Information processing apparatus and method, and computer readable storage medium

Abstract

The invention provides an information processing apparatus and method, and a computer readable storage medium. In an information processing apparatus having an application and a platform that supports an estimation process using a model that has been learned to estimate information for a search process, in a case where an estimation process is performed by using input data and an output estimation result is recorded based on a user input made before using the application and the model, the application acquires the estimation result from the platform, performs a search process using information included in the estimation result, and provides information using the result.

Description

[0001] This application is a divisional application of the invention patent application with application date of March 19, 2020, application number 202010195692.5, and invention name “Information processing device, method and computer-readable storage medium”. Technical Field

[0002] The present disclosure relates to a technology for improving the usability of an application using the results of machine learning. Background Art

[0003] Typically, an application accepts an input operation from a user and provides information associated with the input operation. For example, the input of a search term or image data allows the display of search results similar to the input.

[0004] A search technique using machine learning technology is discussed in Japanese Patent Application Laid-Open No. 2018-190293. In Japanese Patent Application Laid-Open No. 2018-190293, the category to which a target extracted from a photographic image input to an application belongs is estimated by using a learning machine that has learned the relationship between the transaction target and the category to which the transaction target belongs. The transaction target is searched from an online shopping mall using the estimated category and the feature amount of the transaction target.

[0005] In Japanese Patent Application Laid-Open No. 2018-190293, in order to obtain search results, a photographic image must be input. On the other hand, the user who conducts the search cannot input appropriate search conditions into the application in some cases. In the case of wanting to retrieve past information and unknown information, the user may not have appropriate image data or may not be able to come up with a search term as a search condition. In this case, it is sometimes troublesome to consider a search condition suitable for the application.

[0006] Furthermore, before and after activating the application, a user who attempts to search using the application may have given a word or performed an action related to information prompted as a search target. However, in the case where the user has given such a word or performed such an action before activating the application, the user must set the information associated with the word and action as a search condition in the application after activating the application. Even such an operation is sometimes complicated for the user. Summary of the invention

[0007] According to an embodiment of the present disclosure, an information processing device has an application and a platform, the platform supports estimation processing using a model, the model has been learned to estimate information for search processing, the information processing device includes: an acquisition unit, which is configured to acquire an estimation result from the platform by performing estimation processing based on at least one of user input performed on the information processing device in the platform and user input performed on a device communicating with the information processing device via a network as input data, by using information included in an operation history, and recording an estimation result based on the performed estimation processing; an execution unit, which is configured to perform search processing using information included in the acquired estimation result; and a providing unit, which is configured to provide information on an application installed in the information processing device using the result of the search processing, wherein a user allows the application to use the result of the estimation processing.

[0008] Further features of the present disclosure will become apparent from the following description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 An example of a system configuration is shown.

[0010] Figure 2 is a diagram showing an example of a hardware configuration of a mobile device.

[0011] Figure 3 is a diagram showing an example of a module configuration of software of a mobile device.

[0012] FIG. 4A to FIG. 4C Shows an example of data related to input into a learning model.

[0013] Figure 5 is a flowchart showing a series of processes to be implemented by an operating system (OS) of a mobile device, the series of processes including processes using a learning model.

[0014] Figure 6 An example of data related to output obtained by using a learning model is shown.

[0015] Fig. 7A and Figure 7B is a flow chart illustrating a process implemented by the OS of the mobile device for providing estimation results to an application.

[0016] Figure 8 is a flowchart showing processing to be implemented by an application that accepts information provided by the OS.

[0017] Fig. 9 An example of a screen to be provided by an application in the exemplary embodiment is shown.

[0018] Fig.10 is a flowchart describing processing to be implemented by an application in the application example.

[0019] Fig.11A and Fig. 11B An example of a screen to be provided by an application in the application example is shown. DETAILED DESCRIPTION

[0020] Figure 1 An example of a system configuration according to an exemplary embodiment is shown.

[0021] Examples of mobile devices 101 include smart phones, tablet computers, notebook computers, and wearable terminals. Audio auxiliary terminal 102 accepts audio input from a user and provides search results obtained in response to the audio input. Examples of peripheral devices 103 include digital home appliances such as televisions, refrigerators, and multifunctional microwave ovens, and in-vehicle terminals such as vehicle navigation systems.

