Setting support device, setting support system, setting support method, and program

Abstract

To provide a setting support device, a setting support system, a setting support method, and a program allowing a user to easily resolve a setting problem.SOLUTION: Provided is a setting support device having: a setting problem acquisition unit that acquires a setting problem that is a problem related to the settings of a device; a device parameter acquisition unit that acquires a device parameter including the settings of the device; a calculation unit that calculates, by using a learning model, a corresponding parameter corresponding to the setting problem on the basis of the setting problem and the device parameter; and an output unit that outputs the corresponding parameter. Also provided are a setting support method and a program.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a setting support device, a setting support system, a setting support method, and a program that are capable of easily solving setting problems. [Background technology]

[0002] For devices that require user configuration, there is a large gap between the problem the user has, such as poor radio reception on a smartphone, and the solution, such as changing a specific wireless communication parameter on the device. The reason for this gap is that the user does not know which setting parameter needs to be selected and changed to solve the problem the device has. On the other hand, it is impossible to configure the device to solve the problem without taking into account the setting status within each device.

[0003] Patent Document 1 discloses the following estimation device, etc. The specification of the invention states that "the estimation unit 11 functions as an estimation means for estimating an evaluation score (a relative value of the communication quality after the base station parameter change to the communication quality before the base station parameter change) indicating the degree of improvement in communication quality when the base station parameter of the estimation target base station is changed from the setting before the change to the setting after the change, based on the communication quality measurement information and base station parameter setting information of the estimation target base station acquired by the information acquisition unit 13. Specifically, the communication quality measurement information and base station parameter setting information of the estimation target base station before the change in setting are input, and each evaluation score (a relative value of the communication quality after the base station parameter change to the communication quality before the change in base station parameter) after the setting change to the base station parameter set is calculated for each of six types of base station parameter sets Set0 to SetE described later." [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2020-178266 A Summary of the Invention [Problem to be solved by the invention]

[0005] The disclosures of the above-mentioned prior art documents are incorporated herein by reference. The following analysis has been carried out by the present inventors.

[0006] As described above, in the invention disclosed in Patent Document 1, the estimation unit estimates an evaluation score indicating the degree of improvement in communication quality after changing a base station parameter set, which is a combination of base station parameters, based on communication quality measurement information and base station parameter setting information, thereby identifying a base station parameter set that brings about an improvement in communication quality from among multiple parameter sets. In other words, it is possible to identify parameters whose settings should be changed.

[0007] However, the invention disclosed in Patent Document 1 does not accept problems that each device (base station) has, and does not provide a problem-solving means that allows a user to easily input a problem and output setting changes that correspond to the problem.

[0008] Therefore, in one aspect of the present invention, an object is to provide a setting support device, a setting support system, a setting support method, and a program that enable a user to easily solve a setting problem. [Means for solving the problem]

[0009] According to a first aspect of the present invention, there is provided a setting assistance device having a setting problem acquisition unit that acquires a setting problem which is a problem relating to the setting of a device, a device parameter acquisition unit that acquires device parameters including the settings of the device, a calculation unit that calculates corresponding parameters corresponding to the setting problem based on the setting problem and the device parameters, and an output unit that outputs the corresponding parameters.

[0010] According to a second aspect of the present invention, there is provided a setting support system including a setting device and a setting support server device, wherein the setting device has a setting problem acquisition unit that acquires a setting problem which is a problem related to setting, a device parameter acquisition unit that acquires device parameters including the setting of the setting device, and an input data transmission unit that transmits the setting problem and the device parameters, the setting support server device has a calculation unit that calculates corresponding parameters corresponding to the setting problem based on the setting problem and the device parameters using a learning model, and a corresponding parameter transmission unit that transmits the corresponding parameters, and the setting device further has an output unit that outputs the corresponding parameters.

[0011] According to a third aspect of the present invention, there is provided a setting support method which executes the following steps by a computer, the setting support method having the steps of: acquiring a setting problem which is a problem regarding device settings; acquiring device parameters including the device settings; calculating corresponding parameters corresponding to the setting problem based on the setting problem and the device parameters using a learning model; and outputting the corresponding parameters.

[0012] According to a fourth aspect of the present invention, there is provided a program for causing a computer to execute the steps of: acquiring a setting problem, which is a problem relating to device settings; acquiring device parameters including the device settings; calculating corresponding parameters corresponding to the setting problem based on the setting problem and the device parameters using a learning model; and outputting the corresponding parameters.

[0013] The program can be recorded on a computer-readable storage medium. The storage medium can be a non-transient medium such as a semiconductor memory, a hard disk, a magnetic recording medium, an optical recording medium, etc. The present invention can also be embodied as a computer program product. Effect of the Invention

[0014] According to each aspect of the present invention, it is possible to provide a setting support device, a setting support system, a setting support method, and a program that enable a user to easily solve a setting problem. [Brief description of the drawings]

