above-mentioned user behavior analysis method, device, computer equipment and storage medium based on a large-screen TV, and its method implementation include: obtaining the click behavior data of the user during the viewing process, the click behavior data including the click position and the click time; encoding the click position to obtain the click position code; arranging the click position code based on the click time to obtain a user behavior conversation sequence; based on the user behavior conversation sequence, generating a user behavior dynamic line diagram, the user behavior dynamic line diagram is used to display the flow path and traffic distribution between pages of each level; based on the user behavior dynamic line diagram, user behavior modeling is performed to predict user behavior to perform corresponding operations. In the embodiment of the present application, by collecting the click behavior data of the user during the viewing process, constructing a user behavior conversation sequence, and generating a user behavior dynamic line diagram, the user's behavior trajectory and traffic distribution on the large-screen TV can be fully and accurately displayed, providing operators with powerful operational decision support to improve user experience and business conversion rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0042] Figure 1 It is a flow chart of a method for analyzing user behavior based on a large-screen TV in one embodiment of the present invention;

[0043] Figure 2 is a schematic diagram of an interface of a position coding method in one embodiment of the present invention;

[0044] Figure 3 is a user behavior dynamic diagram in one embodiment of the present invention;

[0045] Figure 4 is a structural schematic diagram of a user behavior analysis device based on a large-screen television in one embodiment of the present invention;

[0046] Figure 5 is a schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] The present application provides a user behavior analysis method based on a large-screen TV. The method includes the steps of data collection, behavior coding, sequence construction, flow chart generation, flow chart configuration and optimization, data analysis and report output, etc. It can comprehensively and accurately display the user's behavior trajectory and traffic distribution on the large-screen TV, and provide powerful operational decision-making support for operators.

[0049] In one embodiment, if Figure 1 As shown, a user behavior analysis method based on a large-screen TV is provided, comprising the following steps:

[0050] In step S110, the click behavior data of the user during the viewing process is obtained, and the click behavior data includes the click position and the click time;

[0051] Optionally, the operating system of the large-screen TV or third-party applications, such as various video websites, can be used to obtain the user's click behavior data during the viewing process, such as touch operations on the screen or key operations on the screen through a remote control device, etc. The click behavior data may specifically include data such as click location, click time, and viewing duration.

[0052] Exemplarily, after the user enters the large-screen TV interface, he can use the remote control to select and watch programs according to his preferences. The large-screen TV interface screen is composed of several clickable locations (recommended positions) to enter the interfaces corresponding to different channels, such as TV series, movies, animations, and other channels. After the user clicks these locations, he enters the next-level page, such as the TV series interface. The user can enter different next-level pages by clicking on different recommended positions. If the user is not interested in the content of the current recommended position in the current screen, he can slide to other recommended positions, and then click on the corresponding recommended position to enter the next-level screen of the recommended position. Similarly, if the user is not interested in the content of the entire channel, he can switch to other channels, then click on the recommended position in this channel, and then enter the corresponding next-level screen. However, whether you click on the recommended position on the homepage to enter the next screen, or click on the recommended position after switching channels to enter the next screen, only one click is made. At this time, data on the user's click behavior on the large-screen TV can be collected to form click behavior data.

[0053] It should be noted that the collected click business data should cover the entire process from the user entering the large-screen interface to leaving, ensuring the integrity and accuracy of the data.

[0054] In step S120, the click position is encoded to obtain a click position code;

[0055] In the embodiment of the present application, feature extraction is performed on the collected click behavior data, for example, a feature extraction network, such as a convolutional neural network, can be used to obtain features such as click position and click time. The click position can be coded and defined. For example, see Figure 2 Taking the TV screen as an example, it includes multiple recommended position areas, each of which can correspond to different codes. For example, the first row can be C1-11, C1-12, C1-13 from left to right, the second row can be C1-23, and the third row can be C1-31, C1-32, C1-33, C1-34 from left to right. Then the following can be formed: Figure 2 Schematic diagram of interface position coding is shown.

[0056] It should be noted that since the screen may include multiple levels of interfaces and some target pages, such as a cashier interface, a member interface, etc., in order to distinguish different interfaces, different codes may be configured for different interfaces, for example, the cashier interface may be represented by the letter C, and the member interface may be represented by the letter V, etc. Different click positions of different interfaces may be represented according to the click position codes.

