Set-top box startup screen control method and device, electronic device and storage medium

Abstract

The set-top box boot screen control method and device, electronic device and storage medium provided in the present application relate to the technical field of set-top box boot screen control. In the present application, first, when there are multiple boot screen storage partitions in the flash memory area of ​​the target set-top box, data collection is performed on the historical operation process to obtain historical set-top box operation data; secondly, based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data, a boot screen file matching each target time interval in multiple target time intervals is determined from multiple boot screen files; then, based on the boot screen file matching each target time interval, a corresponding boot screen loading plan is generated, and the boot screen loading plan is sent to the target set-top box. Based on the above content, the problem of poor reliability of set-top box boot screen control existing in the prior art can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of set-top box startup screen control, and in particular to a set-top box startup screen control method and device, electronic equipment and storage medium. Background Art

[0002] For set-top boxes, the functions of the boot logo (boot screen) include: Brand identification: by displaying the operator or brand logo, it helps users identify the brand and service provider of the device; User experience: when the device starts, the boot logo can provide users with visual feedback to let them know that the device is starting normally; Information transmission: in some cases, the boot logo may also contain some prompt information, such as loading or updating status. In other words, different users or users at different times may have different needs, and therefore, different boot logos have different adaptability. However, in the prior art, the boot logo is generally fixed, so it is difficult to effectively meet the actual needs of users, that is, there is a problem of poor reliability in the management and control of the boot logo. Summary of the invention

[0003] In view of this, the purpose of the present application is to provide a set-top box startup screen control method and device, electronic device and storage medium, so as to improve the problem of poor reliability of set-top box startup screen control existing in the prior art.

[0004] To achieve the above objectives, this application adopts the following technical solutions:

[0005] A method for controlling a startup screen of a set-top box, comprising:

[0006] When there are multiple boot screen storage partitions in the flash memory area of ​​the target set-top box, data collection is performed on the historical operation process of the target set-top box to obtain historical set-top box operation data corresponding to the target set-top box, wherein the multiple boot screen storage partitions are used to store multiple boot screen files, the target set-top box is used to load at least one boot screen file during the boot process to form a corresponding boot screen, and the historical set-top box operation data at least includes historical set-top box operation time and historical set-top box operation content corresponding to the historical set-top box operation time;

[0007] Based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data, determining a startup screen file matching each target time interval in a plurality of target time intervals from the plurality of startup screen files, wherein the plurality of target time intervals are formed by dividing a time period;

[0008] Based on the boot screen files that match each target time interval, a corresponding boot screen loading plan is generated, and the boot screen loading plan is sent to the target set-top box, wherein the target set-top box is used to determine the partition identifier of the boot screen storage partition where the boot screen file corresponding to the current time is located through the boot screen loading plan during the boot process, and load the corresponding boot screen file from the corresponding boot screen storage partition based on the partition identifier.

[0009] In a preferred embodiment of the present application, in the above-mentioned set-top box startup screen control method, the step of determining a startup screen file matching each target time interval in a plurality of target time intervals from the plurality of startup screen files based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data includes:

[0010] Splitting and combining the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data to form a plurality of corresponding historical set-top box operation content sequences, wherein the plurality of historical set-top box operation content sequences correspond to a plurality of target time intervals one by one, each of the historical set-top box operation content sequences includes a plurality of historical set-top box operation contents whose corresponding historical set-top box operation time belongs to the corresponding target time interval, and the plurality of historical set-top box operation contents are sorted based on the chronological relationship between the corresponding historical set-top box operation times;

[0011] Using the first feature mining model included in the target boot screen matching network, feature mining is performed on each of the historical set-top box running content sequences, and the running content semantic vector of the target time interval corresponding to each of the historical set-top box running content sequences is output;

[0012] Using the second feature mining model included in the target boot screen matching network, feature mining is performed on each of the boot screen files, and a boot screen semantic vector corresponding to each of the boot screen files is output;

[0013] By utilizing the screen matching model included in the target boot screen matching network, based on the running content semantic vector of each target time interval and the boot screen semantic vector corresponding to each boot screen file, the boot screen file matching each target time interval is determined.

[0014] In a preferred embodiment of the present application, in the above-mentioned set-top box startup screen control method, the step of using the first feature mining model included in the target startup screen matching network to perform feature mining on each of the historical set-top box running content sequences, and outputting the running content semantic vector of the target time interval corresponding to each of the historical set-top box running content sequences, includes:

[0015] For any of the historical set-top box running content sequences, using the embedding unit in the first feature mining model included in the target boot screen matching network, each historical set-top box running content in the historical set-top box running content sequence is embedded to form a corresponding running content embedding vector sequence, and the historical set-top box running time corresponding to each historical set-top box running content is embedded to form a corresponding running time embedding vector sequence;

[0016] Using the feature sequence alignment unit in the first feature mining model, the running content embedding vector sequence and the running time embedding vector sequence are subjected to feature alignment processing, and a corresponding alignment vector sequence is output, wherein each alignment vector in the alignment vector sequence is formed by concatenating the corresponding running content embedding vector and the running time embedding vector;

[0017] The semantic transfer unit in the first feature mining model is used to perform semantic transfer processing on the alignment vector sequence, and an operation content semantic vector of the target time interval corresponding to the historical set-top box operation content sequence is output, wherein the operation content semantic vector carries the semantic information of each alignment vector in the alignment vector sequence.

