JP4603988B2 - Information processing apparatus and method - Google Patents

Description

  The present invention relates to an information processing apparatus and method, and more particularly, to an information processing apparatus and method having a function of providing help information according to a keyword input by voice.

  In a conventional help function, a method of accumulating user operation history or the like and reflecting the operation history or the like in a help information presentation method has been studied.

  For example, in Patent Document 1, a history is referred to, and if there is one in the same state as the current inquiry, it is presented. This method is useful for presenting help information that has been useful in the past. On the other hand, in Patent Document 2, the history is referred to, and if there is the same state, it is excluded and presented. This method is useful for suppressing the presentation of help information for known functions.

  As for online help using voice input, as in Patent Document 3, a user inputs an inquiry sentence by voice, and presents help information in comparison with the processing state of the apparatus, not the history. is there.

Japanese Patent Laid-Open No. 08-036548 Japanese Patent Laid-Open No. 04-291415 Japanese Patent Laid-Open No. 2002-014751

  When inputting a search keyword by voice, there is a problem of erroneous recognition of voice. For this reason, a method is conceivable in which a plurality of candidates are extracted as voice recognition results, given some sort of order, presented to the user, and a desired keyword is selected from them.

  One method of ranking is weighting frequently used words or important words. However, in the help system for device operation, it is considered that there is a high possibility that familiar words and important words are already mastered. Therefore, it is not necessary to present these words in reverse. As described above, when the speech recognition candidate presentation method generally adopted in speech recognition is applied to the device operation help system as it is, an appropriate keyword candidate that successfully includes the keyword desired by the user can be obtained. It is often impossible to make a presentation.

  The present invention provides an information processing apparatus that provides help information corresponding to a keyword obtained by speech recognition, and is capable of presenting keyword candidates in a more appropriate order on the assumption that speech recognition may be erroneously recognized. Objective.

An information processing apparatus according to an aspect of the present invention stores a storage unit that stores a document in which an explanatory text is described for each function, and history data that includes a frequency of use for each function. a history management means for updating the frequency of use, and the sound receiving means for receiving voice information, a plurality of keywords to identify the functions as the recognition target words, the user uttered received by the speech reception means Voice recognition means for performing voice recognition processing on the voice of one keyword and outputting a plurality of recognition result candidates for selection by the user, and the plurality of voices outputted from the voice recognition means based on the history data recognition result candidates respectively determined frequency of use of the corresponding functions for the, and ranking means for performing ranking of said plurality of recognition result candidates as the frequency of use gives a higher ranking in ascending order, before A plurality of recognition result candidates, and presenting means for presenting to the user in descending order of a given rank by the ranking means, said plurality presented by the presenting unit based on a user's selection instruction recognition result of the candidate selecting means for selecting either a keyword on the basis of the documents stored on said storage means, the description of the function corresponding to the keyword selected by the selecting means, the help provided to the user as help information Providing means.

  According to the present invention, in an information processing apparatus that provides help information corresponding to a keyword obtained by voice recognition, it is possible to present keyword candidates in a more appropriate order on the assumption that voice recognition may be erroneously recognized. become.

  DESCRIPTION OF EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings. In addition, this invention is not limited to the following embodiment, It shows only the specific example advantageous for implementation of this invention. In addition, not all combinations of features described in the following embodiments are indispensable as means for solving the problems of the present invention.

(Embodiment 1)
FIG. 1A is a block diagram illustrating a hardware configuration example of an image processing apparatus as an information processing apparatus according to the present embodiment. As specific examples of the image forming apparatus, various apparatuses such as a copying machine, a printer, and a facsimile apparatus can be considered. The image processing apparatus is only an example of an information processing apparatus, and the present invention is not limited to the image processing apparatus. For example, a general-purpose computer system such as a personal computer can be included in the scope of the present invention. Specifically, the present invention can be applied to an application installed in a computer system and an OS help function.

  The image processing apparatus shown in FIG. 1A includes a CPU 1 that controls the entire apparatus, a RAM 2 that functions as a main storage device and provides a work area for the CPU 1, and a ROM 3 that stores a boot program and fixed data. First, the following configuration is provided.

  The HDD 4 is a hard disk device. As shown in the figure, a control program 41, usage history data 42, a keyword-function table 43 described later, a help document 44 describing an operation manual, a recognition dictionary 45, and the like are stored. The display 5 is constituted by, for example, a liquid crystal display device, on which the setting state of the device is displayed. The input device 6 includes, for example, a touch panel type input device provided so as to overlap the display 5, and the user can give various instructions via the input device 6. Reference numeral 7 denotes a microphone for inputting sound, and reference numeral 8 denotes an audio interface (I / F) to which the microphone 7 is connected. The audio I / F 8 includes an amplifier (not shown), a low-pass filter, and an A / D converter. Reference numeral 9 denotes a scanner unit for optically reading a document, and 9a denotes a scanner I / F to which the scanner unit 9 is connected. Reference numeral 10 denotes a printer unit that records and outputs image data read by the scanner unit 9 on a recording sheet. Reference numeral 10a denotes a printer I / F to which the printer unit 10 is connected.

  FIG. 1B is a functional block diagram relating to the help function of the image processing apparatus according to the present embodiment.