[0057] In step S130, the click position codes are arranged based on the click time to obtain a user behavior conversation sequence;

[0058] Optionally, according to the order of click time corresponding to different click positions, the click position codes can be sorted in the order of click time to obtain a position sequence, that is, a user behavior session, such as C1-11, C2-32, C cashier, D order successful. Each session sequence represents a complete user viewing behavior process, including entering from the homepage, jumping to the middle page, and finally exiting. For a user entering the screen multiple times or the behavior of different users entering the screen, such a sequence will be generated, as shown in the following table:

[0059] User behavior flow table:

[0060]

[0061] From the above table, we can see that the user behavior session sequence of user 1 is C1-11, C2-32, C cashier, D order successful. The user behavior session sequence of user 2 is C1-12, C cashier. The user behavior session sequence of user 3 is C1-11, C2-32, C3-22, C2-31.

[0062] It should be noted that the codes of pages at different levels may be different, and the recommendation positions of pages at different levels may also be divided differently.

[0063] In step S140, a user behavior flow chart is generated based on the user behavior session sequence, and the user behavior flow chart is used to show the flow path and traffic distribution between pages of each level;

[0064] Optionally, the user behavior flow conversation table can be analyzed. It can be seen that for L1 layer actions (i.e., the user's first click behavior), there are a finite number of positions (denoted as C1), and there are N1 user click actions (N1>=C1), that is, there are multiple points that are clicked multiple times; at L2 layer, these N1 actions may fall on C2 positions, and the number of clicks from one of the C1 positions is dispersed to one or more C2 positions; similarly, the number of clicks in the C2 position is dispersed to one or more C3 positions of the next layer of actions, such as user 1 and user 3. At the same time, it is also possible that the flow does not flow to the next layer, that is, the user stops at the second layer, such as user 2.

[0065] See also Figure 3 , shows a user behavior dynamic line diagram, such as Figure 3 As shown, there are 10 user behavior sessions for this user, 5 of which first click C1-11, then 3 of them click C2-32, 1 of them enters the cashier, and the other 1 clicks C2-33; of the three who clicked C2-32, 2 of them entered the cashier, and 1 clicked C3-22.

[0066] By drawing each user's behavior session in the above manner, the following can be formed: Figure 3 The user behavior flow chart shown can very intuitively reflect the traffic distribution of the screen position (including the cash register), which trajectories are more likely to form orders; which trajectories are more convenient for users to watch movies; and which trajectories are the main payment loss trajectories, etc., for the reference of operators, which can provide better operational reference value.

[0067] It should be noted that the user behavior flow chart is used to intuitively display the flow path and traffic distribution between pages at different levels.

[0068] In step S150, user behavior modeling is performed based on the user behavior flow chart, and user behavior is predicted to perform corresponding operations.

[0069] Optionally, based on the user behavior flow chart, user behavior modeling can be performed to obtain a user behavior model for predicting user behavior. The user behavior model may include a user behavior model for predicting the optimal user ordering flow, the optimal user viewing flow, etc. The optimal user ordering flow, the optimal user viewing flow, etc. are predicted to adjust the content recommendation strategy, optimize the page layout, and optimize the operation process. For example, if the user's viewing flow is mainly variety shows, the recommendation position of the variety show is placed in the most obvious position, and the channel of the variety show is adjusted to the first position, so that the user can intuitively click to watch and other operations.

[0070] In an embodiment of the present application, a user behavior analysis method based on a large-screen TV is provided, and the method is implemented, including: obtaining the click behavior data of the user during the viewing process, the click behavior data including the click position and the click time; encoding the click position to obtain the click position code; arranging the click position code based on the click time to obtain a user behavior session sequence; generating a user behavior dynamic line diagram based on the user behavior session sequence, the user behavior dynamic line diagram is used to display the flow path and traffic distribution between pages of each level; user behavior modeling is performed based on the user behavior dynamic line diagram, and user behavior is predicted to perform corresponding operations. In an embodiment of the present application, by collecting the click behavior data of the user during the viewing process, constructing a user behavior session sequence, and generating a user behavior dynamic line diagram, the user's behavior trajectory and traffic distribution on the large-screen TV can be fully and accurately displayed, providing operators with powerful operational decision support to improve user experience and business conversion rate.

[0071] In an embodiment of the present application, encoding the click position to obtain the click position code includes:

[0072] Based on the click position, determine the click area and the click page;

[0073] Calling a click position code mapping table corresponding to the click page;

[0074] The click position code corresponding to the click area is searched in the click position code mapping table.