[0022] The mobile device 101 can communicate with the audio auxiliary terminal 102 and the peripheral device 103 via a network. In this exemplary embodiment, for example, To achieve communication between devices, another form of connection can be used.

[0023] The mobile device 101 acquires information associated with the audio input from the user through the audio auxiliary terminal 102 via communication when a situation occurs, and records the information and the time. The mobile device 101 acquires information associated with the audio input from the user, the function operation performed by the user, and the location information about the user from the peripheral device 103 via communication when a situation occurs, and records the information together with the time.

[0024] Figure 2 101 is a diagram showing an example of a hardware configuration of an information processing apparatus such as the mobile device 101 .

[0025] The central processing unit (CPU) 201 executes the program stored in the read-only memory (ROM) 203, and the program of the operating system (OS) loaded from the storage device 204 and the application to the random access memory (RAM) 202. That is, the CPU 201 executes the program stored in the readable storage medium to serve as a processing unit for executing the processing in the flowchart described below. The RAM 202, which is the main memory of the CPU 201, is used as a work area, etc. The touch panel 206, which is an input unit of the mobile device 101, is also used as an input device. The display unit of the touch panel 206 displays the result of the function performed by the OS or the application, for example. In addition, in the case of detecting the user operation of the touch panel 206, the desired control is performed by the associated program. Note that the input device of the mobile device 101 is not limited to the touch panel. For example, audio input is enabled by the microphone 207, and image input is enabled by the camera 209. In addition, a position measurement device 210 such as a global positioning system (GPS) is also a position information input device.

[0026] A network interface (I / F) 205 is connected to a local area network and communicates with devices connected to the network. A short-distance communication I / F 208 communicates with connected devices through a communication interface such as a The mobile device 101 can perform input and output by short-distance communication such as NFC and NFC. The components of the mobile device 101 are connected to an internal bus to be able to communicate with each other.

[0027] The audio auxiliary terminal 102 and the peripheral device 103 also have a hardware configuration equivalent to that of the mobile device 101. That is, the audio auxiliary terminal 102 and the peripheral device 103 each include at least a processor, a memory, a storage device, a network I / F, a short-distance communication I / F, and a mechanism for receiving input. In the peripheral device 103, hardware according to the application purpose is also provided.

[0028] Figure 3 1 is a diagram showing an example of a module configuration of software of the mobile device 101. The diagram shows entities of processing to be realized by executing one or more programs such as an OS and an application in the present exemplary embodiment.

[0029] The collection unit 301 , the input control unit 302 , the analysis service unit 303 , the information providing unit 304 , and the function control unit 305 are modules associated with services provided by the OS.

[0030] The collection unit 301 records the content of the user operation performed on the touch panel 206 or the audio input by the microphone 207 together with the time (date) and location information when the user operation or audio input is detected. In addition, the collection unit 301 requests the audio auxiliary terminal 102 and the peripheral device 103 for operation history information about the mobile device 101 or about the user (owner) of the mobile device 101, receives the information, and collects the information. Figure 4A As shown, this information is managed by storage device 204.

[0031] Note that the present exemplary embodiment includes each OS and application installed in the mobile device 101, and a combination of these.

[0032] Figure 4A It is a table storing information collected by the collection unit 301. The information relates to manual operations and audio input operations performed by the user inside and outside the mobile device 101. When the user allows the OS to record the operation history at the time of installation, the applications running on the OS will be automatically recorded. The operation history of services outside the device can only be obtained from the service if the service can collaborate with the OS and the user allows the collaboration. The table uniformly manages the history recorded one by one in the format defined in each application and service. The content includes time, function information (identification information about functions such as applications and services), user information, location information, and operation content. The information to be collected by the collection unit 301 may include broadcast program information and usage information provided by televisions and digital home appliances as peripheral devices 103.

