Special mode recommendation method and device, computer program product and software system

Abstract

The invention provides a recommendation method and device for a special mode, a computer program product and a software system.The method comprises the steps that a recommendation decision-making tree of the special mode is established, and the recommendation decision-making tree comprises a plurality of scheme branches of the special mode; acquiring user behavior information of a plurality of clients, matching the user behavior information according to the recommendation decision tree, recommending special modes corresponding to scheme branches matched with the user behavior information to the clients, and acquiring recommendation results of the special modes; training a neural network according to the multiple groups of user behavior information and the corresponding recommendation results to obtain a special mode recommendation model; obtaining current user behavior information of the current client, and inputting the current user behavior information into the special mode recommendation model to obtain a special mode recommendation scheme; and according to the recommendation scheme, recommending the special mode corresponding to the recommendation scheme to the current client or not recommending the special mode to the current client, thereby solving the problem of poor user experience caused by indiscriminate recommendation of the special mode.

Description

Technical Field

[0001] The present invention relates to the field of software technology, and in particular to a method, device, computer program product and software system for recommending a special mode. Background Art

[0002] Special software modes, such as elderly care mode, youth mode, and visually impaired mode, are important means for software to meet the needs of special users and improve user experience. However, due to the small number of special user groups, special software modes are not widely used by software users, resulting in the switches of such special modes being often relatively hidden. Special groups usually cannot easily access special software modes.

[0003] Currently, some of the software's special mode switch entrances are located in the software settings or software usage guide, which is not convenient for special users to obtain. Some of them will be pushed indiscriminately through pop-up windows, which is easy to cause invalid recommendations and reduce the user experience of users who do not need special modes. Summary of the invention

[0004] The main purpose of the present application is to provide a method, device, computer program product and software system for recommending a special mode, so as to at least solve the problem in the prior art of indiscriminately recommending special modes resulting in poor user experience.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for recommending a special mode is provided, comprising: establishing a recommendation decision tree for a special mode, the recommendation decision tree comprising multiple solution branches of the special mode, the special mode being a specific functional mode developed for a specific group of people; obtaining user behavior information of multiple clients, and matching the user behavior information according to the recommendation decision tree, recommending the special mode corresponding to the solution branch matched with the user behavior information to the client, and obtaining a recommendation result of the special mode, the user behavior information being the operation behavior information of the target software of the client; training a neural network according to multiple groups of the user behavior information and the corresponding recommendation results to obtain a special mode recommendation model; obtaining the current user behavior information of the current client, inputting the current user behavior information into the special mode recommendation model to obtain a recommendation solution for the special mode; and according to the recommendation solution, recommending the special mode corresponding to the recommendation solution to the current client or not recommending the special mode to the current client.

[0006] Optionally, establishing a recommendation decision tree for a special mode includes: obtaining multiple scenarios applicable to the special mode, the scenarios being working conditions that satisfy at least one condition; establishing corresponding solution branches based on the multiple scenarios, one condition corresponding to one node of the solution branch; and generating the recommendation decision tree based on multiple solution branches.

[0007] Optionally, the user behavior information is matched according to the recommendation decision tree, and the special mode corresponding to the solution branch matching the user behavior information is recommended to the client, including: when the average time consumed for a single operation of the user behavior information is greater than a predetermined average time consumed and the operation hand speed of the user behavior information is less than a predetermined operation hand speed, determining that the user behavior information is successfully matched with the solution branch of the respect and care for the elderly mode, the operation hand speed is the number of operations within a unit time length, and the respect and care for the elderly mode is one of the special modes; and recommending the respect and care for the elderly mode to the client.

[0008] Optionally, the user behavior information is matched according to the recommendation decision tree, and the special mode corresponding to the solution branch that matches the user behavior information is recommended to the client, including: when the user behavior information fails to match all the solution branches of the recommendation decision tree, the special mode is not recommended to the client, and the user behavior information of the client is re-recommended.

[0009] Optionally, obtaining recommendation results corresponding to the user behavior information includes: in response to an operation of accepting the recommendation, determining the special mode of accepting the recommendation; in response to an operation of rejecting the recommendation, determining the special mode of not accepting the recommendation; obtaining recommendation results corresponding to the special mode, the recommendation results including the special mode of accepting the recommendation and the special mode of not accepting the recommendation.