[0075] Optionally, for different click pages, the recommended position settings are different, and the click position codes are also different. Therefore, when the user's click operation is collected, the current page can be detected, and the click position code mapping table corresponding to the current page can be determined, which can specifically include the click position and the code corresponding to the click position. Then, according to the user's click position, the click position code mapping table is queried to determine the click position code.

[0076] Furthermore, before calling the click position code mapping table corresponding to the click page, the method includes:

[0077] Partition each page display interface of the click screen to obtain multiple click areas;

[0078] Each click area is encoded to obtain all click position codes corresponding to each page, so as to generate the click position code mapping table.

[0079] Optionally, each display interface can be partitioned to obtain multiple click areas, each click area can correspond to a unique coding identifier, and the click position in the same click area can correspond to the same click position code. According to the divided click areas, a corresponding coding identifier can be configured for each click area and stored in association with the click area. It should be noted that all pixel coordinates in the click area can be recorded as the click position corresponding to the click area. When the user's click position corresponds to the click position, the code of the area can be used as the click position code.

[0080] In an embodiment of the present application, encoding the click position to obtain the click position code includes:

[0081] Determine whether the current clicked page is the target page;

[0082] If the currently clicked page is the target page, the target page is encoded.

[0083] Optionally, since the screen may include multiple levels of interfaces and some target pages, such as a cashier, a member interface, etc., in order to distinguish different interfaces, different codes may be configured for different interfaces, for example, the cashier may be represented by the letter C, the member interface may be represented by the letter V, the order success interface may be represented by the letter D, etc. After the click position and the target page are encoded, they may be sorted in order according to the click time to obtain multiple user session behaviors.

[0084] In an embodiment of the present application, the click position codes are arranged based on the click time to obtain a user behavior conversation sequence, including:

[0085] Determine whether there are multiple consecutive identical click position codes in the user behavior session sequence, or whether there are consecutive repeated click behavior tracks;

[0086] If so, retain a same click position code or a repeated click behavior track in the user behavior session sequence.

[0087] Optionally, because the user keeps pressing buttons to make selections, many levels appear in the user's movement trajectory, for example, the user repeatedly enters a page and then exits (including repeatedly entering the cashier counter and then exiting); the user enters the lower-level page from the homepage, uses the back key to return to the homepage, and then clicks the recommended position to enter the lower-level page. For these complex situations, the repeated click links or repeated click operations can be deleted. Exemplarily, the user behavior conversation sequence may be “C1-11|C2-32|C2-32|C2-32|C2-32|C Cashier”, where C2-32 appears three times in a row, and it may be adjusted to “C1-11|C2-32|C Cashier”; “C1-11|C2-32|C2-33|C Cashier|C2-32|C2-33|C Cashier|C2-34|C2-32|C Cashier|C2-32|C Cashier|D Order successful”, where |C2-32|C2-33|C Cashier| appears twice, and it may be adjusted to “C1-11|C2-32|C2-33|C Cashier|C2-34|C2-32|C Cashier|D Order successful”.

[0088] Furthermore, each user behavior session starts from the home page, that is, the user enters the lower-level page from the home page and uses the back key to return to the home page. The user clicks the home page mark again to enter the lower-level page, and this home page click behavior can be regarded as a new dynamic line session. For example, the code of the home page can be C1, then, if the code of the starting position in the user behavior session is not C1, it means that the session is incorrect and the user session sequence needs to be regenerated.

[0089] In an embodiment of the present application, after arranging the click position codes based on the click time to obtain the user behavior conversation sequence, the method includes:

[0090] Determine the page level corresponding to the user behavior session sequence;

[0091] When the page level is greater than a preset number of levels, and the total traffic of each page is less than a preset traffic threshold, the page level corresponding to the user behavior session sequence is set to the preset number of levels.

[0092] Optionally, for user behavior sessions with very long links, all user behavior sessions within the period can be counted. Based on the statistical results, if the page level of the session link is greater than N layers (such as 10 layers), and the total traffic proportion is less than M (such as 20%), then the page level of the traffic line session is N layers, such as 10 layers, and the user traffic from N layers downward, such as 11 layers, is classified into other tags.