[0015] [Figure 1] 1 is a block diagram showing an example of a configuration of a setting support device according to the present disclosure. [Diagram 2] 1 is a diagram showing an overview of processing in a setting support device according to the present disclosure. [Diagram 3] 1 is a block diagram showing an example of a configuration of a setting support device according to the present disclosure. [Figure 4] 10 is a flowchart for explaining an operation of the setting support device of the present disclosure. [Diagram 5] 2 is a block diagram showing an example of a hardware configuration of a setting assistance device according to the present disclosure. FIG. [Figure 6] 1 is a block diagram showing an example of a configuration of a setting support device according to the present disclosure. [Figure 7] 10 is a flowchart for explaining an operation of the setting support device of the present disclosure. [Figure 8] FIG. 2 is a diagram showing an overview of the processing of the setting support system of the present disclosure. [Figure 9] 4 is a flowchart for explaining the operation of the setting support system of the present disclosure. [Figure 10] 13 is a flowchart for explaining the operation of the learning model update process after outputting corresponding parameters in the setting support system of the present disclosure. [Figure 11] FIG. 1 is a diagram showing an overview of an embodiment of a setting support system according to the present disclosure. [Figure 12] FIG. 1 illustrates an example of a configuration of a setting support system according to an embodiment of the present disclosure. [Figure 13] FIG. 13 is a diagram showing a learning data set in an embodiment of the setting support system of the present disclosure. [Figure 14] FIG. 2 is a sequence diagram for explaining the operation of an embodiment of the setting support system of the present disclosure. [Figure 15] 11 is a flowchart for explaining the operation during continuous learning of an embodiment of the setting support system of the present disclosure. [Figure 16] FIG. 13 is a diagram showing a configuration in an embodiment of the setting support system of the present disclosure when the system is completed within a wireless device. [Figure 17] A diagram showing a configuration in which only continuous learning is performed outside the wireless device in an embodiment of the setting support system of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] First, an outline of one embodiment will be described. Note that the reference numerals in the drawings are given to each element for convenience as an example to facilitate understanding, and the description of the outline is not intended to be limiting. In this disclosure, the drawings relate to one or more embodiments.

[0017] 1 is a block diagram showing an example of the configuration of a setting support device according to the present disclosure. The setting support device 10 according to the present disclosure includes a setting problem acquisition unit 11, a device parameter acquisition unit 12, a calculation unit 13, and an output unit 14.

[0018] The setting problem acquisition unit 11 acquires a setting problem that is a problem regarding the setting of a device. The device parameter acquisition unit 12 acquires device parameters including the settings of the device. The calculation unit 13 calculates corresponding parameters corresponding to the setting problem based on the setting problem and the device parameters using a learning model, and the output unit outputs the corresponding parameters.

[0019] In this way, the setting assistance device disclosed herein accepts setting problems in the device to be supported from the user (for example, in the case of a communication device, audio is interrupted, noise is introduced, etc.), and then acquires device parameters, which are the current setting parameters of the device. Based on the setting problem and the device parameters, a corresponding parameter, which is a setting parameter corresponding to the setting problem, can be calculated and output using a learning model. Therefore, even a user with little knowledge about device settings, such as an end user, can input a setting problem to the device and learn the corresponding parameter that supports solving the setting problem.

[0020] [First embodiment] [Processing Overview] FIG. 2 is a diagram for illustrating an overview of the processing in the setting support device of the present disclosure. As shown in this diagram, there are a setting support device 10, a user 1, and a device 2 to be supported (hereinafter, a target device 2). The target device 2 and the setting support device 10 may be integrated or may be separate devices. The user 1 is a user of the target device 2. The setting support device 10 acquires a setting problem for the target device 2 from the user 1 in natural language. The setting support device 10 also acquires setting parameters Sp of the device related to the setting problem from the target device 2. The setting support device 10 uses the learning model 3-5 to calculate a corresponding parameter Sa corresponding to the acquired setting problem. The number of elements of the acquired setting parameter Sp and the calculated corresponding parameter Sa may be different (i.e., n ≠ m may be used in FIG. 2).

[0021] The learning model 3-5 performs learning by inputting the corresponding parameters as a teacher signal, a setting problem in natural language, and the setting parameters of the device related to the setting problem. Note that the example in Fig. 2 shows a schematic representation of a neural network model, and the number of elements in the model (shown by circles) and the mode of coupling between elements (shown by wires between elements) are not limited to those shown in Fig. 2.

[0022] [Device configuration] 3 is a block diagram showing an example of the configuration of the setting support device 10 of the present disclosure. As shown in this figure, the setting support device 10 of the present disclosure includes a setting problem acquisition unit 11, a device parameter acquisition unit 12, a calculation unit 13, an output unit 14, and a learning model generation unit 15.

[0023] The setting problem acquisition unit 11 acquires a setting problem that is a problem regarding the setting of the device. In the case of a communication device, a "setting problem" is a sentence, word, phrase, etc. that indicates an inconvenient phenomenon on the user side, such as "audio is interrupted," "audio is distorted," or "noise is introduced." The setting support device 10 of the present disclosure executes the following process to solve this setting problem, and calculates and outputs corresponding parameters as a solution. As described above, this unit may acquire the setting problem in natural language.

[0024] In addition, the posed problem acquisition unit 11 may convert the posed problem written in natural language into a vector representation to have similarity between the posed problems. To generate the vector representation, Word2Vec or Doc2Vec, which can convert a sentence of any length into a vector of a fixed length, may be used.

