Set-top box upgrade management and control method and device, electronic device and storage medium

Abstract

The set-top box upgrade control method and device, electronic device and storage medium provided in the present application relate to the field of set-top box upgrade technology. In the present application, first, the set-top box operation data corresponding to the set-top box to be upgraded and the user behavior data of the set-top box user corresponding to the set-top box to be upgraded are collected; secondly, based on the set-top box operation data and user behavior data, the target set-top box upgrade plan corresponding to the set-top box to be upgraded is analyzed; then, based on the target set-top box upgrade plan, the corresponding operating system upgrade data is sent to the set-top box to be upgraded, so that the set-top box to be upgraded upgrades the corresponding set-top box operating system based on the operating system upgrade data to upgrade to the target version. Based on the above content, the problem of relatively low reliability of set-top box upgrade 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 upgrades, and in particular to a set-top box upgrade management and control method and device, electronic equipment, and storage medium. Background Art

[0002] As an important household device, the set-top box plays an important role in daily life. Among them, in order to meet the growing needs of users, the operating system of the set-top box has gradually become more complicated to support more functional requirements, but, accordingly, the data volume of the operating system will also be larger and larger. Therefore, in the upgrade process of the operating system, it is necessary to obtain an upgrade file with a large data volume. In addition, in order to avoid excessive consumption of network resources, memory resources, etc. by the upgrade file, in the prior art, generally the difference file between the current version and the target version is determined at the back end, and then the difference file is sent to the set-top box, so as to complete the operating system upgrade of the set-top box, but, the inventor has found that only sending the difference file for upgrading will cause the upgrade to fail easily, therefore, corresponding to the upgrade control of the set-top box, there is a relatively low reliability problem in the prior art. Summary of the invention

[0003] In view of this, the purpose of the present application is to provide a set-top box upgrade management method and device, electronic equipment and storage medium, so as to improve the problem of relatively low reliability of set-top box upgrade management in the prior art.

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

[0005] A set-top box upgrade management and control method, comprising:

[0006] Collecting set-top box operation data corresponding to the set-top box to be upgraded and user behavior data of the set-top box user corresponding to the set-top box to be upgraded, wherein the set-top box operation data is used to reflect the abnormal operation of the set-top box to be upgraded, and the user behavior data is used to reflect the use behavior of the set-top box user for the set-top box to be upgraded;

[0007] Based on the set-top box operation data and the user behavior data, analyzing a target set-top box upgrade solution corresponding to the set-top box to be upgraded, wherein the target set-top box upgrade solution belongs to a first set-top box upgrade solution or a second set-top box upgrade solution, the first set-top box upgrade solution refers to using all data of the target version of the operating system file as the operating system upgrade data, and the second set-top box upgrade solution refers to using the difference data between the target version of the operating system file and the current version of the operating system file of the set-top box to be upgraded as the operating system upgrade data;

[0008] Based on the target set-top box upgrade solution, the corresponding operating system upgrade data is sent to the set-top box to be upgraded, so that the set-top box to be upgraded upgrades the corresponding set-top box operating system based on the operating system upgrade data to upgrade to the target version.

[0009] In a preferred embodiment of the present application, in the above-mentioned set-top box upgrade management and control method, the step of analyzing the target set-top box upgrade solution corresponding to the set-top box to be upgraded based on the set-top box operation data and the user behavior data includes:

[0010] Obtaining sample set-top box operation data, sample user behavior data, and set-top box upgrade solution labels, and training a candidate solution prediction network based on the sample set-top box operation data, the sample user behavior data, and the set-top box upgrade solution labels to obtain a target solution prediction network, wherein the target solution prediction network is a neural network;

[0011] The target solution prediction network is used to analyze the set-top box operation data and the user behavior data to obtain a target set-top box upgrade solution corresponding to the set-top box to be upgraded.

[0012] In a preferred embodiment of the present application, in the above-mentioned set-top box upgrade control method, the step of using the target solution prediction network to analyze the set-top box operation data and the user behavior data to obtain the target set-top box upgrade solution corresponding to the set-top box to be upgraded includes:

[0013] Using the first branch network included in the target solution prediction network, performing semantic feature mining on the set-top box operation data, and outputting set-top box operation features corresponding to the set-top box operation data;

[0014] Using the second branch network included in the target solution prediction network, the user behavior data is mined for semantic features, and the user behavior features corresponding to the user behavior data are output, wherein the mining depth in the first branch network has multiple levels, so that the set-top box operation features include multiple levels of set-top box operation sub-features, and the mining depth in the second branch network has multiple levels, so that the user behavior features include multiple levels of user behavior sub-features, and the multiple levels of set-top box operation sub-features correspond to the multiple levels of user behavior sub-features one by one;

[0015] Using the association fusion subnetwork included in the target solution prediction network, the set-top box operation features including multiple levels of set-top box operation sub-features and the user behavior features including multiple levels of user behavior sub-features are associated with significant features and fused to output target features;

[0016] The target feature is analyzed by using the solution prediction subnetwork included in the target solution prediction network, and a target set-top box upgrade solution corresponding to the set-top box to be upgraded is output.