[0093] In an embodiment of the present application, the user behavior modeling is performed based on the user behavior flow chart to predict the user behavior and perform the corresponding operation, including:

[0094] Conducting an in-depth analysis of the user behavior dynamic line diagram to identify the optimal ordering dynamic line, the optimal movie viewing dynamic line, and the order loss dynamic line;

[0095] Based on the optimal ordering route, the optimal movie-watching route, and the order-loss route, an ordering path report, a movie-watching path report, and an order-loss path report are generated respectively;

[0096] Based on the order loss flow, an order path report, a movie viewing path report and an order loss path report are respectively generated to adjust the content recommendation strategy, page layout and operation process.

[0097] Optionally, the user behavior flow chart can be used to intuitively display the flow paths and traffic distribution between pages at each level. By deeply analyzing the flow path and the traffic distribution and performing user behavior modeling, user behavior flows can be identified, such as the optimal ordering flow, the optimal movie viewing flow, and the order loss flow, and the corresponding ordering path report, movie viewing path report, and order loss path report can be generated. Subsequent operations can be implemented based on the ordering path report, movie viewing path report, and order loss path report, for example, content recommendation strategies can be adjusted, page layouts can be optimized, and operation processes can be optimized. For example, if the user's viewing preference is mainly movies, the content recommendations on the page are mainly the types of movies that the user likes, and the movies are adjusted to the maximum recommendation position for display. For users who order membership, if the order fails many times due to cumbersome procedures, the ordering process can be simplified.

[0098] It should be noted that, according to different ordered products, the optimal user ordering route report of the product can be separately counted. And according to different target contents, the optimal user viewing route report of the content can be separately counted.

[0099] In one embodiment of the present application, the user behavior dynamic line diagram is deeply analyzed to identify the optimal ordering dynamic line, the optimal movie watching dynamic line and the order loss dynamic line, including:

[0100] Counting the user behavior paths that generate orders in the user behavior path diagram to determine a plurality of optimal user ordering paths that generate a number of orders greater than a preset number;

[0101] The user behavior moving lines in the user behavior moving line diagram are sorted in descending order according to the movie watching time, so as to determine a plurality of optimal user movie watching moving lines whose movie watching time exceeds a preset time.

[0102] Statistics are collected on the user behavior flow charts in which unsuccessful orders are placed, so as to determine the order loss flow.

[0103] Optionally, statistics are collected for user behavior flow charts that generate orders. The user behavior flow charts that generate orders contain two consecutive links of "C cashier | D order successful". The user order flow is "Cx1 | Cx2 | Cx3 | ... | C cashier | D order successful". The optimal user order flow may be the N user order flows that generate the largest number of orders. The user order flows may be prioritized in descending order of the number of orders. A TopN optimal user order flow report is output based on the sorting results. The optimal user order flow report may include: order path, number of paths, and order quantity / amount.

[0104] The user behavior conversations in the user behavior flow chart are counted according to the viewing time, and the user conversation data of the links with a viewing time of more than M (such as 3600 seconds) are selected for statistical sorting. The TopN user viewing flow report can be output. The user and viewing flow report can include the viewing path, path number, and viewing time.

[0105] The user behavior sessions in the user behavior flow chart are counted according to the number of unsuccessful orders to obtain the order loss flow.

[0106] In the embodiment of the present application, large-screen operation data such as user accounts, program viewing records, and service ordering actions are collected by optimizing the data collection algorithm to achieve comprehensive capture and real-time recording of all user operation behaviors on the large-screen TV. Construct a user behavior conversation sequence to fully record the entire process from the user entering the large-screen interface to leaving, and explore and predict the deep-seated motivations and needs behind the user behavior. By associating the data and using a dynamic line diagram, it is possible to intuitively display the flow and transfer relationship of business traffic between the page layers of different large screens, display complex user processes and paths, and observe and analyze the large-screen content association and contribution between pages at all levels. By analyzing the flow and conversion of users between different pages or functions, deeply exploring the value behind user behavior data, and providing operators with personalized content recommendations and precision marketing strategies, the user experience can be optimized, and the conversion rate and user satisfaction can be improved.