[0033] The input control unit 302 converts the information collected by the collection unit 301 into vectorized data to be input into the analysis service unit 303. When a situation occurs, the vectorized data is recorded in Figure 4B The input management table shown. For example, the collected information is converted or filtered into input data. In the case where the analysis service unit 303 processes phrase-by-phrase input, the analysis service unit 303 divides the information included in the operation content in the history into phrases. Then, the analysis service unit 303 extracts necessary information such as nouns other than verbs to generate input data. In addition, the analysis service unit 303 sometimes uses location information as an additional parameter for analysis processing and estimation processing. Therefore, location information is also recorded. The input control unit 302 can operate in response to the collection of information performed by the collection unit 301, but can operate asynchronously with the information collection.

[0034] The analysis service unit 303 is a so-called artificial intelligence (AI) function for obtaining Figure 4B The input data managed in and the estimation process is performed using the learning model. Figure 4BThe learning model used by the analysis service unit 303 also performs estimation processing using, in addition to the input data managed in the analysis service unit 303, position information associated with the input of the analysis target or profile information about the user of the mobile device 101 as a parameter.

[0035] Figure 4C Profile information about a user registered in the mobile device 101 is shown. The profile information includes hometown, date of birth, gender, interests, address, and occupation. The profile information may optionally include religion and community supported by the OS.

[0036] The analysis service unit 303 provided by the OS can communicate with the cloud service to re-derive the model via the network I / F 205. The cloud service is a platform prepared for implementing processing in the learning phase of creating a model to be used by the analysis service unit 303. The learning model used in the present exemplary embodiment is a model that has been learned based on a number of data in a predetermined format that can be prepared by an input source supported by the OS. The learning model is used to output a word as a search word, which will be used to search for an application to be run on the OS. The input source supported by the OS includes an OS auxiliary function for searching based on audio input from a microphone provided by the OS, an audio auxiliary terminal 102, and a peripheral device 103 provided by a predetermined supplier. Profile information related to users managed by the service of the supplier providing the OS is also used for learning. Note that in the present exemplary embodiment, a model is created by learning from a teacher using a support vector machine (SVM) to output a search word that enables appropriate search results to be obtained in response to the input. However, various other algorithms are also applicable, so, for example, a neural network using deep learning can be used.

[0037] The information providing unit 304 provides the result of the estimation processing performed by the analysis service unit 303 to the cooperative application. Information about the application running on the OS is provided only if the user allows the acceptance of the recommendation based on the estimation result from the analysis service unit 303 at the time of installation. In the following, it is considered that the user has allowed the application with the active analysis service cooperation function. The information providing unit 304 exposes an application programming interface (API) for providing the result of the estimation processing to the application when the application is activated or a request is received from the application.

[0038] The function control unit 305 activates an application upon receiving a user operation.

[0039] The function unit 311 , the display control unit 312 , and the coordination unit 313 , and the function unit 321 , the display control unit 322 , and the coordination unit 323 are modules associated with services provided by two applications (application A and application B) respectively installed to run on the OS.

[0040] Functional units 311 and 321 provide various functions of the application, respectively. If functional units 311 and 321 are web browsers, they analyze hypertext language (HTML) documents related to the website to generate display images or execute scripts, respectively. If functional units 311 and 321 are applications for social networks or applications for exchanging messages, they obtain messages or user information managed in chronological order to process the messages or user information. Display control units 312 and 322 display the processing results from functional units 311 and 321, respectively. Collaboration units 313 and 323 act based on user permission and obtain information via information providing unit 304. The obtained information is processed by functional units 311 and 321 and displayed by display control units 312 and 322, respectively.

[0041] Figure 5 1 is a flowchart describing a series of processes to be implemented by the OS of the mobile device 101, the processes including the processes using the learning model. A program related to the processes is provided by installing a program on the OS to use the learning model. Note that the processes may be implemented by a program acquired from the outside via a network and installed separately.

[0042] This process is performed regularly every few minutes when the OS is operating, for example. In addition, this process can be performed at any other timing, for example when a new operation history is recorded. This process is automatically performed in the background asynchronously with the process to be performed by the application to be provided with information.

[0043] In step S501, the collecting unit 301 collects historical data related to manual operations and audio input operations performed by the user inside and outside the mobile device 101, and manages the historical data, such as Figure 4A As described above, the data to be collected includes the operation content recorded by the operation performed by the user on the touch panel 206, and the audio input through the microphone 207 and the cooperative devices (audio assistance terminal 102 and peripheral device 103) on the network.