[0018] In a preferred embodiment of the present application, in the above-mentioned set-top box startup screen control method, the step of using the semantic transfer unit in the first feature mining model to perform semantic transfer processing on the alignment vector sequence and outputting the operation content semantic vector of the target time interval corresponding to the historical set-top box operation content sequence includes:

[0019] For each alignment vector in the alignment vector sequence, determine whether the alignment vector has an associated alignment vector in the target vector map, and if the associated alignment vector is present, extract an alignment vector sequence fragment including at least the associated alignment vector from the alignment vector sequence where the associated alignment vector is located, wherein the target vector map includes each alignment vector in each alignment vector sequence, and two historical set-top box operation contents corresponding to two alignment vectors having an associated relationship are the same;

[0020] The semantic transfer unit in the first feature mining model is used in combination with the corresponding alignment vector sequence fragment to perform semantic transfer processing on the alignment vector sequence, and the operation content semantic vector of the target time interval corresponding to the historical set-top box operation content sequence is output.

[0021] In a preferred embodiment of the present application, in the above-mentioned set-top box startup screen control method, the step of using the semantic transfer unit in the first feature mining model, combining the corresponding alignment vector sequence fragment, performing semantic transfer processing on the alignment vector sequence, and outputting the operation content semantic vector of the target time interval corresponding to the historical set-top box operation content sequence, includes:

[0022] For each alignment vector in the alignment vector sequence, the semantic information represented by the forward alignment vector of the alignment vector is fused into the alignment vector to obtain a local vector of running content corresponding to the alignment vector, and when the alignment vector has an associated alignment vector, the semantic information represented by the alignment vector sequence fragment corresponding to the alignment vector is fused into the local vector of the running content to obtain a corresponding running content associated vector, and when the alignment vector does not have an associated object vector, the local vector of the running content is used as the corresponding running content associated vector, wherein the forward alignment vector of the first alignment vector is a reference vector carried by the semantic transfer unit in the first feature mining model, and the forward alignment vectors of other alignment vectors are running content associated vectors corresponding to the previous alignment vector;

[0023] After obtaining the running content association vector corresponding to the last alignment vector, the running content association vector corresponding to the last alignment vector is used as the running content semantic vector of the target time interval corresponding to the historical set-top box running content sequence.

[0024] In a preferred embodiment of the present application, in the above-mentioned set-top box startup screen control method, the step of using the second feature mining model included in the target startup screen matching network to perform feature mining on each of the startup screen files, and outputting the startup screen semantic vector corresponding to each of the startup screen files, includes:

[0025] For any of the boot screen files, using the convolution unit in the second feature mining model included in the target boot screen matching network, convolution processing is performed on each boot screen frame in the boot screen file to form a corresponding boot screen convolution vector sequence;

[0026] In the vector transfer unit included in the second feature mining model, for each boot screen convolution vector in the boot screen convolution vector sequence, the semantic information represented by the forward convolution vector of the boot screen convolution vector is fused into the boot screen convolution vector to obtain a corresponding boot screen fusion vector, wherein the forward convolution vector of the first boot screen convolution vector is a reference vector carried by the vector transfer unit, and the forward convolution vectors of other boot screen convolution vectors are boot screen fusion vectors corresponding to the previous boot screen convolution vector;

[0027] After obtaining the boot screen fusion vector corresponding to the last boot screen convolution vector, the boot screen fusion vector corresponding to the last boot screen convolution vector is used as the boot screen semantic vector corresponding to the boot screen file.

[0028] In a preferred embodiment of the present application, in the above-mentioned set-top box startup screen control method, the set-top box startup screen control method further includes:

[0029] Splitting and combining the sample set-top box operation time and the corresponding sample set-top box operation content included in the sample set-top box operation data to form a plurality of corresponding sample set-top box operation content sequences, wherein the plurality of sample set-top box operation content sequences correspond to the plurality of sample time intervals one by one, each of the sample set-top box operation content sequences includes a plurality of sample set-top box operation contents whose corresponding sample set-top box operation time belongs to the corresponding sample time interval, and the plurality of sample set-top box operation contents are sorted based on the chronological relationship between the corresponding sample set-top box operation times;

[0030] Using the first feature mining model included in the candidate boot screen matching network, feature mining is performed on each of the sample set-top box running content sequences, and a sample content semantic vector corresponding to a sample time interval of each of the sample set-top box running content sequences is output;

[0031] Using the second feature mining model included in the candidate startup screen matching network, feature mining is performed on each of the sample startup screen files, and a sample screen semantic vector corresponding to each of the sample startup screen files is output;

[0032] Using the picture matching model included in the candidate startup picture matching network, based on the sample content semantic vector of each sample time interval and the sample picture semantic vector corresponding to each sample startup picture file, determine the sample startup picture file that matches each sample time interval;

[0033] Based on the sample boot screen files matched by each of the sample time intervals and the corresponding boot screen file labels, a network error of the candidate boot screen matching network is calculated, and the network parameters of the candidate boot screen matching network are updated in a direction of reducing the network error to form a corresponding target boot screen matching network, wherein the target boot screen matching network is used to execute the step of determining, from the multiple boot screen files, a boot screen file matching each target time interval in a plurality of target time intervals based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data.

[0034] The present application also provides a set-top box startup screen control device, comprising:

[0035] An operation data collection module is used to collect data on the historical operation process of the target set-top box when there are multiple startup screen storage partitions in the flash memory area of ​​the target set-top box, so as to obtain historical set-top box operation data corresponding to the target set-top box, wherein the multiple startup screen storage partitions are used to store multiple startup screen files, the target set-top box is used to load at least one startup screen file during the startup process to form a corresponding startup screen, and the historical set-top box operation data at least includes a historical set-top box operation time and a historical set-top box operation content corresponding to the historical set-top box operation time;

[0036] a boot screen matching module, configured to determine, from the plurality of boot screen files, a boot screen file that matches each of a plurality of target time intervals based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data, wherein the plurality of target time intervals are formed by dividing a time period;

[0037] A screen loading scheme sending module is used to generate a corresponding boot screen loading scheme based on the boot screen file matching each target time interval, and send the boot screen loading scheme to the target set-top box, wherein the target set-top box is used to determine the partition identifier of the boot screen storage partition where the boot screen file corresponding to the current time is located through the boot screen loading scheme during the boot process, and load the corresponding boot screen file from the corresponding boot screen storage partition based on the partition identifier.