[0107] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0108] In one embodiment, a user behavior analysis device based on a large-screen television is provided, and the user behavior analysis device based on a large-screen television corresponds one-to-one to the user behavior analysis method based on a large-screen television in the above embodiment. Figure 4 As shown, the user behavior analysis device based on a large-screen TV includes a click behavior data acquisition unit 10, a position encoding unit 20, a user behavior session sequence generation unit 30, a user behavior dynamic line diagram generation unit 40 and a user behavior analysis unit 50. Each functional module is described in detail as follows:

[0109] A click behavior data acquisition unit 10, used to acquire the click behavior data of the user during the viewing process, wherein the click behavior data includes the click position and the click time;

[0110] A position encoding unit 20, used to encode the click position to obtain a click position code;

[0111] A user behavior conversation sequence generating unit 30, configured to arrange the click position codes based on the click time to obtain a user behavior conversation sequence;

[0112] A user behavior flow chart generating unit 40 is used to generate a user behavior flow chart based on the user behavior session sequence, wherein the user behavior flow chart is used to display the flow path and traffic distribution between pages of each level;

[0113] The user behavior analysis unit 50 is used to perform user behavior modeling based on the user behavior flow chart, predict user behavior, and perform corresponding operations.

[0114] In an embodiment of the present application, the device further includes: a page encoding unit, configured to:

[0115] Determine whether the current clicked page is the target page;

[0116] If the currently clicked page is a target page, the target page is page-coded.

[0117] In one embodiment of the present application, the device further includes: a user behavior session sequence adjustment unit, configured to:

[0118] Determine whether there are multiple consecutive identical click position codes in the user behavior session sequence, or whether there are consecutive repeated click behavior tracks;

[0119] If so, retain a same click position code or a repeated click behavior track in the user behavior session sequence.

[0120] In one embodiment of the present application, the device further includes: a user behavior session sequence adjustment unit, configured to:

[0121] Determine the page level corresponding to the user behavior session sequence;

[0122] When the page level is greater than a preset number of levels, and the total traffic of each page is less than a preset traffic threshold, the page level corresponding to the user behavior session sequence is set to the preset number of levels.

[0123] In one embodiment of the present application, the user behavior analysis unit 50 is further used to:

[0124] Conducting an in-depth analysis of the user behavior dynamic line diagram to identify the optimal ordering dynamic line, the optimal movie viewing dynamic line, and the order loss dynamic line;

[0125] Based on the optimal ordering route, the optimal movie-watching route, and the order-loss route, an ordering path report, a movie-watching path report, and an order-loss path report are generated respectively;

[0126] Based on the order loss flow, an order path report, a movie viewing path report and an order loss path report are respectively generated to adjust the content recommendation strategy, page layout and operation process.

[0127] In one embodiment of the present application, the user behavior analysis unit 50 is further used to:

[0128] Counting the user behavior paths that generate orders in the user behavior path diagram to determine a plurality of optimal user ordering paths that generate a number of orders greater than a preset number;

[0129] The user behavior moving lines in the user behavior moving line diagram are sorted in descending order according to the movie watching time, so as to determine a plurality of optimal user movie watching moving lines whose movie watching time exceeds a preset time.

[0130] Statistics are collected on the user behavior flow charts in which unsuccessful orders are placed, so as to determine the order loss flow.

[0131] In one embodiment of the present application, the position encoding unit 20 is further used for:

[0132] Based on the click position, determine the click area and the click page;

[0133] Calling a click position code mapping table corresponding to the click page;

[0134] The click position code corresponding to the click area is searched in the click position code mapping table.

[0135] In the embodiment of the present application, large-screen operation data such as user accounts, program viewing records, and service ordering actions are collected by optimizing the data collection algorithm to achieve comprehensive capture and real-time recording of all user operation behaviors on the large-screen TV. Construct a user behavior conversation sequence to fully record the entire process from the user entering the large-screen interface to leaving, and explore and predict the deep-seated motivations and needs behind the user behavior. By associating the data and using a dynamic line diagram, it is possible to intuitively display the flow and transfer relationship of business traffic between the page layers of different large screens, display complex user processes and paths, and observe and analyze the large-screen content association and contribution between pages at all levels. By analyzing the flow and conversion of users between different pages or functions, deeply exploring the value behind user behavior data, and providing operators with personalized content recommendations and precision marketing strategies, the user experience can be optimized, and the conversion rate and user satisfaction can be improved.

[0136] For the specific definition of the user behavior analysis device based on a large-screen TV, please refer to the definition of the user behavior analysis method based on a large-screen TV above, which will not be repeated here. Each module in the above-mentioned user behavior analysis device based on a large-screen TV can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0137] In one embodiment, a computer device is provided. The computer device may be a terminal device, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium. The readable storage medium stores computer-readable instructions. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer-readable instructions are executed by the processor, a user behavior analysis method based on a large-screen TV is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0138] In an embodiment of the present application, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the steps of the user behavior analysis method based on a large-screen TV as described above are implemented.