[0017] In a preferred embodiment of the present application, in the above-mentioned set-top box upgrade management and control method, the step of using the first branch network included in the target solution prediction network to perform semantic feature mining on the set-top box operation data and outputting the set-top box operation features corresponding to the set-top box operation data includes:

[0018] Using a first first deep mining unit in a first branch network included in the target solution prediction network, deep mining is performed on the set-top box operation embedding features corresponding to the set-top box operation data, and outputting the set-top box operation deep features corresponding to the first first deep mining unit;

[0019] Using each first deep mining unit other than the first first deep mining unit in the first branch network, segment the set-top box operation depth feature corresponding to the previous first deep mining unit to form a corresponding plurality of local set-top box operation depth features, and based on the feature size of the set-top box operation depth feature, expand each local set-top box operation depth feature to obtain a corresponding plurality of extended set-top box operation depth features, and respectively perform deep mining on each of the extended set-top box operation depth features, and superimpose the features output by the deep mining to output the set-top box operation depth feature corresponding to the first deep mining unit;

[0020] According to the hierarchical relationship between the first deep mining units, the set-top box operation deep features corresponding to each of the first deep mining units are respectively determined as set-top box operation sub-features of the corresponding level to obtain a set-top box operation feature including set-top box operation sub-features of multiple levels.

[0021] In a preferred embodiment of the present application, in the above-mentioned set-top box upgrade management and control method, the step of using the second branch network included in the target solution prediction network to perform semantic feature mining on the user behavior data and outputting the user behavior features corresponding to the user behavior data includes:

[0022] Using the first second deep mining unit in the second branch network included in the target solution prediction network, deep mining is performed on the user behavior embedding features corresponding to the user behavior data, and the user behavior deep features corresponding to the first second deep mining unit are output;

[0023] Using each second deep mining unit other than the first second deep mining unit in the second branch network, the user behavior deep feature corresponding to the previous second deep mining unit is segmented to form a corresponding plurality of local user behavior deep features, and based on the feature size of the user behavior deep feature, each local user behavior deep feature is expanded to obtain a corresponding plurality of expanded user behavior deep features, and each of the expanded user behavior deep features is deep mined respectively, and the features output by the deep mining are superimposed to output the user behavior deep feature corresponding to the second deep mining unit;

[0024] According to the hierarchical relationship between the second deep mining units, the user behavior deep features corresponding to each of the second deep mining units are respectively determined as user behavior sub-features of the corresponding level to obtain user behavior features including user behavior sub-features of multiple levels.

[0025] In a preferred embodiment of the present application, in the above-mentioned set-top box upgrade management and control method, the step of using the associated fusion sub-network included in the target solution prediction network to perform association mining and fusion of significant features on the set-top box operation features including multiple levels of set-top box operation sub-features and the user behavior features including multiple levels of user behavior sub-features, and outputting the target features includes:

[0026] For each level of the association fusion unit in the association fusion subnetwork included in the target solution prediction network, using the association fusion unit, based on the set-top box operation subfeatures of the corresponding level, the user behavior subfeatures of the corresponding level are mined for significant features, so that significant features associated with the set-top box operation subfeatures in the user behavior subfeatures are mined, and a first associated significant feature corresponding to the association fusion unit is obtained; and based on the user behavior subfeatures of the corresponding level, the set-top box operation subfeatures of the corresponding level are mined for significant features, so that significant features associated with the user behavior subfeatures in the set-top box operation subfeatures are mined, and a second associated significant feature corresponding to the association fusion unit is obtained;

[0027] For each level of the associated fusion unit, using the associated fusion unit, the set-top box operation sub-feature, the user behavior sub-feature, the first associated significant feature and the second associated significant feature of the level corresponding to the associated fusion unit are superimposed to form a corresponding target sub-feature;

[0028] The target sub-features corresponding to the associated fusion units of each level are weighted and fused to output the corresponding target features. In the process of weighted fusion, the weight coefficients corresponding to the target sub-features have a positive correlation with the corresponding levels.

[0029] In a preferred embodiment of the present application, in the above-mentioned set-top box upgrade management and control method, the step of acquiring sample set-top box operation data, sample user behavior data and set-top box upgrade solution labels, and training a candidate solution prediction network based on the sample set-top box operation data, the sample user behavior data and the set-top box upgrade solution labels to obtain a target solution prediction network includes:

[0030] Obtaining sample set-top box operation data, sample user behavior data, and a set-top box upgrade solution label, wherein the set-top box upgrade solution label is used to reflect the corresponding actual set-top box upgrade solution;

[0031] Using the first branch network included in the candidate solution prediction network, performing semantic feature mining on the sample set-top box operation data, and outputting sample set-top box operation features corresponding to the sample set-top box operation data;

[0032] Using the second branch network included in the candidate solution prediction network, performing semantic feature mining on the sample user behavior data, and outputting sample user behavior features corresponding to the sample user behavior data;

[0033] Using the association fusion sub-network included in the candidate solution prediction network, the sample set-top box operation features including multiple levels of sample set-top box operation sub-features and the sample user behavior features including multiple levels of sample user behavior sub-features are associated with significant features and fused to output sample target features;

[0034] Utilizing the solution prediction subnetwork included in the candidate solution prediction network, analyzing the sample target features, and outputting a corresponding sample set-top box upgrade solution;

[0035] Based on the difference between the sample set-top box upgrade solution and the set-top box upgrade solution label, the network parameters of the candidate solution prediction network are updated until the difference converges or the number of updates reaches a preset number, thereby obtaining a corresponding target solution prediction network.

[0036] The present application also provides a set-top box upgrade control device, including:

[0037] A data collection module, used to collect set-top box operation data corresponding to the set-top box to be upgraded and user behavior data of the set-top box user corresponding to the set-top box to be upgraded, wherein the set-top box operation data is used to reflect the abnormal operation of the set-top box to be upgraded, and the user behavior data is used to reflect the use behavior of the set-top box user for the set-top box to be upgraded;

[0038] A solution analysis module, configured to analyze a target set-top box upgrade solution corresponding to the set-top box to be upgraded based on the set-top box operation data and the user behavior data, wherein the target set-top box upgrade solution belongs to a first set-top box upgrade solution or a second set-top box upgrade solution, the first set-top box upgrade solution refers to using all data of the target version of the operating system file as the operating system upgrade data, and the second set-top box upgrade solution refers to using the difference data between the target version of the operating system file and the current version of the operating system file of the set-top box to be upgraded as the operating system upgrade data;

[0039] The system upgrade module is used to send the corresponding operating system upgrade data to the set-top box to be upgraded based on the target set-top box upgrade plan, so that the set-top box to be upgraded upgrades the corresponding set-top box operating system based on the operating system upgrade data to upgrade to the target version.