[0038] Based on the above, the present application also provides an electronic device, including:

[0039] Memory for storing computer programs;

[0040] The processor connected to the memory is used to execute the computer program stored in the memory to implement the above-mentioned set-top box startup screen control method.

[0041] On the basis of the above, the present application also provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is run, each step of the above-mentioned set-top box startup screen control method is executed.

[0042] The set-top box boot screen control method and device, electronic device and storage medium provided by the present application, first, when there are multiple boot screen storage partitions in the flash memory area of ​​the target set-top box, data is collected for the historical operation process to obtain the historical set-top box operation data; secondly, based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data, the boot screen file matching each target time interval in the multiple target time intervals is determined from the multiple boot screen files; then, based on the boot screen file matching each target time interval, a corresponding boot screen loading scheme is generated, and the boot screen loading scheme is sent to the target set-top box. Based on the above content, due to different times, it may represent different user needs, or it may represent different users of the set-top box, and there may also be different needs. Therefore, the boot screen files of each time can be analyzed based on the historical collection of operation data, so that the set-top box can load the corresponding boot screen file at the corresponding time, thereby realizing the reliability of the set-top box boot screen control, and then improving the problem of poor reliability of the set-top box boot screen control existing in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings.

[0044] Figure 1 A structural block diagram of an electronic device provided in an embodiment of the present application.

[0045] Figure 2 A flowchart of a set-top box startup screen control method provided in an embodiment of the present application.

[0046] Figure 3 A schematic diagram of the semantic transfer processing provided in an embodiment of the present application.

[0047] Figure 4 A block diagram of a set-top box startup screen control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0049] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0050] like Figure 1 As shown, an embodiment of the present application provides an electronic device, wherein the electronic device may include a memory, a processor, and a set-top box startup screen control device.

[0051] In detail, the memory and the processor are electrically connected directly or indirectly to achieve data transmission or interaction. For example, the memory and the processor can be electrically connected through one or more communication buses or signal lines. The set-top box startup screen control device includes at least one software function module stored in the memory in the form of software or firmware. The processor is used to execute an executable computer program stored in the memory, for example, the software function module and computer program included in the set-top box startup screen control device, so as to implement the set-top box startup screen control method provided in the embodiment of the present application.

[0052] Optionally, the memory may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc.

[0053] Furthermore, the processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a system on chip (SoC), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0054] Understandably, Figure 1The structure shown is for illustration only, and the electronic device may also include Figure 1 More or fewer components as shown, or with Figure 1 The different configurations shown, for example, may also include a communication unit for exchanging information with other devices (such as a set-top box, etc.).

[0055] Combination Figure 2 The embodiment of the present application also provides a set-top box startup screen control method applicable to the above electronic device. Among them, the method steps defined in the process related to the set-top box startup screen control method can be implemented by the electronic device.

[0056] The following will Figure 2 The specific process shown is explained in detail.

[0057] Step S110, when there are multiple boot screen storage partitions in the flash memory area of ​​the target set-top box, data collection is performed on the historical operation process of the target set-top box to obtain historical set-top box operation data corresponding to the target set-top box.

[0058] In an embodiment of the present application, when there are multiple boot screen storage partitions (such as boot screen storage partition 1 and boot screen storage partition 2) in the flash memory area (flash) of the target set-top box, the electronic device can collect data on the historical operation process of the target set-top box to obtain the historical set-top box operation data corresponding to the target set-top box. The multiple boot screen storage partitions are used to store multiple boot screen files (such as boot screen storage partition 1 stores boot screen file 1, and boot screen storage partition 2 stores boot screen file 2), and the target set-top box is used to load at least one boot screen file during the boot process to form a corresponding boot screen, and the historical set-top box operation data at least includes the historical set-top box operation time and the historical set-top box operation content corresponding to the historical set-top box operation time, such as playing program 1 at 2024-10-24-10:10:20.

[0059] Step S120, based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data, determine a startup screen file matching each target time interval in the multiple target time intervals from the multiple startup screen files.

[0060] In an embodiment of the present application, the electronic device can determine, from the multiple startup screen files, a startup screen file that matches each target time interval in a plurality of target time intervals based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data. Wherein, the multiple target time intervals are formed by segmenting a time period. For example, when the time period is one day, the multiple target time intervals can be in hours, and when the time period is one week, the multiple target time intervals can be in days.

[0061] Step S130, generating a corresponding startup screen loading plan based on each startup screen file matching the target time interval, and sending the startup screen loading plan to the target set-top box.

[0062] In the embodiment of the present application, the electronic device can generate a corresponding boot screen loading scheme based on the boot screen file matching each target time interval, and send the boot screen loading scheme to the target set-top box. The target set-top box is used to determine the partition identifier of the boot screen storage partition where the boot screen file corresponding to the current time is located (such as the identifier of boot screen storage partition 1) through the boot screen loading scheme during the boot process, and load the corresponding boot screen file from the corresponding boot screen storage partition based on the partition identifier.

[0063] Based on the above content, since different times may represent different user needs, or different users of set-top boxes may also have different needs, the boot screen files at each time can be analyzed based on the historical collection and operation data, so that the set-top box can load the corresponding boot screen file at the corresponding time, thereby achieving the reliability of the set-top box startup screen control, and then improving the problem of poor reliability of the set-top box startup screen control in the prior art.