[0044] In step S502, the input control unit 302 extracts Figure 4A The unprocessed records managed in the analysis service unit 303 are vectorized. As described above, this is the processing performed by the input control unit 302 to perform input to the analysis service unit 303. Note that the collected information can be converted or filtered into input data. Figure 4B As shown, information including vectorized data is managed.

[0045] In step S503, the input control unit 302 inputs the vectorized input data to the analysis service unit 303. Figure 4BIn addition to the input data of the latest record included in the , multiple different inputs can also be performed by collectively inputting multiple new record input data.

[0046] In step S504, the analysis service unit 303 performs estimation processing using the input data and the learning model acquired from the input control unit 302. In step S505, the analysis service unit 303 records the result of the estimation processing in the table ( Figure 6 ). Figure 6 In the analysis service unit 303, the result (output) of the estimation process, the time, and the content of the associated input data are recorded.

[0047] The information providing unit 304 will Figure 6 The data recorded in (particularly as a result of the output from the estimation process) is provided to application A and application B.

[0048] Fig. 7A and 7B 1 is a flowchart describing a process for providing an estimation result of the analysis service unit 303 implemented by the OS of the mobile device 101 to an application. In order to use a learning model, a program related to the process is provided by being incorporated into the OS. Note that the process may be implemented by a separately installed program acquired from the outside via a network.

[0049] Fig. 7A In particular, the processing in the case where the function control unit 305 activates an application is shown.

[0050] In step S701, the function control unit 305 detects an application activation instruction based on a user operation. In step S702, the function control unit 305 determines whether the analysis service cooperation function of the application whose activation instruction has been detected is activated. If the function is activated ("Yes" in step S702), the process proceeds to step S703. If the function is not activated ("No" in step S702), the process ends.

[0051] In step S703, the information providing unit 304 receives Figure 6 The estimation result is obtained in the table shown in FIG. One or more records are obtained within a predetermined time period after the current time. Note that at this time, information not provided to the application is managed, and only associated records can be obtained. In step S704, the information providing unit 304 provides the application with information about the records obtained in step S703 as the estimation result. When providing this information, only the records in the Figure 6 The content included in the output managed in .

[0052] Note that in step S704 , the function control unit 305 is designed to pass the information on the record acquired in step S703 as a parameter when activating the application.

[0053] Figure 7B In particular, the processing is shown in the case where the information providing unit 304 cooperates with the activation application. In the mobile device 101, the information providing unit 304 resides as a service and performs processing.

[0054] In step S711, the information providing unit 304 determines whether a request for the estimation result has been accepted from the application. If the request has been accepted ("Yes" in step S711), the process proceeds to step S712. If the request has not been accepted ("No" in step S711), the process proceeds to step S714.

[0055] In step S712, similar to step S703, the information providing unit 304 obtains Figure 6 The estimation result is obtained in the table shown in FIG. 14. In step S713, similarly to step S704, the information providing unit 304 provides the acquired information on the record as the estimation result to the application.

[0056] In step S714, the information providing unit 304 determines whether feedback from the application has been accepted. The feedback indicates that the estimation result provided as information has been used. If the feedback has been accepted ("Yes" in step S714), the process proceeds to step S715. If the feedback has not been accepted ("No" in step S714), the process proceeds to step S711.

[0057] In step S715, the information providing unit 304 refers to Figure 6 The input data that has been input into the analysis service unit 303 when the estimation result used by the user included in the feedback is acquired is specified. Figure 4B Identification information about a function that is an input source of the designated input data is designated. In step S716, the information providing unit 304 records the identification information about the designated function in the storage device 204 in association with the received feedback information.

[0058] The recorded data is provided to the cloud service via the OS for re-deriving the above-mentioned model. The re-derived learning model can be downloaded and installed at the timing of updating the OS.

[0059] Figure 8 3 is a flowchart showing processing implemented by an application that receives information from the information providing unit 304. Here, processing in the case where application A in which the analysis service cooperative function is activated is running will be described.

[0060] In step S801 , the display control unit 312 displays the home screen of the application A based on an application activation instruction provided by a user operation.