[0025] The device parameter acquisition unit 12 acquires device parameters including device settings. In Fig. 2, the device parameters indicating the current settings of the target device 2 are acquired. That is, the setting values ​​are acquired and appropriately converted into a form suitable for the calculation by the calculation unit 13 described later. Specifically, for example, the actual measured values ​​are normalized, and categorical data is converted using a quantification method such as one-hot encoding.

[0026] The calculation unit 13 calculates corresponding parameters corresponding to the set problem based on the set problem and the device parameters by using a learning model. The "learning model" is a model for calculating the corresponding parameters learned by the learning model generation unit 15 described below. The calculation means inputting the set problem and the values ​​of the device parameters into the learning model and obtaining the values ​​of the corresponding parameters which are the results of calculation by the learning model.

[0027] As shown in FIG. 2, a user 1 performs an input in a natural language, and a target device 2 inputs the setting parameters Sp and calculates corresponding parameters Sa using a learning model 3-5.

[0028] The output unit 14 outputs the corresponding parameters, and executes processes such as displaying the corresponding parameters on a display device such as a display, and transmitting the corresponding parameters to another device via communication.

[0029] The learning model generation unit 15 generates a learning model that is learned from learning data that uses a setting problem and device parameters as input data and the setting problem and corresponding parameters corresponding to the device parameters as teacher data. The learning models 3-5 in FIG. 2 are shown in a schematic diagram with a neural network in mind, but other supervised or unsupervised models can be adopted. Although three models, models 3-5, are illustrated in FIG. 2, they may be integrated into one model. That is, models 3-5 may be combined from the beginning to proceed with learning, or models 3 and 4 may be trained first, and then model 5 may be combined to proceed with learning.

[0030] For example, during learning, unsupervised learning may be performed in which text input as learning data is vectorized using the above-mentioned Doc2Vec or the vector representation of device parameters is subjected to dimensionality reduction using a dimensionality reduction algorithm such as principal component analysis. In this case, a principal component having a predetermined cumulative contribution rate may be selected, and the dimensionality-reduced learning data may be output and used as an input value for model 5 to retrain model 5.

[0031] In addition, the learning may be performed by providing the parameter values ​​themselves as training data, or by providing which parameters are related as training data. That is, the vector of the corresponding parameter Sa in FIG. 2, which is the calculation result of the calculation unit 13, may take the value of 0 or 1. In this case, the user can know which parameter to change as a setting item, instead of the parameter value.

[0032] [Explanation of operation] 4 is a flowchart for explaining the operation of the setting assistance device 10 of the present disclosure. As shown in this figure, when the setting assistance device 10 starts its operation, it accepts and acquires a setting problem from the user (step S41). Next, it acquires device parameters including device settings from the target device (step S42). Based on the setting problem and the device parameters, it calculates corresponding parameters corresponding to the setting problem using a learning model (step S43). Finally, it outputs the calculated corresponding parameters (step S44).

[0033] [Hardware configuration] Next, a description will be given of the hardware configuration of the setting support device according to the first embodiment. Fig. 5 is a block diagram showing an example of the hardware configuration of the setting support device 10 according to the first embodiment.

[0034] The setting support device 10 can be configured by an information processing device (computer) and has the configuration exemplified in Fig. 5. For example, the setting support device 10 includes a CPU (Central Processing Unit) 51, a memory 52, an input / output interface 53, and a NIC (Network Interface Card) 54 as a communication means, which are mutually connected by an internal bus 55.

[0035] However, the configuration shown in Fig. 5 is not intended to limit the hardware configuration of the devices constituting the setting support device 10. Each setting support device 10 may include hardware not shown, and may not include the input / output interface 53 as necessary. In addition, the number of CPUs and the like included in the setting support device 10 is not intended to be limited to the example shown in Fig. 5, and for example, each device may include multiple CPUs.

[0036] The memory 52 is a random access memory (RAM), a read only memory (ROM), or an auxiliary storage device (such as a hard disk).

[0037] The input / output interface 53 is a means for interfacing with a display device and an input device (not shown). The display device is, for example, a liquid crystal display, etc. The input device is, for example, a device that accepts user operations such as a keyboard and a mouse.

[0038] When calculating corresponding parameters, the functions of the setting assistance device 10 are realized by a setting problem acquisition program, which is a processing module, a device parameter acquisition program, a calculation program, an output program, and a group of parameters of a trained learning model stored in the memory 52, etc. When generating a learning model, the functions are realized by a learning model generation program and a data set consisting of input learning data and teacher data.

[0039] The above processing modules are realized, for example, by the CPU 51 executing the programs stored in the memory 52. ​​The programs can be updated by downloading them via a network or by using a storage medium storing the programs. The above processing modules may be realized by semiconductor chips. That is, it is only necessary to have some means for executing the functions performed by the above processing modules by some hardware and / or software.

[0040] [Hardware operation: learning] First, a learning model is generated in the setting assistance device 10. A learning model generation program is called from the memory 52 and is executed by the CPU 51. The program sequentially reads the learning data sets stored in the memory 52, and adjusts the parameters of the learning model using the input learning data and teacher data. The parameters may be adjusted using a loss function such as RSS (Residual Sum of Squares), an existing technology. If the model is a neural network model and has multiple layers, a method such as error propagation may be used.