[0064] It should be noted that for step S120, the specific method of determining the startup screen file matching each target time interval in the multiple target time intervals from the multiple startup screen files is not limited and can be selected according to actual needs.

[0065] For example, in an alternative implementation, in order to improve the reliability of the determined matching boot screen file so that it is more in line with the user's actual boot requirements, the above-mentioned step S120 may further include step S121, step S122, step S123 and step S124, and the specific content of each step is described as follows.

[0066] Step S121, splitting and combining the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data to form a corresponding plurality of historical set-top box operation content sequences.

[0067] In an embodiment of the present application, the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data can be split and combined to form a plurality of corresponding historical set-top box operation content sequences. Wherein, the plurality of historical set-top box operation content sequences correspond to a plurality of target time intervals one by one, and each of the historical set-top box operation content sequences includes a plurality of historical set-top box operation contents whose corresponding historical set-top box operation time belongs to the corresponding target time interval, and the plurality of historical set-top box operation contents are sorted based on the sequential relationship between the corresponding historical set-top box operation times. For example, there are target time interval 1 "00:00:00-08:00:00", target time interval 2 "08:00:00-12:00:00", target time interval 3 "12:00:00-18:00:00", target time interval 4 "18:00:00-22:00:00", and target time interval 5 "22:00:00-24:00:00". Thus, for the target time interval 1 "00:00:00-08:00:00", the corresponding historical set-top box running content sequence may be "playing program 1 at 2024-10-21-06:10:20, playing program 2 at 2024-10-22-07:11:25, playing program 1 at 2024-10-22-03:12:28". In order to have a higher correlation with the boot screen, the historical set-top box running time may refer to the time of the first program watched after booting.

[0068] Step S122, using the first feature mining model included in the target boot screen matching network, feature mining is performed on each of the historical set-top box running content sequences, and the running content semantic vector corresponding to the target time interval of each of the historical set-top box running content sequences is output.

[0069] In the embodiment of the present application, the first feature mining model included in the target boot screen matching network can be used to perform feature mining on each of the historical set-top box running content sequences, and output the running content semantic vector of the target time interval corresponding to each of the historical set-top box running content sequences. Wherein, the target boot screen matching network is a neural network, which can be trained to form by corresponding sample data, and the specific training process is described below.

[0070] Step S123, using the second feature mining model included in the target boot screen matching network, perform feature mining on each of the boot screen files respectively, and output a boot screen semantic vector corresponding to each of the boot screen files.

[0071] In an embodiment of the present application, the second feature mining model included in the target boot screen matching network can be used to perform feature mining on each of the boot screen files, and output a boot screen semantic vector corresponding to each of the boot screen files.

[0072] Step S124, using the screen matching model included in the target boot screen matching network, based on the running content semantic vector of each target time interval and the boot screen semantic vector corresponding to each boot screen file, determine the boot screen file that matches each target time interval.

[0073] In an embodiment of the present application, the screen matching model included in the target boot screen matching network can be used to determine the boot screen file that matches each target time interval based on the running content semantic vector of each target time interval and the boot screen semantic vector corresponding to each boot screen file. Exemplarily, for each target time interval, the similarity between the running content semantic vector of the target time interval and each boot screen semantic vector can be calculated, such as cosine similarity, and then the boot screen file corresponding to the boot screen semantic vector with the maximum similarity is used as the boot screen file that matches the target time interval.

[0074] It can be understood that, in the above-mentioned step S122, the specific method of performing feature mining on each of the historical set-top box running content sequences is not limited and can be selected according to actual needs. For example, in an alternative implementation, in order to ensure that the semantic representation of the mined running content semantic vector has a high accuracy, the above-mentioned step S122 can further include step S122a, step S122b and step S122c, and the specific content of each step is described as follows.

[0075] Step S122a, for any one of the historical set-top box operation content sequences, use the embedding unit in the first feature mining model included in the target boot screen matching network to embed each historical set-top box operation content in the historical set-top box operation content sequence to form a corresponding operation content embedding vector sequence, and embed the historical set-top box operation time corresponding to each historical set-top box operation content to form a corresponding operation time embedding vector sequence.

[0076] In an embodiment of the present application, for any one of the historical set-top box operation content sequences, the embedding unit (word embedding model, such as Word2Vec) in the first feature mining model included in the target boot screen matching network can be used to embed each historical set-top box operation content in the historical set-top box operation content sequence to form a corresponding operation content embedding vector sequence, and the historical set-top box operation time corresponding to each historical set-top box operation content can be embedded to form a corresponding operation time embedding vector sequence.

[0077] Step S122b, utilizing the feature sequence alignment unit in the first feature mining model to perform feature alignment processing on the running content embedding vector sequence and the running time embedding vector sequence, and outputting a corresponding alignment vector sequence.

[0078] In an embodiment of the present application, after obtaining the running content embedding vector sequence and the running time embedding vector sequence, the feature sequence alignment unit in the first feature mining model can be used to perform feature alignment processing on the running content embedding vector sequence and the running time embedding vector sequence, and output a corresponding alignment vector sequence. Each alignment vector in the alignment vector sequence is formed based on splicing the corresponding running content embedding vector and the running time embedding vector, so that the running time is integrated into the running content to improve the accuracy of semantic representation.

[0079] Step S122c, using the semantic transfer unit in the first feature mining model, performs semantic transfer processing on the alignment vector sequence, and outputs the operation content semantic vector of the target time interval corresponding to the historical set-top box operation content sequence.

[0080] In the embodiment of the present application, after obtaining the alignment vector sequence, the semantic transfer unit in the first feature mining model can be used to perform semantic transfer processing on the alignment vector sequence, and output the operation content semantic vector of the target time interval corresponding to the historical set-top box operation content sequence. The operation content semantic vector carries the semantic information of each alignment vector in the alignment vector sequence.