[0010] Optionally, a neural network is trained according to multiple groups of the user behavior information and the corresponding recommendation results to obtain a special pattern recommendation model, including: organizing the multiple groups of the user behavior information and the corresponding recommendation results into multiple groups of training data, each group of the training data including a group of the user behavior information and the corresponding recommendation results; and training the neural network with the multiple groups of training data until the accuracy of the recommendation results of the neural network is greater than a predetermined threshold, thereby obtaining the special pattern recommendation model.

[0011] Optionally, after recommending the special mode corresponding to the recommendation scheme to the current client or not recommending the special mode to the current client according to the recommendation scheme, the method also includes: obtaining the recommendation result corresponding to the recommendation scheme; combining the current user behavior information and the recommendation result corresponding to the recommendation scheme into new training data; and using the new training data to continue training the special mode recommendation model.

[0012] According to another aspect of the present application, a recommendation device for a special mode is provided, comprising: an establishment unit, used to establish a recommendation decision tree for the special mode, the recommendation decision tree comprising multiple solution branches of the special mode, the special mode being a specific functional mode developed for a specific group of people; a matching unit, used to obtain user behavior information of multiple clients, and match the user behavior information according to the recommendation decision tree, recommend the special mode corresponding to the solution branch matched with the user behavior information to the client, and obtain a recommendation result of the special mode, wherein the user behavior information is the operation behavior information of the target software of the client; a first training unit, used to train a neural network according to multiple groups of the user behavior information and the corresponding recommendation results to obtain a special mode recommendation model; an analysis unit, used to obtain the current user behavior information of the current client, input the current user behavior information into the special mode recommendation model, and obtain a recommendation solution for the special mode; a recommendation unit, used to recommend the special mode corresponding to the recommendation solution to the current client or not recommend the special mode to the current client according to the recommendation solution.

[0013] According to another aspect of the present application, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, any one of the methods described above is implemented.

[0014] According to another aspect of the present application, a software system is provided, comprising: software, a server, one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the described methods.

[0015] By applying the technical solution of the present application, in the above-mentioned special mode recommendation method, a recommendation decision tree is first used to determine whether to recommend the special mode, so as to obtain the recommendation result of the special mode and improve the success rate of the recommendation. By repeating this process multiple times, multiple groups of user behavior information and corresponding recommendation results can be obtained as training data, and the neural network is trained to obtain a special mode recommendation model. Then, the trained special mode recommendation model is used instead of the decision tree to recommend the special mode, thereby further improving the success rate of the recommendation. Compared with the prior art in which recommendations are made to all users, the recommendations of the present application are more targeted, have a high success rate, and provide a good user experience, thereby solving the problem of indiscriminate recommendation of special modes in the prior art leading to poor user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A hardware structure block diagram of a mobile terminal for executing a recommendation method for a special mode provided in an embodiment of the present application is shown;

[0017] Figure 2 A schematic flow chart of a recommendation method for a special mode provided according to an embodiment of the present application is shown;

[0018] Figure 3 A schematic flow chart of another special mode recommendation method provided according to an embodiment of the present application is shown;

[0019] Figure 4 A structural block diagram of a recommendation device in a special mode provided according to an embodiment of the present application is shown.

[0020] The above drawings include the following reference numerals:

[0021] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0022] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] In order to enable those skilled in the art to better understand the solution of the present application, 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. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] As introduced in the background technology, the indiscriminate recommendation of special modes in the prior art leads to poor user experience. To solve this technical problem, the embodiments of the present application provide a method, device, computer program product and software system for recommending a special mode.

[0026] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0027] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a recommendation method of a special mode of an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0028] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as computer programs corresponding to the recommended methods of the special mode in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, that is, the above-mentioned method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0029] In this embodiment, a recommended method for a special mode running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] Figure 2 FIG. 1 is a flowchart of a method for recommending a special mode according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0031] Step S201, establishing a recommendation decision tree for a special mode, wherein the recommendation decision tree includes a plurality of solution branches for special modes, and the special modes are specific functional modes developed for specific groups of people;

[0032] Step S202, obtaining user behavior information of multiple clients, matching the user behavior information according to the recommendation decision tree, recommending the special mode corresponding to the solution branch matched by the user behavior information to the client, and obtaining the recommendation result of the special mode, wherein the user behavior information is the operation behavior information of the target software of the client;

[0033] Step S203, training a neural network according to the plurality of sets of the user behavior information and the corresponding recommendation results to obtain a special mode recommendation model;

[0034] Step S204, obtaining the current user behavior information of the current client, inputting the current user behavior information into the special mode recommendation model, and obtaining a recommendation scheme for the special mode;

[0035] Step S205: According to the recommendation scheme, the special mode corresponding to the recommendation scheme is recommended to the current client or the special mode is not recommended to the current client.