[0041] [Hardware operation: Calculation time] After the learning is completed, in the setting assistance device 10, the setting problem acquisition program is called from the memory 52 and is executed by the CPU 51. The program acquires the setting problem via the input / output interface 53 and the NIC 54. If the setting problem is voice, a voice recognition process is executed here to convert the voice into text. The textual setting problem is vectorized using a program of the existing technology and temporarily stored in the memory 52. ​​Next, the device parameter acquisition program is called from the memory 52 and is executed by the CPU 51. The program acquires device parameters, which are setting parameters for the target device. Specifically, the program may send a request to the target device via the NIC 54 and acquire the parameters as a response. The acquired parameters are temporarily stored in the memory 52.

[0042] Next, the calculation program is called from memory 52 and is executed by CPU 51. This program reads the trained learning model stored in memory 52. ​​Next, the program executes calculation processing using the setting problem (vector) and device parameters (vector) temporarily stored in memory 52 as input. At this time, the input data is appropriately processed such as standardized. As a result of the calculation processing, the corresponding parameters (vector) are calculated. Next, the output program is called from memory 52 and is executed by CPU 51. This program outputs the corresponding parameters via NIC 54 and input / output interface 53.

[0043] [Effect description] As described above, the setting assistance device 10 of the present disclosure is capable of acquiring a setting problem that a user has with respect to a target device, and calculating corresponding parameters for solving the setting problem based on the setting problem and the device parameters of the target device. Therefore, it is possible to provide a setting assistance device, a setting assistance system, a setting assistance method, and a program that enable a user to easily perform optimal settings based on the output corresponding parameters.

[0044] [Second embodiment] In the second embodiment, based on the first embodiment, a setting support device is provided that is capable of updating an already learned learning model based on the determination result of whether or not the corresponding parameters have been reflected in the target device.

[0045] [Device configuration] 6 is a block diagram showing an example of the configuration of the setting support device 10 of the present disclosure. The setting support device 10 of the present disclosure includes a setting problem acquisition unit 11, a device parameter acquisition unit 12, a calculation unit 13, an output unit 14, and a learning model generation unit 15. These components have already been described in the above embodiment, so description thereof will be omitted. The setting support device 10 in this embodiment is characterized in that it further includes a judgment unit 16, and that the learning model generation unit updates the learning model according to the judgment result of the judgment unit 16.

[0046] The judgment unit 16 judges whether the corresponding parameters have been reflected in the device. The corresponding parameters calculated by the learning model and output by the output unit 14 are changed in setting by a user operation. Here, the judgment unit 16 compares the calculated and output corresponding parameters with the latest device parameters acquired by the device parameter acquisition unit 12, and judges whether they match in part or in whole. If the judgment result shows a match, the corresponding parameters are considered to have been reflected in the device parameters of the target device, and a trigger for updating the learning model is transmitted to the learning model generation unit 15.

[0047] The learning model generation unit 15 updates the learning model according to the judgment result of the judgment unit 16. Specifically, for example, when it is judged that the corresponding parameter is reflected as an apparatus parameter in the target apparatus as a result of the judgment, the learning model may be updated based on the corresponding parameter, the setting problem which is the input data from which the corresponding parameter was calculated, and the apparatus parameters. Specifically, so-called online learning may be performed using, for example, the setting problem, the apparatus parameters, and the calculated corresponding parameter. Here, if the weight between elements of the learning model is Wn, the value of the loss function is l, and the learning rate is α, then

number

[0048] [Explanation of operation] FIG. 7 is a flowchart for explaining the operation of the setting support device 10 of the present disclosure. The process from the start of the operation to the output of the corresponding parameters (steps S71 to S74, not shown) has already been explained in FIG. 4 (steps S41 to S44), so the description will be omitted. When the corresponding parameters are output, it is determined whether the corresponding parameters have been reflected in the device (step S75). If it is determined that the corresponding parameters have been reflected (step S75, Y), the learning model is updated based on the corresponding parameters determined to have been reflected in the device, the setting problem that is the input data from which the corresponding parameters were calculated, and the device parameters (step S76). If it is determined that the corresponding parameters have not been reflected (step S75, N), the series of processes is terminated.

[0049] [Effect description] In the setting assistance device 10 of the present disclosure, it is possible to update the learning model based on whether the outputted corresponding parameters are reflected in the device parameters. This makes it possible to generate a learning model that is more optimized for the setting problem, and to output more appropriate corresponding parameters to the user.

[0050] [Third embodiment] In the third embodiment, a setting support system including a setting device 20 and a setting support server device 30 will be described.

[0051] [Processing configuration] FIG. 8 is a diagram showing an overview of the processing of the setting support system of the present disclosure. As shown in this figure, the setting support system includes a setting device 20 and a setting support server device 30. The device to be set and the setting device 20 may be integrated or may be separate devices. The setting device 20 includes a setting problem acquisition unit 11, a device parameter acquisition unit 12, an output unit 14, a judgment unit 16, and an input data transmission unit 17. The setting support server device 30 includes a calculation unit 13, a learning model generation unit 15, and a corresponding parameter transmission unit 18. The setting support system of the present disclosure is characterized in that the setting device 20 includes an input data transmission unit 17, and the setting support server device 30 includes a corresponding parameter transmission unit 18. Other constituent elements have been described in the above embodiment, so description thereof will be omitted.