[0040] Based on the above, the present application also provides an electronic device, including:

[0041] Memory for storing computer programs;

[0042] 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 upgrade management and control method.

[0043] 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 upgrade management and control method is executed.

[0044] The set-top box upgrade control method and device, electronic device and storage medium provided by the present application, first, collect the set-top box operation data corresponding to the set-top box to be upgraded and the user behavior data of the set-top box user corresponding to the set-top box to be upgraded; secondly, based on the set-top box operation data and the user behavior data, analyze the target set-top box upgrade plan corresponding to the set-top box to be upgraded; then, based on the target set-top box upgrade plan, send the corresponding operating system upgrade data to the set-top box to be upgraded, so that the set-top box to be upgraded upgrades the corresponding set-top box operating system based on the operating system upgrade data to upgrade to the target version. Based on the above content, since before sending the operating system upgrade data, the target set-top box upgrade plan corresponding to the set-top box to be upgraded will be analyzed based on the set-top box operation data and the user behavior data, so that the target set-top box upgrade plan is more matched with the actual situation of the set-top box upgrade, therefore, when upgrading based on the target set-top box upgrade plan, the reliability of the upgrade can be relatively higher, so that the upgrade can be controlled with high reliability, thereby improving the problem of relatively low reliability of set-top box upgrade control existing in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] 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.

[0046] Figure 1 A structural block diagram of an electronic device provided in an embodiment of the present application.

[0047] Figure 2 A flowchart of a set-top box upgrade management and control method provided in an embodiment of the present application.

[0048] Figure 3 A network architecture diagram of a target solution prediction network provided in an embodiment of the present application.

[0049] Figure 4 A block diagram of a set-top box upgrade control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] 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.

[0051] 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.

[0052] 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 upgrade control device.

[0053] 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 upgrade 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 upgrade control device, so as to implement the set-top box upgrade control method provided in the embodiment of the present application.

[0054] 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.

[0055] 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.

[0056] Understandably, Figure 1 The 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).

[0057] Combination Figure 2 The present application also provides a set-top box upgrade control method applicable to the above electronic device. The method steps defined in the process related to the set-top box upgrade control method can be implemented by the electronic device. Figure 2 The process shown is described in detail.

[0058] Step S110, collecting set-top box operation data corresponding to the set-top box to be upgraded and user behavior data of the set-top box user corresponding to the set-top box to be upgraded.

[0059] In an embodiment of the present application, the electronic device may collect set-top box operation data corresponding to the set-top box to be upgraded and user behavior data of the set-top box user corresponding to the set-top box to be upgraded. The set-top box operation data is used to reflect the abnormal operation of the set-top box to be upgraded (such as network status, power supply status, downtime status, etc.), and the user behavior data is used to reflect the use behavior of the set-top box user for the set-top box to be upgraded (such as the willingness to upgrade different set-top box solutions, the frequency of use of the set-top box to be upgraded, etc.).

[0060] Step S120: Analyze the target set-top box upgrade solution corresponding to the set-top box to be upgraded based on the set-top box operation data and the user behavior data.

[0061] In an embodiment of the present application, the electronic device can analyze the target set-top box upgrade scheme corresponding to the set-top box to be upgraded based on the set-top box operation data and the user behavior data. Wherein, the target set-top box upgrade scheme belongs to the first set-top box upgrade scheme or the second set-top box upgrade scheme, the first set-top box upgrade scheme refers to using all data of the target version of the operating system file as the operating system upgrade data, and the second set-top box upgrade scheme refers to using the difference data between the target version of the operating system file and the current version of the operating system file of the set-top box to be upgraded as the operating system upgrade data. For example, if the set-top box operation data reflects that the network condition is not good, the second set-top box upgrade scheme can be selected, and if the set-top box operation data reflects that the network condition is good and the memory resources are sufficient, and the user behavior data reflects that the set-top box user is willing to spend more time waiting, the first set-top box upgrade scheme can be selected.

[0062] Step S130, based on the target set-top box upgrade solution, the corresponding operating system upgrade data is sent to the set-top box to be upgraded, so that the set-top box to be upgraded upgrades the corresponding set-top box operating system based on the operating system upgrade data to upgrade to the target version.

[0063] In an embodiment of the present application, the electronic device can send corresponding operating system upgrade data to the set-top box to be upgraded based on the target set-top box upgrade plan, so that the set-top box to be upgraded upgrades the corresponding set-top box operating system based on the operating system upgrade data to upgrade to the target version.

[0064] Based on the above content, since the target set-top box upgrade plan corresponding to the set-top box to be upgraded will be analyzed based on the set-top box operation data and user behavior data before sending the operating system upgrade data, the target set-top box upgrade plan is more in line with the actual situation of the set-top box upgrade. Therefore, when upgrading based on the target set-top box upgrade plan, the reliability of the upgrade can be relatively higher. In this way, high-reliability management and control of the upgrade can be achieved, thereby improving the problem of relatively low reliability of set-top box upgrade management in the prior art.

[0065] It should be noted that for step S120, the specific method of analyzing the target set-top box upgrade solution corresponding to the set-top box to be upgraded is not limited and can be selected according to actual needs.