[0036] In the above-mentioned special mode recommendation method, a recommendation decision tree is first used to determine whether to recommend the special mode, so as to obtain the recommendation result of the special mode and improve the success rate of the recommendation. By repeating this many times, multiple groups of user behavior information and corresponding recommendation results can be obtained as training data, and the neural network is trained to obtain a special mode recommendation model. Then, the trained special mode recommendation model is used instead of the decision tree to recommend the special mode, thereby further improving the success rate of the recommendation. Compared with the prior art in which all users are recommended, the recommendation of this application is more targeted, has a high success rate, and has a good user experience, which solves the problem of indiscriminate recommendation of special modes in the prior art, resulting in poor user experience.

[0037] In order to construct a recommendation decision tree, in an optional implementation, the above step S201 includes:

[0038] Step S2011, obtaining multiple scenarios applicable to the above special mode, where the above scenario is a working condition that satisfies at least one condition;

[0039] Step S2012, establishing corresponding solution branches according to the multiple scenarios, where one condition corresponds to one node of the solution branch;

[0040] Step S2013, generating the above-mentioned recommendation decision tree according to the multiple above-mentioned solution branches.

[0041] In the above implementation, the special modes of the software include elderly care mode, youth mode, visually impaired mode, etc., each of which has corresponding conditions. Satisfying a combination of conditions is the scenario where the above special mode is applicable. There can be multiple combinations of conditions. One condition in the combination of conditions establishes a node and forms a solution branch. The solution branches established by all the condition combinations form a recommended decision tree, which can be used to determine which special mode is applicable.

[0042] In order to accurately recommend the elderly care model, in an optional implementation, the above step S202 includes:

[0043] Step S2021, when the average time taken for a single operation of the user behavior information is greater than a predetermined average time taken and the operation hand speed of the user behavior information is less than a predetermined operation hand speed, it is determined that the user behavior information successfully matches the above scheme branch of the respect for the elderly care mode, the above operation hand speed is the number of operations within a unit time length, and the respect for the elderly care mode is one of the above special modes;

[0044] Step S2022, recommending the elderly care mode to the client.

[0045] In the above implementation, if the user's operating speed is less than 6 times / minute, it is considered that the user may need a special mode, and if the user takes more than 10 seconds to complete a certain operation, it is considered that the user is more likely to use the elderly care mode than the normal mode, and the system can recommend the elderly care mode to the user.

[0046] In order to ensure user experience, in an optional implementation, the above step S202 further includes:

[0047] Step S2023: When the user behavior information fails to match all the solution branches of the recommendation decision tree, the special mode is not recommended to the client, and the user behavior information of the client is refreshed.

[0048] In the above implementation, the enterprise server judges the uploaded user behavior information based on the decision tree algorithm to determine whether a special mode needs to be recommended to the user at present. If the match fails, the server does not make a recommendation, and the client software continues to track the user's operation behavior to avoid recommending special modes to inappropriate people and ensure user experience.

[0049] In order to improve flexibility, in an optional implementation, the above step S202 further includes:

[0050] Step S2024, in response to the operation of accepting the recommendation, determining the above-mentioned special mode of accepting the recommendation;

[0051] Step S2025, in response to the operation of rejecting the recommendation, determining not to accept the recommended special mode;

[0052] Step S2026, obtaining recommendation results corresponding to the above-mentioned special modes, wherein the above-mentioned recommendation results include the above-mentioned special modes that accept the recommendation and the above-mentioned special modes that do not accept the recommendation.

[0053] In the above implementation, if the match is successful, the server will recommend the corresponding special mode to the current client software user through a software pop-up window. The user can choose whether to use the special mode by himself / herself, and there is no forced switching of the special mode to ensure flexibility. The recommendation result is also recorded, that is, whether to accept the recommended special mode.