[0139] In an embodiment of the application, a readable storage medium is provided, wherein the readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the user behavior analysis method based on a large-screen TV as described above are implemented.

[0140] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they may include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0141] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0142] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A user behavior analysis method based on a large-screen TV, characterized in that: The method comprises: Acquire the user's click behavior data during the viewing process, wherein the click behavior data includes the click position and the click time; Encoding the click position to obtain a click position code; Arranging the click position codes based on the click time to obtain a user behavior session sequence; Based on the user behavior session sequence, a user behavior flow chart is generated, wherein the user behavior flow chart is used to display the flow path and traffic distribution between pages at each level; Performing in-depth analysis on the flow path and the traffic distribution to identify the optimal ordering route, the optimal movie-watching route, and the order loss route; Based on the optimal ordering route, the optimal movie-watching route, and the order-loss route, an ordering path report, a movie-watching path report, and an order-loss path report are generated respectively; Adjust the content recommendation strategy, page layout and operation process based on the ordering path report, movie viewing path report and order churn path report.

2. The method for analyzing user behavior based on a large-screen TV according to claim 1, characterized in that: After obtaining the click behavior data of the user during the viewing process, the method includes: Determine whether the current clicked page is the target page; If the currently clicked page is a target page, the target page is page-coded.

3. The method for analyzing user behavior based on a large-screen TV according to claim 1, characterized in that: After arranging the click position codes based on the click time to obtain the user behavior conversation sequence, the method includes: Determine whether there are multiple consecutive identical click position codes in the user behavior session sequence, or whether there are consecutive repeated click behavior tracks; If so, retain a same click position code or a repeated click behavior track in the user behavior session sequence.

4. The method for analyzing user behavior based on a large-screen TV according to claim 1, characterized in that: After arranging the click position codes based on the click time to obtain the user behavior conversation sequence, the method includes: Determine the page level corresponding to the user behavior session sequence; When the page level is greater than a preset number of levels, and the total traffic of each page is less than a preset traffic threshold, the page level corresponding to the user behavior session sequence is set to the preset number of levels.

5. The method for analyzing user behavior based on a large-screen TV according to claim 4, characterized in that: Performing an in-depth analysis on the user behavior dynamic line diagram to identify the optimal ordering dynamic line, the optimal movie viewing dynamic line, and the order loss dynamic line, including: Counting the user behavior paths that generate orders in the user behavior path diagram to determine a plurality of optimal user ordering paths that generate a number of orders greater than a preset number; Sorting the user behavior moving lines in the user behavior moving line diagram in descending order according to the movie watching time, so as to determine a plurality of optimal user movie watching moving lines whose movie watching time exceeds a preset time; Statistics are collected on the user behavior flow charts in which unsuccessful orders are placed, so as to determine the order loss flow.

6. The method for analyzing user behavior based on a large-screen TV according to claim 1, characterized in that: The step of encoding the click position to obtain the click position code includes: Based on the click position, determine the click area and the click page; Calling a click position code mapping table corresponding to the click page; The click position code corresponding to the click area is searched in the click position code mapping table.

7. A user behavior analysis device based on a large-screen TV, characterized in that: The device comprises: A click behavior data acquisition unit, used to acquire the click behavior data of the user during the viewing process, wherein the click behavior data includes the click position and the click time; A position encoding unit, used for encoding the click position to obtain a click position code; A user behavior conversation sequence generating unit, configured to arrange the click position codes based on the click time to obtain a user behavior conversation sequence; A user behavior flow chart generating unit, used to generate a user behavior flow chart based on the user behavior session sequence, wherein the user behavior flow chart is used to display the flow path and traffic distribution between pages of each level; User behavior analysis unit, used to: Performing in-depth analysis on the flow path and the traffic distribution to identify the optimal ordering route, the optimal movie-watching route, and the order loss route; Based on the optimal ordering route, the optimal movie-watching route, and the order-loss route, an ordering path report, a movie-watching path report, and an order-loss path report are generated respectively; Adjust the content recommendation strategy, page layout and operation process based on the ordering path report, movie viewing path report and order churn path report.

8. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executed on the processor, characterized in that: When the processor executes the computer-readable instructions, it implements the user behavior analysis method based on a large-screen TV as described in any one of claims 1 to 6.

9. A readable storage medium having computer-readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by the processor, the user behavior analysis method based on a large-screen TV as described in any one of claims 1 to 6 is implemented.

Images