[0061] In step S802, the function unit 311 performs a search process using the estimation result provided by the information providing unit 304. Specifically, the search process is performed by using words such as "basketball" and "collection of wonderful games" included in the estimation result to automatically retrieve users who make relevant postings. The function unit 311 can search using "and" or "or" based on the provided estimation result. In addition, the search can be performed after selectively partially extracting the estimation result based on the search target of application A or by using the search results obtained by using "or". The search target can be in an external area connected by a network.

[0062] In step S803 , the display control unit 312 automatically updates the display content upon receiving the search result from the function unit 311 .

[0063] Fig. 9 An example of a screen of application A to be provided by mobile device 101 after updating is shown. Display 901 indicates an object that is acquired by application A via a network and that many other users are currently paying attention to. Display 902 indicates a result of a search process using an estimation result provided by information providing unit 304 as “AI search”. Display 902 indicates a processing result desired by a user of application A. The processing result has been acquired through an estimation result that has been acquired from a history associated with a user's words and actions in a time period immediately before and after activating application A and output from the OS, and through an action such as activating application A.

[0064] In step S804, the functional unit 311 determines whether a predetermined time has passed since the processing in step S802 was last performed. If the predetermined time has passed ("Yes" in step S804), the processing proceeds to step S805. If the predetermined time has not passed ("No" in step S804), the processing proceeds to step S806. In step S805, the collaboration unit 313 requests the information providing unit 304 for the estimation result. When the estimation result is accepted, the processing in and after step S802 is performed again. If there is no difference in the estimation result, the functional unit 311 can skip the search processing in step S802 and the update processing in step S803. Steps S804 and S805 enable the latest estimation result obtained by the analysis service unit 303 to be applied to the application.

[0065] In step S806, the function unit 311 determines whether a user operation has been performed on the screen provided by application A. If a user operation has been performed ("Yes" in step S806), the process proceeds to step S807. If a user operation has not been performed ("No" in step S806), the process returns to step S804.

[0066] In step S807, the function unit 311 performs processing based on the user operation. Specifically, in the case where objects and links included in the display 901 and the display 902 are specified, display switching and processing for information provision are performed based on the specification.

[0067] In step S808, the function unit 311 determines whether the user operation caused by the processing in step S807 is associated with the estimation result received from the information providing unit 304. For example, in the case where an object or link included in the display 902 is specified, it is determined that a user operation associated with the estimation result has been performed. If the user operation has been associated with the estimation result ("Yes" in step S808), the processing proceeds to step S809. If not ("No" in step S808), the processing returns to step S804. In step S809, the collaboration unit 313 sends feedback including the estimation result associated with the user operation to the information providing unit 304.

[0068] A first application example will be described. Fig.10 The exemplary embodiment described above shows Figure 8 An application example in which the flowchart in is applied to another application. Fig.10 In, with Figure 8 The same steps as in the steps are denoted by the same step numbers, and their descriptions will be omitted. The differences and effects will be described below.

[0069] In step S1001, the function unit 311 determines whether the processing performed in step S807 is a predetermined user operation. If the processing is a predetermined user operation ("Yes" in step S1001), the processing proceeds to step S1002. If the processing is not a predetermined user operation ("No" in step S1001), the processing proceeds to step S808.

[0070] Specific examples of the predetermined user operation are a scroll operation to be realized by a flick operation and an operation on a display object associated with a search function.

[0071] Specifically, in the case where the activated application is an application that displays messages posted by the user in chronological order on a timeline, the user scrolls the messages on the screen by a flick operation rather than a swipe operation. At this time, it is considered that the user who has performed the flick operation desires to see messages or image data posted in the relatively distant past. In the case where the user sees data from several years or decades ago, the data is retrieved by the user repeatedly flicking the screen to perform a scrolling operation.

[0072] Furthermore, in the case where an operation has been performed on a display object associated with a search function provided in advance in any application, the intention of the user who desires to perform a search using a specific search function can be grasped.

[0073] The present application example allows the user to use the estimation result provided by the information providing unit 304 in consideration of such intention of the user.

[0074] In step S1002 , the function unit 311 performs a search process using the estimation result provided by the information providing unit 304 , and automatically updates the display content reflecting the search result in the display content.

[0075] Fig.11A An example of a screen provided by an application for displaying messages posted by a user in chronological order on a timeline is shown. The processing in step S1002 is reflected on the screen.