[0052] Here, in the setting support system of the present disclosure, a plurality of setting devices may be connected to one setting support server device 30 and may share a learning model.

[0053] The input data transmission unit 17 transmits the setting questions and device parameters acquired by the setting device 20 to the setting assistance server device 30.

[0054] The corresponding parameter transmission unit 18 transmits the corresponding parameters calculated by the setting assistance server device 30 to the setting device 20 .

[0055] [Explanation of operation] 9 is a flow chart for explaining the operation of the setting support system of the present disclosure. As shown in this figure, the setting device 20 acquires a setting problem (step S91). Next, device parameters are acquired (step S92). The acquired setting problem and device parameters are transmitted (step S93). After that, the setting support server device 30 calculates corresponding parameters corresponding to the setting problem based on the received setting problem and the device parameters using a learning model (step S94). The calculated corresponding parameters are transmitted (step S95). The setting device 20 receives this and outputs the corresponding parameters (step S96).

[0056] Fig. 10 is a flowchart for explaining the operation of the learning model update process after the corresponding parameters are output in the setting support system of the present disclosure. As shown in this figure, after the corresponding parameters are output in the setting device 20, it is determined whether the corresponding parameters are reflected in the device (step S1017). If it is determined that the corresponding parameters are reflected (step S1017, Y), the setting support server device 30 updates the learning model based on the corresponding parameters determined to be reflected in the device, the setting problem that is the input data from which the corresponding parameters were calculated, and the device parameters (step S1018). If it is determined that the corresponding parameters are not reflected (step 1017, N), the series of processes ends.

[0057] [Effect description] According to the setting support system of the present disclosure, it is possible to calculate corresponding parameters corresponding to a setting problem in cooperation with both the setting device 20 and the setting support server device 30. Since the calculation process of the corresponding parameters is centralized in the setting support server device 30, even when the processing capacity of the setting device 20 is limited, such as in a small mobile terminal, the setting device 20 can make an inquiry to the setting support server device and quickly process the parameters.

[0058] In addition, multiple setting devices 20 can be connected to the setting support server device 30, and by generating and updating a learning model between the multiple setting devices 20 and the setting support server device 30, it is possible to provide a more versatile learning model.

[0059] [Example] An embodiment of the setting support system of the present disclosure will be described below. The following is an embodiment of the setting support system in which the setting device is a wireless device.

[0060] [Outline of the embodiment] FIG. 11 is a diagram showing an overview of an embodiment of the setting support system of the present disclosure. As shown in this diagram, a user inquires of a wireless device (corresponding to a setting device) that the "line is unstable." At this time, band steering is in an OFF state as a device parameter in the wireless device. The wireless device transmits the user's inquiry (wireless quality problem) and the device parameters to an analysis server. The analysis server performs classification using a machine learning model and returns the result of the optimal setting to the wireless device. The wireless device presents the user with a setting in which band steering is ON as the optimal setting.

[0061] [Configuration of the embodiment] 12 is a diagram showing an example of the configuration of an embodiment of the setting support system of the present disclosure. As shown in this diagram, the setting support function of the setting support system of the present invention is mainly realized by the wireless device 101 and a machine learning model in the analysis server 201. Depending on the capacity of the machine learning model, it may be possible to operate even if it is incorporated into the wireless device 101.

[0062] There are six functions related to the invention in the wireless device 101, numbered 102 to 107. The natural language input function 102 accepts wireless quality problems from the user in a natural language format and transmits them to the analysis server 201 for classification. Note that in the case of character input using a screen, the user's input is transmitted directly to the analysis server 201, whereas in the case of voice input, the voice waveform is converted into a character format and then transmitted to the analysis server 201 in the character format.

[0063] The device parameter acquisition function 103 acquires the parameters of the wireless device (radio field strength, bandwidth, interference information, device settings, etc.) This acquired data is also sent to the analysis server 201 for classification.

[0064] The setting presentation function 104 presents to the user the contents of the optimal settings classified by the machine learning model and the wireless quality problems that are solved by the settings.

[0065] The setting selection / complementary input function 105 allows the user to select whether or not to reflect the presented setting contents in the device, and allows the user to input a small amount of complementary information (such as a password) as necessary.

[0066] The setting reflection function 106 reflects the optimum settings classified based on the received supplementary items.

[0067] The wireless communication quality acquisition function 107 has a function of acquiring the current wireless communication quality (communication stability, delay, packet loss, etc.) and the wireless quality before the setting was reflected from the past communication quality log. The acquired wireless communication quality is then transmitted to the continuous learning function 207 of the analysis server 201.

[0068] The main functions related to the invention in the analysis server 201 are the machine learning model 202 and the continuous learning function 207.

[0069] The internal structure of the machine learning model 202 is divided into four components, 203 to 206. The natural language processing module 203 accepts the user's wireless quality problem in natural language format, interprets its meaning, and encodes it into a format that is easy for machines to use. The equipment parameter encoding module 204 encodes the equipment parameters into a form that is easy for machines to use, such as numbers or vectors (one-hot encoding for categories, scaling for numbers, etc.). It must be decided in advance which equipment parameters to use. The integration module for both representations 205 inputs the outputs of the natural language processing module 203 and the equipment parameter encoding module 204, and integrates the two features.