[0066] For example, in an alternative implementation, in order to improve the reliability of the analyzed target set-top box upgrade solution so that the compatibility between the set-top box to be upgraded and the set-top box user can be higher, the above-mentioned step S120 can further include step S121 and step S122, and the specific content of each step is described as follows.

[0067] Step S121, obtaining sample set-top box operation data, sample user behavior data and set-top box upgrade solution labels, and based on the sample set-top box operation data, the sample user behavior data and the set-top box upgrade solution labels, training a candidate solution prediction network to obtain a target solution prediction network.

[0068] In the embodiment of the present application, sample set-top box operation data, sample user behavior data and set-top box upgrade solution labels can be obtained, and based on the sample set-top box operation data, the sample user behavior data and the set-top box upgrade solution labels, the candidate solution prediction network is trained to obtain the target solution prediction network. The target solution prediction network is a neural network.

[0069] Step S122, using the target solution prediction network, analyzing the set-top box operation data and the user behavior data to obtain a target set-top box upgrade solution corresponding to the set-top box to be upgraded.

[0070] In an embodiment of the present application, after a reliable target solution prediction network is trained, the target solution prediction network can be used to analyze the set-top box operation data and the user behavior data to obtain a target set-top box upgrade solution corresponding to the set-top box to be upgraded.

[0071] It can be understood that, in the above step S121, the specific method of training the candidate solution prediction network is not limited and can be selected according to actual needs.

[0072] For example, in an alternative implementation, in order to ensure that the trained target solution prediction network has a high reliability, the above step S121 may further include the following contents:

[0073] First, sample set-top box operation data, sample user behavior data and set-top box upgrade solution labels can be obtained, wherein the set-top box upgrade solution labels are used to reflect the corresponding actual set-top box upgrade solution, and the actual set-top box upgrade solution can be a solution actually required by the corresponding user;

[0074] Secondly, using the first branch network included in the candidate solution prediction network, semantic feature mining is performed on the sample set-top box operation data, and sample set-top box operation features corresponding to the sample set-top box operation data are output, and reference may be made to the relevant description below;

[0075] Then, using the second branch network included in the candidate solution prediction network, semantic feature mining is performed on the sample user behavior data, and sample user behavior features corresponding to the sample user behavior data are output, and reference may be made to the relevant description below;

[0076] Further, using the association fusion sub-network included in the candidate solution prediction network, the sample set-top box operation features including multiple levels of sample set-top box operation sub-features and the sample user behavior features including multiple levels of sample user behavior sub-features are subjected to association mining and fusion of significant features, and sample target features are output, which can be referred to the relevant description below;

[0077] Further, the solution prediction subnetwork included in the candidate solution prediction network is used to analyze the sample target features and output the corresponding sample set-top box upgrade solution, which can be referred to the relevant description below;

[0078] Finally, based on the difference between the sample set-top box upgrade solution and the set-top box upgrade solution label, the network parameters of the candidate solution prediction network are updated until the difference converges or the number of updates reaches a preset number, and the corresponding target solution prediction network is obtained; exemplarily, an error calculation can be performed based on the sample set-top box upgrade solution and the set-top box upgrade solution label (the specific error calculation formula is not specifically limited here) to obtain the corresponding error, and then, the network parameters of the candidate solution prediction network can be updated in the direction of reducing the error until the error converges or the number of updates reaches a preset number (which can be configured according to actual needs), thereby obtaining the corresponding target solution prediction network.

[0079] It can be understood that, in the above step S122, the specific method of using the target solution prediction network to analyze the set-top box operation data and the user behavior data is not limited and can be selected according to actual needs.

[0080] For example, in an alternative implementation, in order to ensure that the target set-top box upgrade solution has a high reliability, the above-mentioned step S122 may further include step S122a, step S122b, step S122c and step S122d, and the specific content of each step is described as follows.

[0081] Step S122a, using the first branch network included in the target solution prediction network, performs semantic feature mining on the set-top box operation data, and outputs the set-top box operation features corresponding to the set-top box operation data.

[0082] In an embodiment of the present application, the first branch network included in the target solution prediction network can be used to perform semantic feature mining on the set-top box operation data, and output the set-top box operation features corresponding to the set-top box operation data. In other words, the semantic information in the set-top box operation data can be mined. In addition, in an embodiment of the present application, the expression form of each feature can be a vector.

[0083] Step S122b, using the second branch network included in the target solution prediction network to perform semantic feature mining on the user behavior data, and output user behavior features corresponding to the user behavior data.

[0084] In an embodiment of the present application, the second branch network included in the target solution prediction network can be used to perform semantic feature mining on the user behavior data and output user behavior features corresponding to the user behavior data. Wherein, the mining depth in the first branch network has multiple levels, so that the set-top box operation feature includes multiple levels of set-top box operation sub-features, and the mining depth in the second branch network has multiple levels, so that the user behavior feature includes multiple levels of user behavior sub-features, and the multiple levels of set-top box operation sub-features correspond to the multiple levels of user behavior sub-features.

[0085] Step S122c, using the associated fusion sub-network included in the target solution prediction network, the set-top box operation features including multiple levels of set-top box operation sub-features and the user behavior features including multiple levels of user behavior sub-features are associated with significant features and fused to output the target features.

[0086] In an embodiment of the present application, the associated fusion sub-network included in the target solution prediction network can be used to perform association mining and fusion of significant features on the set-top box operation features including multiple levels of set-top box operation sub-features and the user behavior features including multiple levels of user behavior sub-features, and output target features. In this way, full fusion of the semantic information corresponding to the set-top box operation data and the user behavior data can be achieved, thereby obtaining target features with better semantic representation.