[0076] The object 1101 on the screen indicates an additional object for jumping to time information or a message associated with the search results of the data included in the estimation result among the multiple messages included in the scroll destination of the scroll bar. When performing a flick operation, the user can select any one of the objects 1101 that appear automatically, which can cause the display of the desired message. Alternatively, as the scroll destination of the user's micro-operation, the function unit 311 controls to display the message associated with the search results.

[0077] Furthermore, in the case where a message associated with the search result in step S1002 is included in a plurality of messages to be displayed during screen scrolling by a flick operation, scrolling may be stopped while the message is being displayed. As a result, the user is prevented from skipping the message.

[0078] Fig. 11B An example of a screen to which the processing in step S1002 has been reflected in a case where the user has selected to activate a specific search function on the application is shown.

[0079] exist Fig. 11BIn the display 1102, in addition to the input field where the user can input any search word, the result of "AI search" obtained by using the estimated result provided by the information providing unit 304 is displayed. An automatic search is performed based on the word search and the time period (from the current time to the time included in the estimated result). The user can perform other operations such as an operation for additionally inputting a search word into the input field and an operation for deleting the search word "AI search".

[0080] In this application example, in addition to the predetermined operation performed by the user on the application, the above-mentioned estimation result is automatically applied. Therefore, it is likely that the search target desired by the user will be provided immediately. In this application example, user actions such as visually finding the search target and entering the appropriate search term that the user thinks of can be omitted.

[0081] A second application example will be described. The above-mentioned OS also includes a reporting function and a deviation adjustment function.

[0082] The report function is used to present the basis on which the learning model derives the output from the input data in the estimation process. For example, in the case of selecting an output, the input data and parameters used as the basis for obtaining the output are listed. The degree of influence of the listed data on the derivation of the output can be displayed.

[0083] The bias adjustment function is a function for detecting a tendency that an unexpected output is likely to be obtained for a predetermined input in an estimation process using a learning model and notifying such a situation. In addition, in this function, a conversion rule is set for the input control unit 302. The conversion rule is used to reflect a reverse bias for obtaining an estimation result desired by the user based on a user instruction for a predetermined input. Hereinafter, in the case where this setting is made, if a predetermined input is accepted, at least a part of the input information is changed and used for the learning model according to the conversion rule.

[0084] A third application example will be described. The present disclosure includes an apparatus or system configured by appropriately combining the above-described exemplary embodiments and a method thereof.

[0085] Other embodiments

[0086] In addition, the embodiments of the present invention may be implemented by reading and executing computer executable instructions (e.g., one or more programs) recorded on a storage medium (also more completely referred to as a "non-transitory computer-readable storage medium") to perform one or more functions in the above-mentioned embodiments, and / or a computer of a system or device including one or more circuits (e.g., an application-specific integrated circuit (ASIC)) for performing one or more functions in the above-mentioned embodiments, and the embodiments of the present invention may be implemented by, for example, reading and executing the computer executable instructions from the storage medium by the computer of the system or device to perform one or more functions in the above-mentioned embodiments, and / or controlling the one or more circuits to perform one or more functions in the above-mentioned embodiments. The computer may include one or more processors (e.g., a central processing unit (CPU), a microprocessing unit (MPU)), and may include a network of separate computers or separate processors to read and execute the computer executable instructions. The computer executable instructions may be provided to the computer, for example, from a network or the storage medium. The storage medium may include, for example, a hard disk, a random access memory (RAM), a read-only memory (ROM), a memory of a distributed computing system, an optical disk (such as a compact disc (CD), a digital versatile disc (DVD), or a Blu-ray disc (BD) TM ), flash memory devices, memory cards, etc.

[0087] The embodiments of the present invention may also be implemented by providing software (program) for performing the functions of the above-described embodiments to a system or device via a network or various storage media, and a computer or a central processing unit (CPU) or a microprocessing unit (MPU) of the system or device reads and executes the program.

[0088] Although the present disclosure includes exemplary embodiments, it should be understood that the invention is not limited to the disclosed exemplary embodiments.The scope of the following claims is to be accorded the broadest interpretation so as to encompass all such modifications and equivalent structures and functions.