[0070] The classification module 206 performs classification by inputting the outputs of the integration module 205 for both representations. In addition, multiple classification is performed by applying a softmax function to the fully connected layer. The number of classification targets must be determined in advance in the learning stage, and the format of the objective variable (O1 in FIG. 13) must also match this. Note that when the input and output of the machine learning model are expressed in this invention description, this refers to the input and output of the machine learning model 202.

[0071] The continuous learning function 207 feeds back the results of the user's use of the present invention and uses them for continuous learning.

[0072] Fig. 13 is a diagram showing the learning data set in the setting support system of the present disclosure. As shown in this figure, supervised learning is performed with two explanatory variables, the user's wireless quality problem E1 and the device parameter E2, and the optimal wireless device setting O1 as the objective variable. The configuration and correlation between them are described below.

[0073] The user's wireless quality problem E1 is part of the input data of the machine learning model of the present invention, and indicates the problems and improvement requests that the user has regarding wireless communication quality. These are accepted in a natural language format and input to the model as explanatory variables. The role of these variables is to enable the model to classify and propose settings that correspond to the user's specific quality improvement requests.

[0074] The device parameters E2 represent information about the wireless device (signal strength, bandwidth, device settings, etc.). These parameters are acquired by the wireless device and are used as input data for the machine learning model. The role of the device parameters E2 is to enable the model to classify and propose appropriate settings taking into account the current situation of the wireless device. This allows the model to present optimal settings for each individual user's environment.

[0075] The optimal wireless equipment setting O1 is the objective variable of the machine learning model, and represents the optimal setting of the wireless equipment to be selected based on the user's wireless quality problem E1 and the equipment parameters E2. The machine learning model classifies and predicts the optimal setting from these explanatory variables, and presents it to the user. The continuous learning is performed taking into consideration whether the user has reflected the presented setting and the change in wireless quality due to the reflection of the setting, but the basic configuration is the same.

[0076] Since there is a correlation between the explanatory variables and the objective variable, this will be explained. Regarding the correlation between the user's wireless quality problem E1 and the optimal wireless device setting O1, the wireless quality problem that the user has (such as a decrease in communication speed or a decrease in connection stability) directly affects the selection of the optimal wireless device setting. Since a setting is required to deal with a specific problem, it is considered that there is a correlation between the user's wireless quality problem E1 and the optimal setting O1.

[0077] Regarding the correlation between the device parameter E2 and the optimal wireless device setting O1, the device parameters (signal strength, bandwidth, current setting, etc.) that reflect the current state of the wireless device also affect the determination of the optimal wireless device setting. Since it is necessary to select an appropriate setting that adapts to the environment, it is considered that a correlation also exists between the device parameter E2 and the optimal setting O1.

[0078] These correlations allow the machine learning model to predict and estimate optimal wireless equipment settings from explanatory variables (user wireless quality problems and equipment parameters). As long as the training data set maintains the correlations, the model can make accurate and effective setting suggestions.

[0079] [Explanation of the operation of the embodiment] The flow of the entire function will be described with reference to Figures 12 and 14. Figure 14 is a sequence diagram for explaining the operation of the embodiment of the setting support system of the present disclosure. First, the wireless device uses the natural language input function 102 to acquire wireless quality problems that the user is having (step S1).

[0080] At the same time, the device parameter acquisition function 103 acquires the settings, state, etc. within the device (step S2).

[0081] Once the acquisition is complete, the data is sent to the analysis server 201. The acquired data is then input to a natural language processing module 203 and a device parameter encoding module 204, and the optimal settings are classified by a machine learning model 202 (step S3). The classification results are used by the setting presentation function 104, which presents an outline of the corresponding settings to the user. Note that since the classification results only indicate the optimal settings, the corresponding setting outlines and the like must be prepared in advance in the wireless device or the analysis server, and presented using the setting presentation function 104.

[0082] After the settings are presented, the setting selection / completion input function 105 is used to ask the user whether or not to reflect the settings (step S4).

[0083] If the user selects to reflect the presented settings, the user is prompted to input necessary information such as a password, and the settings are then reflected using the settings reflection function 106 (step S5).

[0084] Finally, the wireless communication quality before and after the setting is reflected and whether the presented setting has been reflected are sent as feedback to the analysis server 201 (step S6). The past communication quality is recorded in a past log or the like so that the wireless communication quality after the setting is reflected can be obtained. In this way, appropriate settings are presented to the user based on the user's wireless quality problem and device parameters.

[0085] Next, continuous learning will be described with reference to Fig. 15. Fig. 15 is a flowchart for explaining the operation during continuous learning of an embodiment of the setting support system of the present disclosure. Continuous learning is a mechanism for maintaining or improving accuracy by re-learning newly acquired data using some function. In the present invention, when a user reflects the presented optimal settings in a wireless device, a learning data set including the results is used for continuous learning (step S1501).

[0086] Next, based on the value acquired by the wireless communication quality acquisition function 107, an improvement value of 0 to 1 is calculated as the result of improvement of wireless communication quality. This is calculated for each element (delay, packet loss, etc.) expressing wireless communication quality (step S1502). If the improvement value is negative, it is set to 0, and the calculation of the improvement value is determined according to each element expressing wireless quality. For example, if the element ping [ms] expressing delay drops from 100 to 90, the improvement value for the latter will be higher than that for the latter drop from 30 to 20, and the improvement value is calculated according to the characteristics of the element.