[0081] It is understandable that, in the above step S122c, the specific manner of semantic transfer processing of the alignment vector sequence is not limited and can be selected according to actual needs. For example, in an alternative implementation, in order to ensure the reliability of semantic transfer processing and to make the semantics of the output running content semantic vector richer, the above step S122c can further include step c1 and step c2, and the specific content of each step is described as follows.

[0082] Step c1, for each alignment vector in the alignment vector sequence, determine whether the alignment vector has an associated alignment vector in the target vector map, and if so, extract an alignment vector sequence fragment including at least the associated alignment vector from the alignment vector sequence where the associated alignment vector is located.

[0083] In an embodiment of the present application, for each alignment vector in the alignment vector sequence, it can be determined whether the alignment vector has an associated alignment vector (i.e., an alignment vector with an associated relationship) in the target vector map, and when there is an associated alignment vector, an alignment vector sequence fragment including at least the associated alignment vector can be cut out from the alignment vector sequence where the associated alignment vector is located. For example, the associated alignment vector can be taken as the center and the specified distance (such as one alignment vector or two alignment vectors) can be extended forward and backward in the corresponding alignment vector sequence for cutting out. The target vector map includes each alignment vector in each alignment vector sequence, and the two historical set-top box operation contents corresponding to the two alignment vectors with an associated relationship are the same.

[0084] Step c2, using the semantic transfer unit in the first feature mining model, combined with the corresponding alignment vector sequence fragment, performs semantic transfer processing on the alignment vector sequence, and outputs the operation content semantic vector of the target time interval corresponding to the historical set-top box operation content sequence.

[0085] In the embodiment of the present application, the semantic transfer unit in the first feature mining model is used to combine the corresponding alignment vector sequence fragments to perform semantic transfer processing on the alignment vector sequence, and output the operation content semantic vector of the target time interval corresponding to the historical set-top box operation content sequence. Based on this, the semantic information of the associated alignment vector can be integrated in the process of semantic transfer processing, so that the semantics of the output operation content semantic vector is richer.

[0086] It is understandable that in the above step c2, the specific manner of performing semantic transfer processing on the alignment vector sequence in combination with the corresponding alignment vector sequence fragment is not limited and can be selected according to actual needs. For example, in an alternative implementation, in order to fully integrate the alignment vector sequence fragment in the process of semantic transfer processing, Figure 3 , the above step c2 may further include the following contents:

[0087] First, for each alignment vector in the alignment vector sequence, the semantic information represented by the forward alignment vector of the alignment vector is fused into the alignment vector to obtain the local vector of the running content corresponding to the alignment vector (exemplarily, the forward alignment vector can be multiplied by the transposed vector of the alignment vector to obtain the corresponding similarity parameter, and then the similarity parameter is used as the weight to weight the alignment vector to obtain the corresponding local vector of the running content), and when the alignment vector has an associated alignment vector, the semantic information represented by the alignment vector sequence fragment corresponding to the alignment vector is fused into the local vector of the running content to obtain the corresponding running content associated vector (exemplarily, each alignment vector in the alignment vector sequence fragment can be averaged to obtain the associated vector The corresponding mean vector, then the mean vector can be multiplied by the transposed vector of the local vector of the running content to obtain the corresponding similarity parameter, then the similarity parameter is used as a weight to weight the local vector of the running content to obtain the corresponding running content association vector), and, when the alignment vector does not have an associated object vector, the local vector of the running content is used as the corresponding running content association vector, wherein the forward alignment vector of the first alignment vector is a reference vector carried by the semantic transfer unit in the first feature mining model (that is, as a network parameter of the semantic transfer unit, formed during the training process, and can be a random vector in the initial stage of training), and the forward alignment vectors of other alignment vectors are the running content association vectors corresponding to the previous alignment vector;

[0088] Secondly, after obtaining the running content association vector corresponding to the last alignment vector, the running content association vector corresponding to the last alignment vector is used as the running content semantic vector of the target time interval corresponding to the historical set-top box running content sequence; or, the running content association vector corresponding to the last alignment vector and each alignment vector in the alignment vector sequence can be averaged to obtain the running content semantic vector. In this way, the problem of semantic distortion caused by excessive sequence depth during the transmission process can be reduced to a certain extent.

[0089] It can be understood that, in the above step S123, the specific method of performing feature mining on each of the boot screen files is not limited and can be selected according to actual needs. For example, in an alternative implementation, in order to ensure the reliability of the mined boot screen semantic vector, the above step S123 can further include the following contents:

[0090] First, for any one of the boot screen files, using the convolution unit in the second feature mining model included in the target boot screen matching network, convolution processing is performed on each boot screen frame in the boot screen file to form a corresponding boot screen convolution vector sequence, wherein the order relationship between the boot screen convolution vectors in the boot screen convolution vector sequence can be determined based on the order relationship of the corresponding boot screens in the boot screen file;

[0091] Secondly, in the vector transfer unit included in the second feature mining model, for each boot screen convolution vector in the boot screen convolution vector sequence, the semantic information represented by the forward convolution vector of the boot screen convolution vector is fused into the boot screen convolution vector (the fusion method is as described above), and the corresponding boot screen fusion vector is obtained, wherein the forward convolution vector of the first boot screen convolution vector is a reference vector carried by the vector transfer unit (the reference vector can be formed as a network parameter of the vector transfer unit during the training process, and in the initial stage of training, the reference vector can be a randomly generated vector), and the forward convolution vectors of other boot screen convolution vectors are boot screen fusion vectors corresponding to the previous boot screen convolution vector;

[0092] Then, after obtaining the boot screen fusion vector corresponding to the last boot screen convolution vector, the boot screen fusion vector corresponding to the last boot screen convolution vector is used as the boot screen semantic vector corresponding to the boot screen file; or, the boot screen fusion vector corresponding to the last boot screen convolution vector and each boot screen convolution vector in the boot screen convolution vector sequence can be averaged to obtain the boot screen semantic vector. In this way, the problem of semantic distortion caused by excessive sequence depth during the transmission process can be reduced to a certain extent.