[0087] Step S122d, using the solution prediction subnetwork included in the target solution prediction network, the target feature is analyzed to output a target set-top box upgrade solution corresponding to the set-top box to be upgraded.

[0088] In an embodiment of the present application, after obtaining the target feature, the target feature can be analyzed using the solution prediction subnetwork included in the target solution prediction network, and the target set-top box upgrade solution corresponding to the set-top box to be upgraded can be output. Exemplarily, the solution prediction subnetwork can include a fully connected network and an output function (such as a classification function such as softmax or Sigmoid), that is, the target feature can be processed using the fully connected network to obtain the corresponding fully connected feature, and then the fully connected feature can be processed using the output function to obtain the corresponding probability, and then, based on the corresponding probability, the first set-top box upgrade solution or the second set-top box upgrade solution is determined as the target set-top box upgrade solution corresponding to the set-top box to be upgraded.

[0089] It can be understood that, in the above step S122a, the specific method of using the first branch network included in the target solution prediction network to mine the semantic features of the set-top box operation data is not limited and can be selected according to actual needs. For example, in an alternative implementation, in order to ensure that the mined set-top box operation features can have richer semantic information, the above step S122a can further include the following content:

[0090] First, a first first deep mining unit in a first branch network included in the target solution prediction network is used to perform deep mining on the set-top box operation embedding feature corresponding to the set-top box operation data, and a set-top box operation deep feature corresponding to the first first deep mining unit is output; illustratively, the deep mining may be self-attention processing, that is, self-attention processing is performed on the set-top box operation embedding feature to obtain a corresponding self-attention feature, and the self-attention feature is used as the corresponding set-top box operation deep feature. In addition, the set-top box operation embedding feature may be obtained by performing word embedding processing on the set-top box operation data (which may be implemented by a corresponding word embedding model);

[0091] Secondly, using each first deep mining unit other than the first first deep mining unit in the first branch network, the set-top box operation depth feature corresponding to the previous first deep mining unit is segmented to form a corresponding plurality of local set-top box operation depth features (exemplarily, equal-size segmentation can be performed so that the feature size of each local set-top box operation depth feature is consistent), and based on the feature size of the set-top box operation depth feature, each local set-top box operation depth feature is expanded (such as by interpolation to supplement more detail information) to obtain a corresponding plurality of extended set-top box operation depth features, and each of the extended set-top box operation depth features is deep mined (such as self-attention processing) respectively, and the features output by the deep mining are superimposed to output the set-top box operation depth feature corresponding to the first deep mining unit (i.e., the respective attention features obtained by the self-attention processing are superimposed);

[0092] Then, according to the hierarchical relationship between the first deep mining units, the set-top box operation depth features corresponding to each of the first deep mining units are respectively determined as the set-top box operation sub-features of the corresponding level, so as to obtain the set-top box operation features including set-top box operation sub-features of multiple levels; illustratively, the set-top box operation depth features corresponding to the first first deep mining unit can be used as the set-top box operation sub-features of the first level; the set-top box operation depth features corresponding to the second first deep mining unit can be used as the set-top box operation sub-features of the second level.

[0093] It can be understood that, in the above step S122b, the specific method of using the second branch network included in the target solution prediction network to mine the semantic features of the user behavior data is not limited and can be selected according to actual needs. For example, in an alternative implementation, in order to ensure that the mined user behavior features can have richer semantic information, the above step S122b can further include the following content:

[0094] First, the first second deep mining unit in the second branch network included in the target solution prediction network is used to perform deep mining on the user behavior embedding features corresponding to the user behavior data, and output the user behavior deep features corresponding to the first second deep mining unit; illustratively, the deep mining can be self-attention processing, that is, self-attention processing is performed on the user behavior embedding features to obtain corresponding self-attention features, and use them as corresponding user behavior deep features. In addition, the user behavior embedding features can be obtained by performing word embedding processing on the user behavior data (which can be implemented by a corresponding word embedding model);

[0095] Secondly, using each second deep mining unit other than the first second deep mining unit in the second branch network, the user behavior deep feature corresponding to the previous second deep mining unit is segmented to form a corresponding plurality of local user behavior deep features (exemplarily, equal-size segmentation can be performed so that the feature size of each local user behavior deep feature is consistent), and based on the feature size of the user behavior deep feature, each local user behavior deep feature is expanded (such as by interpolation to supplement more detail information) to obtain a corresponding plurality of expanded user behavior deep features, and each of the expanded user behavior deep features is deep mined (such as self-attention processing) respectively, and the features output by the deep mining are superimposed to output the user behavior deep feature corresponding to the second deep mining unit (i.e., the respective attention features obtained by the self-attention processing are superimposed);

[0096] Then, according to the hierarchical relationship between the second deep mining units, the user behavior deep features corresponding to each of the second deep mining units are respectively determined as user behavior sub-features of the corresponding level to obtain user behavior features including user behavior sub-features of multiple levels; illustratively, the user behavior deep features corresponding to the first second deep mining unit can be used as user behavior sub-features of the first level; the user behavior deep features corresponding to the second second deep mining unit can be used as user behavior sub-features of the second level.