[0087] Next, the average of the calculated multiple improvement values ​​(two in the case of only delay and packet loss) is calculated, and this score is used as the weight of the corresponding learning data set during continuous learning (step S1503). This enables the machine learning model to learn with a greater focus on factors that have a significant impact on wireless communication quality.

[0088] Finally, the user's wireless quality problem and device parameters are used as explanatory variables, the presented optimal settings as objective variables, and the calculated weights are used for continuous learning (step S1504). A concrete example will be presented. Consider a case where the user input is "wireless is unstable," the output is "band steering" and "change communication mode (e.g., turn IEEE802.11ax setting ON)," with values ​​of 0.55 and 0.45, respectively, and the band steering function is presented and reflected as a result. If the output is 0.6 and 0.4 after learning is performed with a weight of 0.1, then with a weight of 0.4, the output will be 0.7 and 0.3, which is more likely to present the "band steering function."

[0089] [Effect description] In the setting support system according to the embodiment of the present disclosure, by inputting wireless quality problems and presenting settings based on a machine learning model, it is possible to present appropriate settings to users who have no wireless knowledge. In addition, it is also possible to address individual user problems by using device parameters for machine learning predictions.

[0090] [Another Example 1] In the present invention, the results obtained from the wireless device are used on the analysis server, but depending on the capacity of the entire machine learning model, it is also possible to complete the process using only the wireless device (Figure 16), or to select to perform only the learning in a separate environment (Figure 17).

[0091] When the process is completed using only the wireless device, the machine learning model and continuous learning are embedded in the wireless device without using an analysis server, as shown in Figure 16. In this case, it is necessary to reduce the performance of the natural language module, reduce the number of settings to be classified, and reduce the number of internal parameters of the entire machine learning model. Furthermore, since larger computational resources are required when learning is performed, it is necessary to turn off other functions during times when the device is not in use, or to prepare a wireless device with high computational processing capabilities in the first place. In addition, since there is a shortage of learning data, it is difficult to improve accuracy through continuous learning.

[0092] When classifying within the wireless device and performing learning in a different environment, the machine learning model is incorporated into the wireless device as shown in Figure 17, and the continuous learning function is used on the analysis server. In this case, although not as much attention as above, it is necessary to pay attention to capacity and computational resources. Also, the machine learning model 202 after continuous learning can be updated by incorporating it into a firmware update.

[0093] [Another Example 2] In the present invention, when a user inputs a wireless quality problem, a setting corresponding to the problem is presented. If the input is a natural language that has nothing to do with wireless quality, a mechanism that can respond appropriately will be described as another embodiment 2.

[0094] The learning dataset is configured so that the machine learning model can respond appropriately even when the user inputs natural language content unrelated to wireless quality issues. Specifically, natural language inputs with content unrelated to wireless quality (e.g., weather information or general conversations) and the classification result "no appropriate settings" in that case are added to the learning dataset. By including such data in the learning dataset, the machine learning model responds appropriately to inputs unrelated to wireless quality issues and acquires the ability to determine "no appropriate settings." As a result, when the user inputs unrelated content, the model does not make setting suggestions, and it is possible to prevent unrelated setting changes.

[0095] The correlation between "No appropriate settings" and "Wireless quality problems" will now be explained. It can be said that there is a certain correlation between "No appropriate settings" and "Wireless quality problems". However, this correlation does not indicate a relationship in which the two directly affect each other, but rather an inverse relationship. Specifically, this means that the classification result of "No appropriate settings" is applied to natural language input that is not related to wireless quality problems. In other words, when "No appropriate settings" is selected, this indicates that the presence of wireless quality problems is low or has no relevance at all. Therefore, "No appropriate settings" and the presence of wireless quality problems have an inverse relationship with each other.

[0096] A part or all of the above disclosure may be described as follows, but is not limited to the following. [Appendix 1] This is as described above with respect to the setting assistance device according to the first aspect. [Appendix 2] The setting support device according to claim 1, further comprising a learning model generation unit that receives a setting problem and device parameters as input data and generates a learning model learned from learning data using the setting problem and corresponding parameters corresponding to the device parameters as teacher data, wherein the calculation unit calculates the corresponding parameters using the learning model. [Appendix 3] The setting support device according to claim 1 or 2, wherein the setting question acquisition unit acquires setting questions in a natural language. [Appendix 4] The setting support device of Appendix 3, which is dependent on Appendix 2, preferably comprises: the setting problem acquisition unit vectorizing the setting problem written in natural language; and the learning model generation unit vectorizing the setting problem. [Appendix 5] Preferably, the setting support device of Appendix 2 further comprises a judgment unit that judges whether the corresponding parameters have been reflected in the device, and the learning model generation unit updates the learning model according to the judgment result of the judgment unit. [Appendix 6] The learning model generation unit updates the learning model based on the corresponding parameters determined to be reflected in the device, the setting problems which are input data for calculating the corresponding parameters, and the device parameters, preferably according to the setting support device of Appendix 5. [Appendix 7] This is as described above in relation to the second aspect of the setting support system. [Appendix 8] The setting support system of Appendix 7, wherein the setting support server device further has a learning model generation unit that generates a learning model trained using learning data that uses a setting problem and device parameters as input data and corresponding parameters corresponding to the setting problem as teacher data, and the calculation unit calculates the corresponding parameters using the learning model. [Appendix 9] This is the same as the setting support method related to the third aspect described above. [Appendix 10] This is as per the program related to the fourth perspective mentioned above. [Appendix 11] The setting support device of Appendix 3, wherein the learning model calculation unit further uses a setting problem unrelated to the device parameters and corresponding parameters as input data, and generates a learning model learned from learning data using an output indicating that there is no appropriate setting as training data. Note that, like Supplementary Note 1, Supplementary Notes 9 and 10 can be expanded into Supplementary Notes 2 to 6.