[0093] On the basis of the above embodiment, in order to ensure that the above step S120 can be reliably executed, a corresponding neural network can also be pre-trained for matching. That is to say, in an alternative implementation, the set-top box startup screen control method can also include the following steps:

[0094] First, the sample set-top box operation time and the corresponding sample set-top box operation content included in the sample set-top box operation data are split and combined to form a plurality of corresponding sample set-top box operation content sequences, wherein the plurality of sample set-top box operation content sequences correspond to a plurality of sample time intervals one by one, each of the sample set-top box operation content sequences includes a plurality of sample set-top box operation contents whose corresponding sample set-top box operation time belongs to the corresponding sample time interval, and the plurality of sample set-top box operation contents are sorted based on the chronological relationship between the corresponding sample set-top box operation times, as described above;

[0095] Secondly, using the first feature mining model included in the candidate boot screen matching network, feature mining is performed on each of the sample set-top box running content sequences, and the sample content semantic vector of the sample time interval corresponding to each of the sample set-top box running content sequences is output, as described above;

[0096] Then, using the second feature mining model included in the candidate boot screen matching network, feature mining is performed on each of the sample boot screen files, and a sample screen semantic vector corresponding to each of the sample boot screen files is output, as described above;

[0097] Further, using the picture matching model included in the candidate startup picture matching network, based on the sample content semantic vector of each sample time interval and the sample picture semantic vector corresponding to each sample startup picture file, a sample startup picture file matching each sample time interval is determined, as described above;

[0098] Finally, based on the sample boot screen files matched by each sample time interval and the corresponding boot screen file label (which can be a boot screen file selected by the user), the network error of the candidate boot screen matching network is calculated (the error calculation formula can be configured according to actual needs), and the network parameters of the candidate boot screen matching network are updated in the direction of reducing the network error (until the network error converges or the number of updates is greater than the target number, etc.), forming a corresponding target boot screen matching network, wherein the target boot screen matching network is used to execute the step of determining the boot screen file matching each target time interval in the multiple boot screen files based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data, i.e., step S120.

[0099] Combination Figure 4 The embodiment of the present application also provides a set-top box startup screen control device applicable to the above electronic device. The set-top box startup screen control device may include an operation data acquisition module, a startup screen matching module, and a screen loading scheme sending module.

[0100] In detail, the operation data collection module can be used to collect data on the historical operation process of the target set-top box when there are multiple boot screen storage partitions in the flash memory area of ​​the target set-top box, and obtain the historical set-top box operation data corresponding to the target set-top box, wherein the multiple boot screen storage partitions are used to store multiple boot screen files, and the target set-top box is used to load at least one boot screen file during the boot process to form a corresponding boot screen, and the historical set-top box operation data at least includes the historical set-top box operation time and the historical set-top box operation content corresponding to the historical set-top box operation time. In the embodiment of the present application, the operation data collection module can be used to perform Figure 2 As shown in step S110, the relevant contents of the operation data acquisition module can refer to the above description of step S110.

[0101] In detail, the boot screen matching module can be used to determine a boot screen file that matches each target time interval in a plurality of target time intervals from the plurality of boot screen files based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data, wherein the plurality of target time intervals are formed by dividing a time period. In the embodiment of the present application, the boot screen matching module can be used to perform Figure 2 As shown in step S120, the relevant contents of the boot screen matching module can refer to the above description of step S120.

[0102] In detail, the screen loading scheme sending module can be used to generate a corresponding boot screen loading scheme based on the boot screen file matching each target time interval, and send the boot screen loading scheme to the target set-top box, wherein the target set-top box is used to determine the partition identifier of the boot screen storage partition where the boot screen file corresponding to the current time is located through the boot screen loading scheme during the boot process, and load the corresponding boot screen file from the corresponding boot screen storage partition based on the partition identifier. In the embodiment of the present application, the screen loading scheme sending module can be used to execute Figure 2 As shown in step S130, the relevant contents of the screen loading scheme sending module can refer to the above description of step S130.

[0103] In an embodiment of the present application, corresponding to the above-mentioned set-top box startup screen control method applied to the electronic device, a computer-readable storage medium is also provided, in which a computer program is stored, and when the computer program is run, each step of the set-top box startup screen control method is executed. Among them, each step executed when the aforementioned computer program is run will not be repeated here one by one, and reference can be made to the explanation of the set-top box startup screen control method in the previous text.

[0104] In summary, the set-top box boot screen control method and device, electronic device and storage medium provided by the present application, first, when there are multiple boot screen storage partitions in the flash memory area of ​​the target set-top box, data is collected for the historical operation process to obtain historical set-top box operation data; secondly, based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data, a boot screen file matching each target time interval in multiple target time intervals is determined from multiple boot screen files; then, based on the boot screen file matching each target time interval, a corresponding boot screen loading scheme is generated, and the boot screen loading scheme is sent to the target set-top box. Based on the above content, due to different times, it may represent different user needs, or it may represent different users of set-top boxes, and there may also be different needs. Therefore, the boot screen files of each time can be analyzed based on the historical collection of operation data, so that the set-top box can load the corresponding boot screen file at the corresponding time, thereby achieving the reliability of the set-top box boot screen control, and then improving the problem of poor reliability of the set-top box boot screen control existing in the prior art.