[0097] It is understandable that, in the above step S122c, the specific manner of performing association mining and fusion of significant features for the set-top box operation feature including multiple levels of set-top box operation sub-features and the user behavior feature including multiple levels of user behavior sub-features is not limited and can be selected according to actual needs. For example, in an alternative implementation, in combination with Figure 3 In order to ensure that the mined target features can have richer semantic information, the above step S122c can further include the following contents:

[0098] First, for each level of the association fusion unit in the association fusion subnetwork included in the target solution prediction network, the association fusion unit is used to mine the significant features of the user behavior subfeatures of the corresponding level based on the set-top box operation subfeatures of the corresponding level, so that the significant features in the user behavior subfeatures that are associated with the set-top box operation subfeatures are mined, and the first associated significant features corresponding to the association fusion unit are obtained (for example, the set-top box operation subfeature and the user behavior subfeature can be multiplied to obtain the corresponding similarity parameter, and then the user behavior subfeatures are mined based on the similarity parameter). The sub-features of the corresponding level are weighted to obtain the corresponding first associated significant feature), and the set-top box operation sub-features of the corresponding level are mined for significant features based on the user behavior sub-features of the corresponding level, so that the significant features associated with the user behavior sub-features in the set-top box operation sub-features are mined to obtain the second associated significant feature corresponding to the associated fusion unit (exemplarily, the user behavior sub-feature and the set-top box operation sub-feature can be multiplied to obtain the corresponding similarity parameter, and then the set-top box operation sub-features are weighted based on the similarity parameter to obtain the corresponding second associated significant feature);

[0099] Secondly, for each level of the associated fusion unit, the associated fusion unit is used to superimpose the set-top box operation sub-feature, user behavior sub-feature, first associated significant feature and second associated significant feature of the corresponding level of the associated fusion unit to form a corresponding target sub-feature;

[0100] Then, the target sub-features corresponding to the associated fusion units of each level are weighted and fused to output the corresponding target features. In the process of weighted fusion, the weight coefficients corresponding to the target sub-features are positively correlated with the corresponding levels, that is, the higher the level, the larger the corresponding weight coefficients, and the lower the level, the smaller the corresponding weight coefficients. In addition, the sum of the weight coefficients is equal to 1.

[0101] Combination Figure 4 The embodiment of the present application also provides a set-top box upgrade control device applicable to the above electronic device. The set-top box upgrade control device may include a data acquisition module, a solution analysis module and a system upgrade module.

[0102] In detail, the data acquisition module can be used to collect set-top box operation data corresponding to the set-top box to be upgraded and user behavior data of the set-top box user corresponding to the set-top box to be upgraded, wherein the set-top box operation data is used to reflect the abnormal operation of the set-top box to be upgraded, and the user behavior data is used to reflect the use behavior of the set-top box user for the set-top box to be upgraded. Figure 2As shown in step S110, the relevant contents of the data acquisition module can refer to the above description of step S110.

[0103] In detail, the solution analysis module can be used to analyze the target set-top box upgrade solution corresponding to the set-top box to be upgraded based on the set-top box operation data and the user behavior data, wherein the target set-top box upgrade solution belongs to the first set-top box upgrade solution or the second set-top box upgrade solution, the first set-top box upgrade solution refers to using all data of the target version of the operating system file as the operating system upgrade data, and the second set-top box upgrade solution refers to using the difference data between the target version of the operating system file and the current version of the operating system file of the set-top box to be upgraded as the operating system upgrade data. In the embodiment of the present application, the solution analysis module can be used to perform Figure 2 As shown in step S120, the relevant contents of the solution analysis module can refer to the above description of step S120.

[0104] In detail, the system upgrade module can be used to send the corresponding operating system upgrade data to the set-top box to be upgraded based on the target set-top box upgrade solution, so that the set-top box to be upgraded upgrades the corresponding set-top box operating system based on the operating system upgrade data to upgrade to the target version. Figure 2 As shown in step S130, the relevant contents of the system upgrade module can refer to the above description of step S130.

[0105] In an embodiment of the present application, corresponding to the above-mentioned set-top box upgrade 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 upgrade 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 upgrade control method in the previous text.