[0054] In order to achieve accurate recommendation, in an optional implementation, the above step S203 includes:

[0055] Step S2031, combining the multiple sets of user behavior information and the corresponding recommendation results into multiple sets of training data, each set of the training data including a set of user behavior information and the corresponding recommendation results;

[0056] Step S2032, using the above-mentioned multiple groups of training data to train the above-mentioned neural network until the accuracy of the above-mentioned recommendation results of the above-mentioned neural network is greater than a predetermined threshold, thereby obtaining the above-mentioned special mode recommendation model.

[0057] In the above implementation, after the server collects a large amount of user behavior information-special mode recommendation results, the first stage ends and the second stage begins. A large amount of data is the basic condition for R&D personnel to train computer models. R&D personnel build a "user behavior information-recommendation result" data set based on the large amount of user behavior and recommendation result data collected by the server in the first stage. R&D personnel build a computer neural network and train it based on the data in the data set until the accuracy of the above recommendation results of the above neural network is greater than the predetermined threshold, and obtain a computer network model that automatically recommends special modes, that is, a special mode recommendation model.

[0058] In order to further improve the accuracy of the recommendation, in an optional implementation, after recommending the special mode corresponding to the recommendation scheme to the current client or not recommending the special mode to the current client according to the recommendation scheme, the method further includes:

[0059] Step S301, obtaining the above-mentioned recommendation result corresponding to the above-mentioned recommendation scheme;

[0060] Step S302, combining the current user behavior information and the recommendation results corresponding to the recommendation scheme into new training data;

[0061] Step S303: continue training the special mode recommendation model using the new training data.

[0062] In the above implementation, the recommendation scheme and recommendation results of the special mode recommendation model are obtained to form new training data, and the special mode recommendation model is continuously iterated to continuously improve the accuracy of the recommendation.

[0063] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the recommended method of the special mode of the present application will be described in detail below in conjunction with specific embodiments.

[0064] This embodiment relates to a specific special mode recommendation method, such as Figure 3 As shown, the following steps are included:

[0065] 1. At the beginning of the first stage, the developer configures a recommendation decision tree for the special mode of the relevant software on the server. A decision tree is a model that uses a tree data structure to display decision rules and classification results. For example, if the user's operation speed is less than 6 times / minute, it is considered that the user may need a special mode, and if the user takes more than 10 seconds to complete an operation, it is considered that the user is more likely to use the elderly care mode than the normal mode, and the system can recommend the elderly care mode to the user.

[0066] 2. The client software tracks the customer's operating behavior and collects user behavior information related to the decision tree.

[0067] 3. The client software initiates a request to upload user behavior information to the enterprise server.

[0068] 4. The enterprise server uses the decision tree algorithm to judge the uploaded user behavior information and determine whether it is necessary to recommend a special mode to the user.

[0069] 5. If the match fails, the server will not make any recommendations, and the client software will continue to track the user's operation behavior.

[0070] 6. If the match is successful, the server will recommend the corresponding special mode to the current client software user through a software pop-up window, and the user can choose whether to use the special mode.

[0071] 7. The client software takes whether the user uses the recommended special mode as the recommendation result and uploads the recommendation result to the server.

[0072] 8. After the server collects a large amount of user behavior information - the results of special mode recommendations, the first stage ends and the second stage begins.

[0073] 9. A large amount of data is the basic condition for R&D personnel to train computer models. R&D personnel build a "user behavior information-recommendation result" data set based on the large amount of user behavior and recommendation result data collected by the server in the first phase.

[0074] 10. R&D personnel build a computer neural network, train it based on the data set, and obtain a computer network model that automatically recommends special patterns. This model is more accurate than the recommendation strategy configured by R&D personnel, avoiding overly absolute "one-size-fits-all" recommendations.

[0075] 11. Use trained computer network models instead of decision trees for special mode recommendations.

[0076] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0077] The embodiment of the present application also provides a recommendation device for a special mode. It should be noted that the recommendation device for a special mode of the embodiment of the present application can be used to execute the recommendation method for a special mode provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0078] The following introduces the recommended device of the special mode provided in the embodiment of the present application.