[0097] The disclosures of the above cited patent documents and the like are incorporated herein by reference. Within the framework of the entire disclosure of the present invention (including the scope of claims), modifications and adjustments of the embodiments and examples are possible based on the basic technical ideas. Furthermore, within the framework of the entire disclosure of the present invention, various combinations and selections of the various disclosed elements (including each element of each claim, each element of each embodiment or example, each element of each drawing, etc.) are possible. In other words, the present invention naturally includes various modifications and corrections that a person skilled in the art would be able to make in accordance with the entire disclosure including the scope of claims and the technical ideas. In particular, with regard to the numerical ranges described in this specification, any numerical value or subrange included in the range should be interpreted as being specifically described even if not otherwise specified. [Explanation of symbols]

[0098] 1 :User 2: Target device 3-5: Model, learning model 10: Setting support device 11:Setting problem acquisition part 12: Equipment parameter acquisition section 13: Calculation section 14: Output section 15: Learning model generation unit 16: Judgment department 17: Input data transmission unit 18: Corresponding parameter transmission section 20: Setting device 30: Setting support server device 51: CPU 52: Memory 53: Input / Output Interface 54:NIC 55: Internal bus 101: Radio equipment 102: Natural language input function 103: Equipment parameter acquisition function 104: Setting suggestion function 105: Setting selection / completion input function 106: Setting reflection function 107: Wireless communication quality acquisition function 201: Analysis Server 202: Machine learning models 203: Natural Language Processing Module 204: Device Parameter Encoding Module 205: Integration module for both representations 206: Classification module 207:Continuous learning function E1: Wireless quality problem E2: Equipment parameters O1: Wireless device settings

Claims

1. a setting problem acquisition unit for acquiring a setting problem which is a problem regarding the setting of the device; an apparatus parameter acquisition unit for acquiring apparatus parameters including settings of the apparatus; A calculation unit that calculates corresponding parameters corresponding to the set problem based on the set problem and the device parameters using a learning model; an output unit for outputting the corresponding parameters; A setting support device having the above configuration.

2. A learning model generating unit generates a learning model using learning data in which a setting problem and an apparatus parameter are input data and corresponding parameters corresponding to the setting problem and the apparatus parameter are used as teacher data, The calculation unit calculates the corresponding parameters using the learning model. The setting support device according to claim 1.

3. The setting support device according to claim 1 , wherein the setting question acquisition unit acquires setting questions written in a natural language.

4. the set problem acquisition unit vectorizes the set problem written in natural language; The learning model generation unit is a vectorized problem. The setting support device according to claim 3 dependent on claim 2.

5. A determination unit that determines whether the corresponding parameter is reflected in the device, The learning model generation unit updates the learning model in accordance with the judgment result of the judgment unit. The setting support device according to claim 2.

6. the learning model generation unit updates the learning model based on the corresponding parameters determined to be reflected in the device, the set problem which is the input data for calculating the corresponding parameters, and the device parameters; The setting support device according to claim 5.

7. A setting support system including a setting device and a setting support server device, The setting device includes: A setting problem acquisition unit that acquires a setting problem that is a problem regarding a setting; an apparatus parameter acquisition unit for acquiring apparatus parameters including settings of the setting apparatus; an input data transmitting unit that transmits the setting problem and the device parameters; having The setting support server device A calculation unit that calculates corresponding parameters corresponding to the set problem based on the set problem and the device parameters using a learning model; a corresponding parameter transmission unit for transmitting the corresponding parameters; The setting device further comprises: an output unit for outputting the corresponding parameters; A setting support system having the above configuration.

8. The setting support server device The present invention further includes a learning model generating unit that generates a learning model trained by learning data using a setting problem and an apparatus parameter as input data and a corresponding parameter corresponding to the setting problem as training data, The calculation unit calculates the corresponding parameters using the learning model. The setting support system according to claim 7.

9. A setting support method for executing the following steps by a computer, obtaining a configuration problem, the configuration problem being a problem related to the configuration of the device; obtaining device parameters including settings for said device; calculating corresponding parameters corresponding to the set problem based on the set problem and the device parameters using a learning model; outputting the corresponding parameters; A setting support method having the above configuration.

10. obtaining a configuration problem, the configuration problem being a problem related to the configuration of the device; obtaining device parameters including settings for said device; A process of calculating corresponding parameters corresponding to the set problem based on the set problem and the device parameters using a learning model; outputting the corresponding parameters; A program for causing a computer to execute the following.

Images