[0106] In summary, the set-top box upgrade control method and device, electronic device and storage medium provided by the present application, first, collect the set-top box operation data corresponding to the set-top box to be upgraded and the user behavior data of the set-top box user corresponding to the set-top box to be upgraded; secondly, based on the set-top box operation data and the user behavior data, analyze the target set-top box upgrade scheme corresponding to the set-top box to be upgraded; then, based on the target set-top box upgrade scheme, send the corresponding operating system upgrade data to the set-top box to be upgraded, so that the set-top box to be upgraded upgrades the corresponding set-top box operating system based on the operating system upgrade data to upgrade to the target version. Based on the above content, since before sending the operating system upgrade data, the target set-top box upgrade scheme corresponding to the set-top box to be upgraded will be analyzed based on the set-top box operation data and the user behavior data, so that the target set-top box upgrade scheme is more matched with the actual situation of the set-top box upgrade, therefore, when upgrading based on the target set-top box upgrade scheme, the reliability of the upgrade can be relatively higher, so that the upgrade can be controlled with high reliability, thereby improving the problem of relatively low reliability of set-top box upgrade control existing in the prior art.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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 set-top box upgrade management and control method, characterized in that: include: Collecting set-top box operation data corresponding to the set-top box to be upgraded and user behavior data of the set-top box user corresponding to the set-top box to be upgraded, wherein the set-top box operation data is used to reflect the abnormal operation of the set-top box to be upgraded, and the user behavior data is used to reflect the use behavior of the set-top box user for the set-top box to be upgraded; Based on the set-top box operation data and the user behavior data, analyzing a target set-top box upgrade solution corresponding to the set-top box to be upgraded, wherein the target set-top box upgrade solution belongs to a first set-top box upgrade solution or a second set-top box upgrade solution, the first set-top box upgrade solution refers to using all data of the target version of the operating system file as the operating system upgrade data, and the second set-top box upgrade solution refers to using the difference data between the target version of the operating system file and the current version of the operating system file of the set-top box to be upgraded as the operating system upgrade data; Based on the target set-top box upgrade solution, the corresponding operating system upgrade data is sent to the set-top box to be upgraded, so that the set-top box to be upgraded upgrades the corresponding set-top box operating system based on the operating system upgrade data to upgrade to the target version; The step of analyzing the target set-top box upgrade solution corresponding to the set-top box to be upgraded based on the set-top box operation data and the user behavior data includes: Obtaining sample set-top box operation data, sample user behavior data, and set-top box upgrade solution labels, and training a candidate solution prediction network based on the sample set-top box operation data, the sample user behavior data, and the set-top box upgrade solution labels to obtain a target solution prediction network, wherein the target solution prediction network is a neural network; Utilizing the target solution prediction network, analyzing the set-top box operation data and the user behavior data, and obtaining a target set-top box upgrade solution corresponding to the set-top box to be upgraded; The step of using the target solution prediction network to analyze the set-top box operation data and the user behavior data to obtain a target set-top box upgrade solution corresponding to the set-top box to be upgraded includes: Using the first branch network included in the target solution prediction network, performing semantic feature mining on the set-top box operation data, and outputting set-top box operation features corresponding to the set-top box operation data; Using the second branch network included in the target solution prediction network, the user behavior data is mined for semantic features, and the user behavior features corresponding to the user behavior data are output, wherein the mining depth in the first branch network has multiple levels, so that the set-top box operation features include multiple levels of set-top box operation sub-features, and the mining depth in the second branch network has multiple levels, so that the user behavior features include multiple levels of user behavior sub-features, and the multiple levels of set-top box operation sub-features correspond to the multiple levels of user behavior sub-features one by one; Using the association fusion subnetwork included in the target solution prediction network, the set-top box operation features including multiple levels of set-top box operation sub-features and the user behavior features including multiple levels of user behavior sub-features are associated with significant features and fused to output target features; Utilizing the solution prediction subnetwork included in the target solution prediction network, analyzing the target features, and outputting a target set-top box upgrade solution corresponding to the set-top box to be upgraded; The step of using the first branch network included in the target solution prediction network to perform semantic feature mining on the set-top box operation data and outputting the set-top box operation features corresponding to the set-top box operation data includes: Using a first first deep mining unit in a first branch network included in the target solution prediction network, deep mining is performed on the set-top box operation embedding features corresponding to the set-top box operation data, and outputting the set-top box operation deep features corresponding to the first first deep mining unit; Using each first deep mining unit other than the first first deep mining unit in the first branch network, segment the set-top box operation depth feature corresponding to the previous first deep mining unit to form a corresponding plurality of local set-top box operation depth features, and based on the feature size of the set-top box operation depth feature, expand each local set-top box operation depth feature to obtain a corresponding plurality of extended set-top box operation depth features, and respectively perform deep mining on each of the extended set-top box operation depth features, and superimpose the features output by the deep mining to output the set-top box operation depth feature corresponding to the first deep mining unit; According to the hierarchical relationship between the first deep mining units, the set-top box operation deep features corresponding to each of the first deep mining units are respectively determined as set-top box operation sub-features of the corresponding level to obtain a set-top box operation feature including set-top box operation sub-features of multiple levels.

2. The set-top box upgrade management and control method according to claim 1, characterized in that: The step of using the second branch network included in the target solution prediction network to perform semantic feature mining on the user behavior data and outputting user behavior features corresponding to the user behavior data includes: Using the first second deep mining unit in the second branch network included in the target solution prediction network, deep mining is performed on the user behavior embedding features corresponding to the user behavior data, and the user behavior deep features corresponding to the first second deep mining unit are output; Using each second deep mining unit other than the first second deep mining unit in the second branch network, the user behavior deep feature corresponding to the previous second deep mining unit is segmented to form a corresponding plurality of local user behavior deep features, and based on the feature size of the user behavior deep feature, each local user behavior deep feature is expanded to obtain a corresponding plurality of expanded user behavior deep features, and each of the expanded user behavior deep features is deep mined respectively, and the features output by the deep mining are superimposed to output the user behavior deep feature corresponding to the second deep mining unit; According to the hierarchical relationship between the second deep mining units, the user behavior deep features corresponding to each of the second deep mining units are respectively determined as user behavior sub-features of the corresponding level to obtain user behavior features including user behavior sub-features of multiple levels.

3. The set-top box upgrade management and control method according to claim 1, characterized in that: The step of using the association fusion subnetwork included in the target solution prediction network to perform association mining and fusion of significant features on the set-top box operation sub-features including multiple levels of the set-top box operation features and the user behavior sub-features including multiple levels of the user behavior features, and outputting the target features, comprises: For each level of the association fusion unit in the association fusion subnetwork included in the target solution prediction network, using the association fusion unit, based on the set-top box operation subfeatures of the corresponding level, the user behavior subfeatures of the corresponding level are mined for significant features, so that significant features associated with the set-top box operation subfeatures in the user behavior subfeatures are mined, and a first associated significant feature corresponding to the association fusion unit is obtained; and based on the user behavior subfeatures of the corresponding level, the set-top box operation subfeatures of the corresponding level are mined for significant features, so that significant features associated with the user behavior subfeatures in the set-top box operation subfeatures are mined, and a second associated significant feature corresponding to the association fusion unit is obtained; For each level of the associated fusion unit, using the associated fusion unit, the set-top box operation sub-feature, the user behavior sub-feature, the first associated significant feature and the second associated significant feature of the level corresponding to the associated fusion unit are superimposed to form a corresponding target sub-feature; The target sub-features corresponding to the associated fusion units of each level are weighted and fused to output the corresponding target features. In the process of weighted fusion, the weight coefficients corresponding to the target sub-features have a positive correlation with the corresponding levels.