[0079] Figure 4 is a structural block diagram of a recommendation device according to a special mode of an embodiment of the present application. Figure 4 As shown, the device comprises:

[0080] An establishing unit 10 is used to establish a recommendation decision tree for a special mode, wherein the recommendation decision tree includes a plurality of solution branches for special modes, and the special mode is a specific functional mode developed for a specific group of people;

[0081] The matching unit 20 is used to obtain user behavior information of multiple clients, match the user behavior information according to the recommendation decision tree, recommend the special mode corresponding to the solution branch matched by the user behavior information to the client, and obtain the recommendation result of the special mode, wherein the user behavior information is the operation behavior information of the target software of the client;

[0082] A first training unit 30 is used to train a neural network according to the plurality of sets of user behavior information and the corresponding recommendation results to obtain a special mode recommendation model;

[0083] The analysis unit 40 is used to obtain the current user behavior information of the current client, input the current user behavior information into the special mode recommendation model, and obtain the recommendation scheme of the special mode;

[0084] The recommendation unit 50 is used to recommend the special mode corresponding to the recommendation scheme to the current client or not recommend the special mode to the current client according to the recommendation scheme.

[0085] In the above-mentioned special mode recommendation device, a recommendation decision tree is first used to determine whether to recommend the special mode, so as to obtain the recommendation result of the special mode and improve the success rate of the recommendation. By repeating this many times, multiple groups of user behavior information and corresponding recommendation results can be obtained as training data, and the neural network is trained to obtain a special mode recommendation model. Then, the trained special mode recommendation model is used instead of the decision tree to recommend the special mode, thereby further improving the success rate of the recommendation. Compared with the prior art in which all users are recommended, the recommendation of this application is more targeted, has a high success rate, and has a good user experience, which solves the problem of indiscriminate recommendation of special modes in the prior art leading to poor user experience.

[0086] In order to construct a recommendation decision tree, in an optional implementation, the building unit includes:

[0087] A first acquisition module is used to acquire multiple scenarios applicable to the special mode, where the scenario is a working condition that satisfies at least one condition;

[0088] An establishment module, used to establish corresponding solution branches according to the multiple scenarios, where one condition corresponds to one node of the solution branch;

[0089] A generation module is used to generate the above-mentioned recommendation decision tree according to the above-mentioned multiple solution branches.

[0090] In the above implementation, the special modes of the software include elderly care mode, youth mode, visually impaired mode, etc., each of which has corresponding conditions. Satisfying a combination of conditions is the scenario where the above special mode is applicable. There can be multiple combinations of conditions. One condition in the combination of conditions establishes a node and forms a solution branch. The solution branches established by all the condition combinations form a recommended decision tree, which can be used to determine which special mode is applicable.

[0091] In order to accurately recommend the elderly care model, in an optional implementation, the matching unit includes:

[0092] a determination module, configured to determine that the user behavior information successfully matches the scheme branch of the respect-for-the-elderly-care mode when the average time taken for a single operation of the user behavior information is greater than a predetermined average time taken and the operation hand speed of the user behavior information is less than a predetermined operation hand speed, the operation hand speed being the number of operations within a unit time, and the respect-for-the-elderly-care mode being one of the special modes;

[0093] The first recommendation module is used to recommend the above-mentioned elderly care model to the above-mentioned client.

[0094] In the above implementation, if the user's operating speed is less than 6 times / minute, it is considered that the user may need a special mode, and if the user takes more than 10 seconds to complete a certain operation, it is considered that the user is more likely to use the elderly care mode than the normal mode, and the system can recommend the elderly care mode to the user.

[0095] In order to ensure user experience, in an optional implementation manner, the matching unit further includes:

[0096] The second recommendation module is used for not recommending the special mode to the client and re-recommending the user behavior information of the client when the user behavior information fails to match all the solution branches of the recommendation decision tree.

[0097] In the above implementation, the enterprise server judges the uploaded user behavior information based on the decision tree algorithm to determine whether a special mode needs to be recommended to the user at present. If the match fails, the server does not make a recommendation, and the client software continues to track the user's operation behavior to avoid recommending special modes to inappropriate people and ensure user experience.