[0105] In several embodiments provided in the embodiments of the present application, it should be understood that the disclosed device and method can also be implemented in other ways. The device and method embodiments described above are merely schematic, for example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the device, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0106] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0107] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, electronic device, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code. It should be noted that in this article, the term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or device. Without more constraints, an element defined by the phrase "comprising a..." does not exclude the existence of other identical elements in the process, method, article or apparatus comprising the element.

[0108] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for controlling the startup screen of a set-top box, characterized in that: include: When there are multiple boot screen storage partitions in the flash memory area of ​​the target set-top box, data collection is performed on the historical operation process of the target set-top box to obtain historical set-top box operation data corresponding to the target set-top box, wherein the multiple boot screen storage partitions are used to store multiple boot screen files, the target set-top box is used to load at least one boot screen file during the boot process to form a corresponding boot screen, and the historical set-top box operation data at least includes historical set-top box operation time and historical set-top box operation content corresponding to the historical set-top box operation time; Based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data, determining a startup screen file matching each target time interval in a plurality of target time intervals from the plurality of startup screen files, wherein the plurality of target time intervals are formed by dividing a time period; Based on the startup screen file matched with each target time interval, a corresponding startup screen loading scheme is generated, and the startup screen loading scheme is sent to the target set-top box, wherein the target set-top box is used to determine the partition identifier of the startup screen storage partition where the startup screen file corresponding to the current time is located through the startup screen loading scheme during the startup process, and load the startup screen file from the corresponding startup screen storage partition based on the partition identifier; The step of determining, from the plurality of startup screen files, a startup screen file matching each target time interval in a plurality of target time intervals based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data, comprises: Splitting and combining the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data to form a plurality of corresponding historical set-top box operation content sequences, wherein the plurality of historical set-top box operation content sequences correspond to a plurality of target time intervals one by one, each of the historical set-top box operation content sequences includes a plurality of historical set-top box operation contents whose corresponding historical set-top box operation time belongs to the corresponding target time interval, and the plurality of historical set-top box operation contents are sorted based on the chronological relationship between the corresponding historical set-top box operation times; Using the first feature mining model included in the target boot screen matching network, feature mining is performed on each of the historical set-top box running content sequences, and the running content semantic vector of the target time interval corresponding to each of the historical set-top box running content sequences is output; Using the second feature mining model included in the target boot screen matching network, feature mining is performed on each of the boot screen files, and a boot screen semantic vector corresponding to each of the boot screen files is output; By utilizing the screen matching model included in the target boot screen matching network, based on the running content semantic vector of each target time interval and the boot screen semantic vector corresponding to each boot screen file, the boot screen file matching each target time interval is determined.

2. The set-top box startup screen control method according to claim 1, characterized in that: The step of using the first feature mining model included in the target boot screen matching network to perform feature mining on each of the historical set-top box running content sequences, and outputting the running content semantic vector of the target time interval corresponding to each of the historical set-top box running content sequences, comprises: For any of the historical set-top box running content sequences, using the embedding unit in the first feature mining model included in the target boot screen matching network, each historical set-top box running content in the historical set-top box running content sequence is embedded to form a corresponding running content embedding vector sequence, and the historical set-top box running time corresponding to each historical set-top box running content is embedded to form a corresponding running time embedding vector sequence; Using the feature sequence alignment unit in the first feature mining model, the running content embedding vector sequence and the running time embedding vector sequence are subjected to feature alignment processing, and a corresponding alignment vector sequence is output, wherein each alignment vector in the alignment vector sequence is formed by concatenating the corresponding running content embedding vector and the running time embedding vector; The semantic transfer unit in the first feature mining model is used to perform semantic transfer processing on the alignment vector sequence, and an operation content semantic vector of the target time interval corresponding to the historical set-top box operation content sequence is output, wherein the operation content semantic vector carries the semantic information of each alignment vector in the alignment vector sequence.

3. The set-top box startup screen control method according to claim 2, characterized in that: The step of using the semantic transfer unit in the first feature mining model to perform semantic transfer processing on the alignment vector sequence and outputting the operation content semantic vector of the target time interval corresponding to the historical set-top box operation content sequence includes: For each alignment vector in the alignment vector sequence, determine whether the alignment vector has an associated alignment vector in the target vector map, and if the associated alignment vector is present, extract an alignment vector sequence fragment including at least the associated alignment vector from the alignment vector sequence where the associated alignment vector is located, wherein the target vector map includes each alignment vector in each alignment vector sequence, and two historical set-top box operation contents corresponding to two alignment vectors having an associated relationship are the same; The semantic transfer unit in the first feature mining model is used in combination with the corresponding alignment vector sequence fragment to perform semantic transfer processing on the alignment vector sequence, and the operation content semantic vector of the target time interval corresponding to the historical set-top box operation content sequence is output.

4. The method for controlling the startup screen of a set-top box according to claim 3, characterized in that: The step of utilizing the semantic transfer unit in the first feature mining model, combining with the corresponding alignment vector sequence fragment, performing semantic transfer processing on the alignment vector sequence, and outputting the operation content semantic vector of the target time interval corresponding to the historical set-top box operation content sequence, comprises: For each alignment vector in the alignment vector sequence, the semantic information represented by the forward alignment vector of the alignment vector is fused into the alignment vector to obtain a local vector of running content corresponding to the alignment vector, and when the alignment vector has an associated alignment vector, the semantic information represented by the alignment vector sequence fragment corresponding to the alignment vector is fused into the local vector of the running content to obtain a corresponding running content associated vector, and when the alignment vector does not have an associated object vector, the local vector of the running content is used as the corresponding running content associated vector, wherein the forward alignment vector of the first alignment vector is a reference vector carried by the semantic transfer unit in the first feature mining model, and the forward alignment vectors of other alignment vectors are running content associated vectors corresponding to the previous alignment vector; After obtaining the running content association vector corresponding to the last alignment vector, the running content association vector corresponding to the last alignment vector is used as the running content semantic vector of the target time interval corresponding to the historical set-top box running content sequence.