Claims

1. An information processing device having an application and a platform, the platform supporting an estimation process using a model that has been learned to estimate information for a search process, the information processing device comprising: an acquisition unit configured to acquire an estimation result from the platform by performing an estimation process based on at least one of a user input performed on the information processing device in the platform and a user input performed on a device communicating with the information processing device via a network as input data, by using information included in the operation history, and recording an estimation result based on the performed estimation process; an execution unit configured to execute a search process using information included in the acquired estimation result; as well as a providing unit configured to provide information on an application installed in the information processing device using a result of the search process, Therein, the user allows the application to use the results of the estimation process.

2. The information processing device according to claim 1, wherein: The platform is provided as an operating system.

3. The information processing device according to claim 1, wherein: The model is installed in an information processing device for use by the platform.

4. The information processing device according to claim 1, further comprising a request unit configured to request the estimation result from the platform, and in, In response to the request, the acquisition unit acquires the estimation result.

5. The information processing device according to claim 4, wherein: The estimation result is periodically requested from the platform.

6. The information processing device according to claim 1, wherein: When the application is activated, the estimation result is obtained from the platform.

7. The information processing device according to claim 1 further includes a sending unit, which is configured to send feedback including the estimated result to the platform when the application accepts a user operation associated with the result of a search process using the information included in the estimated result.

8. The information processing device according to claim 1, in, In a case where a predetermined operation performed by a user is detected, a search process using information included in the estimation result is performed on a search target associated with the predetermined operation, and Among them, the content to be provided is updated by using the result of the search process.

9. The information processing device according to claim 8, wherein: The predetermined operation includes a scroll operation to be realized by a flick operation, and display is performed by using a result of the search process as a scroll destination.

10. The information processing device according to claim 1, wherein: The device capable of communicating via a network is at least any one of an audio assistance terminal, a digital home appliance, and a vehicle-mounted terminal.

11. The information processing device according to claim 1, wherein: The user input includes audio input.

12. A method for an application installed in an information processing device having a platform, the platform supporting an estimation process using a model that has been learned to estimate information for a search process, the method comprising: acquiring an estimation result from the platform, while performing an estimation process based on at least one of a user input performed on an information processing device in the platform and a user input performed on a device that can communicate with the information processing device via a network as input data, by using information included in the operation history, and recording an estimation result based on the performed estimation process; performing a search process using information included in the acquired estimation result; as well as Use the results of the search process to provide information, Therein, the user allows the application to use the results of the estimation process.

13. The method according to claim 12, wherein: The platform is provided as an operating system.

14. The method according to claim 12, wherein: The model is installed in an information processing device for use by the platform.

15. The method according to claim 12, further comprising: requesting the estimation result from the platform; as well as In response to the request, the estimation result is obtained.

16. The method according to claim 15, wherein: The estimation result is periodically requested from the platform.

17. The method according to claim 12, wherein: When the application is activated, the estimation result is obtained from the platform.

18. The method according to claim 12, further comprising: In a case where a user operation associated with a result of a search process using information included in an estimation result is accepted, feedback including the estimation result is transmitted to the platform.

19. The method according to claim 12, in, In a case where a predetermined operation performed by a user is detected, a search process using information included in the estimation result is performed on a search target associated with the predetermined operation, and Among them, the content to be provided is updated by using the result of the search process.

20. The method according to claim 19, wherein: The predetermined operation includes a scroll operation to be realized by a flick operation, and display is performed by using a result of the search process as a scroll destination.

21. The method according to claim 12, wherein: Devices capable of communicating via the network include audio auxiliary terminals, digital home appliances, and vehicle-mounted terminals.

22. The method according to claim 12, wherein: The user input includes audio input.

23. A computer-readable storage medium storing instructions, wherein: The instructions are related to an application, and the instructions cause an information processing device to perform operations, the information processing device having a platform, the platform supporting an estimation process using a model that has been learned to estimate information for a search process, the operations comprising: acquiring an estimation result from the platform, while performing an estimation process based on at least one of a user input performed on an information processing device in the platform and a user input performed on a device that can communicate with the information processing device via a network as input data, by using information included in the operation history, and recording an estimation result based on the performed estimation process; performing a search process using information included in the acquired estimation result; and Use the results of the search process to provide information, Therein, the user allows the application to use the results of the estimation process.

Images