[0098] In order to improve flexibility, in an optional implementation manner, the matching unit further includes:

[0099] A first response module, configured to determine the above-mentioned special mode of accepting the recommendation in response to the operation of accepting the recommendation;

[0100] A second response module, configured to, in response to the operation of rejecting the recommendation, determine the above-mentioned special mode that is not to be recommended;

[0101] The second acquisition module is used to obtain the recommendation results corresponding to the above-mentioned special mode, and the above-mentioned recommendation results include the above-mentioned special mode that accepts the recommendation and the above-mentioned special mode that does not accept the recommendation.

[0102] In the above implementation, if the match is successful, the server will recommend the corresponding special mode to the current client software user through a software pop-up window. The user can choose whether to use the special mode by himself / herself, and there is no forced switching of the special mode to ensure flexibility. The recommendation result is also recorded, that is, whether to accept the recommended special mode.

[0103] In order to achieve accurate recommendation, in an optional implementation, the first training unit includes:

[0104] A combination module, used to combine the multiple sets of the user behavior information and the corresponding recommendation results into multiple sets of training data, each set of the training data includes a set of the user behavior information and the corresponding recommendation results;

[0105] The training module is used to train the above-mentioned neural network using the above-mentioned multiple groups of training data until the accuracy of the above-mentioned recommendation results of the above-mentioned neural network is greater than a predetermined threshold, thereby obtaining the above-mentioned special mode recommendation model.

[0106] In the above implementation, after the server collects a large amount of user behavior information-special mode recommendation results, the first stage ends and the second stage begins. A large amount of data is the basic condition for R&D personnel to train computer models. R&D personnel build a "user behavior information-recommendation result" data set based on the large amount of user behavior and recommendation result data collected by the server in the first stage. R&D personnel build a computer neural network and train it based on the data in the data set until the accuracy of the above recommendation results of the above neural network is greater than the predetermined threshold, and obtain a computer network model that automatically recommends special modes, that is, a special mode recommendation model.

[0107] In order to further improve the accuracy of the recommendation, in an optional implementation, the above device further includes:

[0108] An acquiring unit, configured to acquire the recommendation result corresponding to the recommendation scheme after recommending the special mode corresponding to the recommendation scheme to the current client or not recommending the special mode to the current client according to the recommendation scheme;

[0109] A generating unit, configured to combine the current user behavior information and the recommendation result corresponding to the recommendation scheme into the new training data;

[0110] The second training unit is used to continue training the special mode recommendation model by adopting the new training data.

[0111] In the above implementation, the recommendation scheme and recommendation results of the special mode recommendation model are obtained to form new training data, and the special mode recommendation model is continuously iterated to continuously improve the accuracy of the recommendation.

[0112] The recommendation device of the special mode includes a processor and a memory. The establishment unit, the matching unit, the first training unit, the analysis unit and the recommendation unit are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0113] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the problem of poor user experience caused by indiscriminate recommendation of special modes in the prior art can be solved by adjusting kernel parameters.

[0114] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0115] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the recommendation method of the special mode.

[0116] Specifically, the recommended methods for special modes include:

[0117] Step S201, establishing a recommendation decision tree for a special mode, wherein the recommendation decision tree includes a plurality of solution branches for special modes, and the special modes are specific functional modes developed for specific groups of people;

[0118] Step S202, obtaining user behavior information of multiple clients, matching the user behavior information according to the recommendation decision tree, recommending the special mode corresponding to the solution branch matched by the user behavior information to the client, and obtaining the recommendation result of the special mode, wherein the user behavior information is the operation behavior information of the target software of the client;

[0119] Step S203, training a neural network according to the plurality of sets of the user behavior information and the corresponding recommendation results to obtain a special mode recommendation model;

[0120] Step S204, obtaining the current user behavior information of the current client, inputting the current user behavior information into the special mode recommendation model, and obtaining a recommendation scheme for the special mode;

[0121] Step S205: According to the recommendation scheme, the special mode corresponding to the recommendation scheme is recommended to the current client or the special mode is not recommended to the current client.

[0122] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the recommended method of the special mode is executed when the program is run.