5. The method for controlling the startup screen of a set-top box according to claim 1, characterized in that: The step of using the second feature mining model included in the target boot screen matching network to perform feature mining on each of the boot screen files and outputting a boot screen semantic vector corresponding to each of the boot screen files comprises: For any of the boot screen files, using the convolution unit in the second feature mining model included in the target boot screen matching network, convolution processing is performed on each boot screen frame in the boot screen file to form a corresponding boot screen convolution vector sequence; In the vector transfer unit included in the second feature mining model, for each boot screen convolution vector in the boot screen convolution vector sequence, the semantic information represented by the forward convolution vector of the boot screen convolution vector is fused into the boot screen convolution vector to obtain a corresponding boot screen fusion vector, wherein the forward convolution vector of the first boot screen convolution vector is a reference vector carried by the vector transfer unit, and the forward convolution vectors of other boot screen convolution vectors are boot screen fusion vectors corresponding to the previous boot screen convolution vector; After obtaining the boot screen fusion vector corresponding to the last boot screen convolution vector, the boot screen fusion vector corresponding to the last boot screen convolution vector is used as the boot screen semantic vector corresponding to the boot screen file.

6. The method for controlling the startup screen of a set-top box according to any one of claims 1 to 5, characterized in that: The set-top box startup screen control method also includes: Splitting and combining the sample set-top box operation time and the corresponding sample set-top box operation content included in the sample set-top box operation data to form a plurality of corresponding sample set-top box operation content sequences, wherein the plurality of sample set-top box operation content sequences correspond to the plurality of sample time intervals one by one, each of the sample set-top box operation content sequences includes a plurality of sample set-top box operation contents whose corresponding sample set-top box operation time belongs to the corresponding sample time interval, and the plurality of sample set-top box operation contents are sorted based on the chronological relationship between the corresponding sample set-top box operation times; Using the first feature mining model included in the candidate boot screen matching network, feature mining is performed on each of the sample set-top box running content sequences, and a sample content semantic vector corresponding to a sample time interval of each of the sample set-top box running content sequences is output; Using the second feature mining model included in the candidate startup screen matching network, feature mining is performed on each sample startup screen file, and a sample screen semantic vector corresponding to each sample startup screen file is output; Using the picture matching model included in the candidate startup picture matching network, based on the sample content semantic vector of each sample time interval and the sample picture semantic vector corresponding to each sample startup picture file, determine the sample startup picture file that matches each sample time interval; Based on the sample boot screen files matched by each of the sample time intervals and the corresponding boot screen file labels, a network error of the candidate boot screen matching network is calculated, and the network parameters of the candidate boot screen matching network are updated in a direction of reducing the network error to form a corresponding target boot screen matching network, wherein the target boot screen matching network is used to execute the step of determining, from the multiple boot screen files, a boot screen file matching each target time interval in a plurality of target time intervals based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data.

7. A set-top box startup screen control device, characterized in that: include: An operation data collection module is used to collect data on the historical operation process of the target set-top box when there are multiple startup screen storage partitions in the flash memory area of ​​the target set-top box, so as to obtain historical set-top box operation data corresponding to the target set-top box, wherein the multiple startup screen storage partitions are used to store multiple startup screen files, the target set-top box is used to load at least one startup screen file during the startup process to form a corresponding startup screen, and the historical set-top box operation data at least includes a historical set-top box operation time and a historical set-top box operation content corresponding to the historical set-top box operation time; a boot screen matching module, configured to determine, from the plurality of boot screen files, a boot screen file that matches each of a plurality of target time intervals based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data, wherein the plurality of target time intervals are formed by dividing a time period; A screen loading scheme sending module is used to generate a corresponding boot screen loading scheme based on the boot screen file matched with each target time interval, and send the boot screen loading scheme to the target set-top box, wherein the target set-top box is used to determine the partition identifier of the boot screen storage partition where the boot screen file corresponding to the current time is located through the boot screen loading scheme during the boot process, and load the corresponding boot screen file from the corresponding boot screen storage partition based on the partition identifier; Wherein, based on the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data, determining the startup screen file matching each target time interval in the multiple target time intervals from the multiple startup screen files comprises: Splitting and combining the historical set-top box operation time and the corresponding historical set-top box operation content included in the historical set-top box operation data to form a plurality of corresponding historical set-top box operation content sequences, wherein the plurality of historical set-top box operation content sequences correspond to a plurality of target time intervals one by one, each of the historical set-top box operation content sequences includes a plurality of historical set-top box operation contents whose corresponding historical set-top box operation time belongs to the corresponding target time interval, and the plurality of historical set-top box operation contents are sorted based on the chronological relationship between the corresponding historical set-top box operation times; Using the first feature mining model included in the target boot screen matching network, feature mining is performed on each of the historical set-top box running content sequences, and the running content semantic vector of the target time interval corresponding to each of the historical set-top box running content sequences is output; Using the second feature mining model included in the target boot screen matching network, feature mining is performed on each of the boot screen files, and a boot screen semantic vector corresponding to each of the boot screen files is output; By utilizing the screen matching model included in the target boot screen matching network, based on the running content semantic vector of each target time interval and the boot screen semantic vector corresponding to each boot screen file, the boot screen file matching each target time interval is determined.

8. An electronic device, characterized in that: include: Memory for storing computer programs; A processor connected to the memory is used to execute the computer program stored in the memory to implement the set-top box startup screen control method described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is run, the set-top box startup screen control method described in any one of claims 1 to 6 is executed.

Images