4. The set-top box upgrade management and control method according to any one of claims 1 to 3, characterized in that: The step of acquiring sample set-top box operation data, sample user behavior data and set-top box upgrade solution labels, and training a candidate solution prediction network based on the sample set-top box operation data, the sample user behavior data and the set-top box upgrade solution labels to obtain a target solution prediction network includes: Obtaining sample set-top box operation data, sample user behavior data, and a set-top box upgrade solution label, wherein the set-top box upgrade solution label is used to reflect the corresponding actual set-top box upgrade solution; Using the first branch network included in the candidate solution prediction network, performing semantic feature mining on the sample set-top box operation data, and outputting sample set-top box operation features corresponding to the sample set-top box operation data; Using the second branch network included in the candidate solution prediction network, performing semantic feature mining on the sample user behavior data, and outputting sample user behavior features corresponding to the sample user behavior data; Using the association fusion sub-network included in the candidate solution prediction network, the sample set-top box operation features including multiple levels of sample set-top box operation sub-features and the sample user behavior features including multiple levels of sample user behavior sub-features are associated with significant features and fused to output sample target features; Utilizing the solution prediction subnetwork included in the candidate solution prediction network, analyzing the sample target features, and outputting a corresponding sample set-top box upgrade solution; Based on the difference between the sample set-top box upgrade solution and the set-top box upgrade solution label, the network parameters of the candidate solution prediction network are updated until the difference converges or the number of updates reaches a preset number, thereby obtaining a corresponding target solution prediction network.

5. A set-top box upgrade control device, characterized in that: include: A data collection module, used to collect set-top box operation data corresponding to the set-top box to be upgraded and user behavior data of the set-top box user corresponding to the set-top box to be upgraded, wherein the set-top box operation data is used to reflect the abnormal operation of the set-top box to be upgraded, and the user behavior data is used to reflect the use behavior of the set-top box user for the set-top box to be upgraded; A solution analysis module, configured to analyze a target set-top box upgrade solution corresponding to the set-top box to be upgraded based on the set-top box operation data and the user behavior data, wherein the target set-top box upgrade solution belongs to a first set-top box upgrade solution or a second set-top box upgrade solution, the first set-top box upgrade solution refers to using all data of the target version of the operating system file as the operating system upgrade data, and the second set-top box upgrade solution refers to using the difference data between the target version of the operating system file and the current version of the operating system file of the set-top box to be upgraded as the operating system upgrade data; A system upgrade module, configured to send corresponding operating system upgrade data to the set-top box to be upgraded based on the target set-top box upgrade solution, so that the set-top box to be upgraded upgrades the corresponding set-top box operating system based on the operating system upgrade data to upgrade to the target version; Wherein, analyzing the target set-top box upgrade solution corresponding to the set-top box to be upgraded based on the set-top box operation data and the user behavior data includes: Obtaining sample set-top box operation data, sample user behavior data, and set-top box upgrade solution labels, and training a candidate solution prediction network based on the sample set-top box operation data, the sample user behavior data, and the set-top box upgrade solution labels to obtain a target solution prediction network, wherein the target solution prediction network is a neural network; Utilizing the target solution prediction network, analyzing the set-top box operation data and the user behavior data, and obtaining a target set-top box upgrade solution corresponding to the set-top box to be upgraded; The step of using the target solution prediction network to analyze the set-top box operation data and the user behavior data to obtain a target set-top box upgrade solution corresponding to the set-top box to be upgraded includes: Using the first branch network included in the target solution prediction network, performing semantic feature mining on the set-top box operation data, and outputting set-top box operation features corresponding to the set-top box operation data; Using the second branch network included in the target solution prediction network, the user behavior data is mined for semantic features, and the user behavior features corresponding to the user behavior data are output, wherein the mining depth in the first branch network has multiple levels, so that the set-top box operation features include multiple levels of set-top box operation sub-features, and the mining depth in the second branch network has multiple levels, so that the user behavior features include multiple levels of user behavior sub-features, and the multiple levels of set-top box operation sub-features correspond to the multiple levels of user behavior sub-features one by one; Using the association fusion subnetwork included in the target solution prediction network, the set-top box operation features including multiple levels of set-top box operation sub-features and the user behavior features including multiple levels of user behavior sub-features are associated with significant features and fused to output target features; Utilizing the solution prediction subnetwork included in the target solution prediction network, analyzing the target features, and outputting a target set-top box upgrade solution corresponding to the set-top box to be upgraded; The method of using the first branch network included in the target solution prediction network to perform semantic feature mining on the set-top box operation data and outputting the set-top box operation features corresponding to the set-top box operation data includes: Using a first first deep mining unit in a first branch network included in the target solution prediction network, deep mining is performed on the set-top box operation embedding features corresponding to the set-top box operation data, and outputting the set-top box operation deep features corresponding to the first first deep mining unit; Using each first deep mining unit other than the first first deep mining unit in the first branch network, segment the set-top box operation depth feature corresponding to the previous first deep mining unit to form a corresponding plurality of local set-top box operation depth features, and based on the feature size of the set-top box operation depth feature, expand each local set-top box operation depth feature to obtain a corresponding plurality of extended set-top box operation depth features, and respectively perform deep mining on each of the extended set-top box operation depth features, and superimpose the features output by the deep mining to output the set-top box operation depth feature corresponding to the first deep mining unit; According to the hierarchical relationship between the first deep mining units, the set-top box operation deep features corresponding to each of the first deep mining units are respectively determined as set-top box operation sub-features of the corresponding level to obtain a set-top box operation feature including set-top box operation sub-features of multiple levels.

6. 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 upgrade management and control method described in any one of claims 1-4.

7. 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 upgrade management and control method described in any one of claims 1 to 4 is executed.

Images