[0123] Specifically, the recommended methods for special modes include:

[0124] Step S201, establishing a recommendation decision tree for a special mode, wherein the recommendation decision tree includes a plurality of solution branches for special modes, and the special modes are specific functional modes developed for specific groups of people;

[0125] Step S202, obtaining user behavior information of multiple clients, matching the user behavior information according to the recommendation decision tree, recommending the special mode corresponding to the solution branch matched by the user behavior information to the client, and obtaining the recommendation result of the special mode, wherein the user behavior information is the operation behavior information of the target software of the client;

[0126] Step S203, training a neural network according to the plurality of sets of the user behavior information and the corresponding recommendation results to obtain a special mode recommendation model;

[0127] Step S204, obtaining the current user behavior information of the current client, inputting the current user behavior information into the special mode recommendation model, and obtaining a recommendation scheme for the special mode;

[0128] Step S205: According to the recommendation scheme, the special mode corresponding to the recommendation scheme is recommended to the current client or the special mode is not recommended to the current client.

[0129] An embodiment of the present invention provides a software system, which includes software, a server, a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, at least the following steps are implemented:

[0130] Step S201, establishing a recommendation decision tree for a special mode, wherein the recommendation decision tree includes a plurality of solution branches for special modes, and the special modes are specific functional modes developed for specific groups of people;

[0131] Step S202, obtaining user behavior information of multiple clients, matching the user behavior information according to the recommendation decision tree, recommending the special mode corresponding to the solution branch matched by the user behavior information to the client, and obtaining the recommendation result of the special mode, wherein the user behavior information is the operation behavior information of the target software of the client;

[0132] Step S203, training a neural network according to the plurality of sets of the user behavior information and the corresponding recommendation results to obtain a special mode recommendation model;

[0133] Step S204, obtaining the current user behavior information of the current client, inputting the current user behavior information into the special mode recommendation model, and obtaining a recommendation scheme for the special mode;

[0134] Step S205: According to the recommendation scheme, the special mode corresponding to the recommendation scheme is recommended to the current client or the special mode is not recommended to the current client.

[0135] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps:

[0136] Step S201, establishing a recommendation decision tree for a special mode, wherein the recommendation decision tree includes a plurality of solution branches for special modes, and the special modes are specific functional modes developed for specific groups of people;

[0137] Step S202, obtaining user behavior information of multiple clients, matching the user behavior information according to the recommendation decision tree, recommending the special mode corresponding to the solution branch matched by the user behavior information to the client, and obtaining the recommendation result of the special mode, wherein the user behavior information is the operation behavior information of the target software of the client;

[0138] Step S203, training a neural network according to the plurality of sets of the user behavior information and the corresponding recommendation results to obtain a special mode recommendation model;

[0139] Step S204, obtaining the current user behavior information of the current client, inputting the current user behavior information into the special mode recommendation model, and obtaining a recommendation scheme for the special mode;

[0140] Step S205: According to the recommendation scheme, the special mode corresponding to the recommendation scheme is recommended to the current client or the special mode is not recommended to the current client.

[0141] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0142] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0143] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0144] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0145] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0146] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0147] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0148] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0149] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0150] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0151] 1) In the special mode recommendation method of the present application, a recommendation decision tree is first used to determine whether to recommend a special mode, so as to obtain the recommendation result of the special mode and improve the success rate of the recommendation. By repeating this process multiple times, multiple groups of user behavior information and corresponding recommendation results can be obtained as training data. The neural network is trained to obtain a special mode recommendation model, and then the trained special mode recommendation model is used to replace the decision tree for special mode recommendation, thereby further improving the success rate of the recommendation. Compared with the prior art in which all users are recommended, the recommendation of the present application is more targeted, has a high success rate, and provides a good user experience, thereby solving the problem of poor user experience caused by indiscriminate recommendation of special modes in the prior art.

[0152] 2) In the special mode recommendation device of the present application, a recommendation decision tree is first used to determine whether to recommend the special mode, so as to obtain the recommendation result of the special mode and improve the success rate of the recommendation. By repeating this process multiple times, multiple groups of user behavior information and corresponding recommendation results can be obtained as training data, and the neural network is trained to obtain a special mode recommendation model. Then, the trained special mode recommendation model is used instead of the decision tree to recommend the special mode, thereby further improving the success rate of the recommendation. Compared with the prior art in which all users are recommended, the recommendation of the present application is more targeted, has a high success rate, and provides a good user experience, thereby solving the problem of indiscriminate recommendation of special modes in the prior art leading to poor user experience.

[0153] 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 special mode recommendation method, characterized in that: include: Establishing a recommendation decision tree for a special mode, wherein the recommendation decision tree includes a plurality of solution branches for special modes, wherein the special mode is a specific functional mode developed for a specific population; Obtaining user behavior information of multiple clients, matching the user behavior information according to the recommendation decision tree, recommending the special mode corresponding to the solution branch matched by the user behavior information to the client, and obtaining the recommendation result of the special mode, wherein the user behavior information is the operation behavior information of the target software of the client; Training a neural network according to the plurality of sets of user behavior information and the corresponding recommendation results to obtain a special mode recommendation model; Acquire current user behavior information of the current client, input the current user behavior information into the special mode recommendation model, and obtain a recommendation scheme for the special mode; According to the recommendation scheme, the special mode corresponding to the recommendation scheme is recommended to the current client or the special mode is not recommended to the current client.

2. The method according to claim 1, characterized in that Build a recommendation decision tree for a special model, including: Acquire multiple scenarios applicable to the special mode, where the scenarios are working conditions that meet at least one condition; Establish corresponding solution branches according to the multiple scenarios, where one condition corresponds to one node of the solution branch; The recommendation decision tree is generated according to the multiple solution branches.

3. The method according to claim 1, characterized in that Matching the user behavior information according to the recommendation decision tree and recommending the special mode corresponding to the solution branch matched by the user behavior information to the client includes: When the average time taken for a single operation of the user behavior information is greater than a predetermined average time taken and the operation hand speed of the user behavior information is less than a predetermined operation hand speed, it is determined that the user behavior information successfully matches the solution branch of the respect for the elderly care mode, the operation hand speed is the number of operations within a unit time, and the respect for the elderly care mode is one of the special modes; The elderly care model is recommended to the client.

4. The method according to claim 1, characterized in that: Matching the user behavior information according to the recommendation decision tree and recommending the special mode corresponding to the solution branch matched by the user behavior information to the client includes: In the case where the user behavior information fails to match all the solution branches of the recommendation decision tree, the special mode is not recommended to the client, and the user behavior information of the client is reset.

5. The method according to claim 1, characterized in that Obtaining the recommendation result corresponding to the user behavior information includes: In response to an operation of accepting the recommendation, determining the special mode of accepting the recommendation; In response to rejecting the recommended operation, determining not to accept the recommended special mode; The recommendation result corresponding to the special mode is obtained, and the recommendation result includes the special mode that accepts the recommendation and the special mode that does not accept the recommendation.

6. The method according to claim 1, characterized in that A neural network is trained according to the multiple sets of user behavior information and the corresponding recommendation results to obtain a special mode recommendation model, including: Combining multiple sets of the user behavior information and the corresponding recommendation results into multiple sets of training data, each set of the training data including a set of the user behavior information and the corresponding recommendation results; The neural network is trained using the multiple sets of training data until the accuracy of the recommendation results of the neural network is greater than a predetermined threshold, thereby obtaining the special mode recommendation model.

7. The method according to claim 6, characterized in that After recommending the special mode corresponding to the recommendation scheme to the current client or not recommending the special mode to the current client according to the recommendation scheme, the method further includes: Obtaining the recommendation result corresponding to the recommendation scheme; Combining the current user behavior information and the recommendation results corresponding to the recommendation scheme into new training data; The special mode recommendation model is continued to be trained using the new training data.

8. A recommendation device of a special mode, characterized in that: include: An establishing unit, used for establishing a recommendation decision tree for a special mode, wherein the recommendation decision tree includes a plurality of solution branches for special modes, wherein the special mode is a specific functional mode developed for a specific population; a matching unit, configured to obtain user behavior information of multiple clients, match the user behavior information according to the recommendation decision tree, recommend the special mode corresponding to the solution branch matched by the user behavior information to the client, and obtain a recommendation result of the special mode, wherein the user behavior information is operation behavior information of the target software of the client; A first training unit, configured to train a neural network according to a plurality of sets of user behavior information and corresponding recommendation results to obtain a special mode recommendation model; An analysis unit, used to obtain current user behavior information of the current client, input the current user behavior information into the special mode recommendation model, and obtain a recommendation scheme for the special mode; A recommendation unit is used to recommend the special mode corresponding to the recommendation scheme to the current client or not recommend the special mode to the current client according to the recommendation scheme.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A software system, characterized in that: include: Software, a server, one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of claims 1 to 7.

Images