  An operation manual database 101 stores an operation manual document (corresponding to the help document 44), and the HDD 4 plays this role. Reference numeral 102 denotes a voice input unit for inputting voices such as keywords when searching for an operation manual, which is realized by the microphone 7 and the audio I / F 8. Reference numeral 103 denotes an operation input unit for operating a device including a manual search operation, which is realized by the input device 6. A manual search unit 104 executes manual search. A voice recognition unit 105 performs voice recognition on the voice from the voice input unit 102, and a voice recognition dictionary (corresponding to the recognition dictionary 45) 106. The speech recognition unit 105 sets a keyword for specifying the function of the image processing apparatus as a recognition target word. An operation processing unit 107 performs processing according to an operation instruction from the operation input unit 103, and a search result processing unit 108 performs processing such as ordering search results by the manual search unit 104. Reference numeral 109 denotes a speech recognition result candidate processing unit that performs processing such as ordering the speech recognition candidates obtained by the speech recognition unit 105. A usage history storage unit 110 stores a usage history of the function of the device (corresponding to the usage history data 42), and is realized by the HDD 4. An image display unit 111 displays a voice recognition result, a search result, and an operation processing result, and is realized by the display 5. The manual search unit 104, the voice recognition unit 105, the operation processing unit 107, the search result processing unit 108, and the voice recognition result candidate processing unit 109 described above are each realized by the CPU 1 executing the control program 41.

  FIG. 2 is a flowchart showing an operation manual search process by the image processing apparatus according to this embodiment. As a premise of the operation manual search process, it is assumed that the operation processing unit 107 also operates as a history management unit and updates the usage history data 42 every time a certain function is activated. An example of the data structure of the usage history data 42 will be described later.

  First, in step S201, an audio input from the audio input unit 102 is accepted. At this time, the user can utter a voice as a search keyword for the operation manual. In the next step S202, the voice received in step S201 is recognized. Here, for example, it is assumed that when the user utters “density”, two keywords 1) “mode” and 2) “density” are output as recognition results by voice recognition. Here, an example in which two keywords are output is shown, but three or more keywords may be output.

  In the next step S203, the presentation order of recognition candidates is created with reference to the usage history data 42.

  Here, FIG. 3 shows an example of the data structure of the keyword-function table 43. This keyword-function table 43 shows what functions each search keyword (index word) corresponds to. Keywords and functions do not have to correspond one-on-one. For example, as shown in the figure, the keyword “mode” has a plurality of functions such as “standard mode”, “mode memory”, “user mode”, “application mode”, “sorter mode”, and “double-sided mode”. It may be adapted.

  FIG. 4 shows an example of the data structure of the help document (operation manual) 44. As shown in the figure, an operation explanation (comment) and a procedure are described for each function.

  FIG. 5 shows an example data structure of the usage history data 42. As shown in the figure, the usage history data 42 is configured to include, for each function, the usage frequency and usage date / time of the function.

  In step S203, first, the function name corresponding to each keyword candidate output in step S202 is specified with reference to the keyword-function table 43 as shown in FIG. Thereafter, the use history data 42 as shown in FIG. 5 is referred to, and the use frequency of each specified function is obtained. Then, the two keyword candidates “mode” and “density” are ranked according to the frequency of use. For example, a higher rank may be given in ascending order of use frequency.

  Or, if the difference in usage frequency between the two candidates is greater than the threshold value, the one with the lower frequency is ranked higher, and if the difference between the two usage frequencies is less than or equal to the threshold value, the latest history Ranking may be done by giving priority to the older one. For example, referring to the example of the usage history data 42 in FIG. 5, the function “copy density” (FIG. 3) corresponding to “density” is the frequency 40. On the other hand, functions corresponding to “mode” include “standard mode, mode memory, user mode, application mode, sorter mode, duplex mode”, and their frequencies are “5054, 0, 0, 0, 2012, 1123”. Is. When the sum is taken, the difference in frequency is large, and “density” is higher than “mode”.

  Next, proceeding to step S204, the two keywords are displayed on the display 5 in the order according to the ranking result obtained in step S203, and presented to the user. For example, as shown in FIG. 6, the upper keyword “density” is displayed above.

  In the next step S205, the user keyword selection is accepted. As shown in FIG. 6, each keyword is provided with a check box, and the user can select a candidate by touching the check box of the desired keyword. Here, it is assumed that the keyword candidate “density” is selected by the user.

  Next, in step S206, the operation manual (help document 44) is searched with the selected keyword. As shown in FIG. 3, the function name corresponding to the keyword “density” is “copy density”. As shown in FIG. 4, the help document 44 describes an operation description (comment) for each function. Therefore, the corresponding description is specified by searching for the function name “copy density”. be able to.

  In step S207, the specified explanatory text is displayed on the display 5 and provided to the user. FIG. 7 shows an example of the display. As in the example shown in the figure, it is possible to provide a display form in which a link is provided in the function name and the operation procedure is followed from there.

  As described above, according to the present embodiment, the keyword candidates are ranked according to the function usage frequency, and the keyword candidates are presented to the user according to the ranking. As a result, the user can easily access the description of the function corresponding to the desired keyword. In particular, if a high rank is given to a function whose frequency of use is low, a high rank is given to a function that the user may not know. Thereby, even when there is a misrecognition of voice recognition, correction to the correct answer can be performed effectively.

  In the above-described example, the frequency of the corresponding functions is summed in order to determine the search keyword presentation order. However, instead of this, the speech recognition result may be expanded to the corresponding function, the presentation order of the function may be obtained in order of frequency, the function name may be presented, and the user may select it.

(Embodiment 2)
In the first embodiment described above, an example in which the keyword candidate “density” is selected has been described. In this case, since the function corresponding to “density” is only “copy density”, the explanatory text presented is only for this “copy density”. On the other hand, when there are a plurality of functions corresponding to the selected keyword candidates, the explanations for the plurality of functions are listed. In this case, it is desirable that the presentation order is controlled according to the use frequency. In the second embodiment, control processing in such a case will be described.

  FIG. 8 is a flowchart showing the processing contents in step S207 described above in the present embodiment. Here, a case where “enlarged copy” is selected from the recognition candidates of “enlarged copy” and “single-sided copy” in step S205 as shown in FIG. 9 will be described as an example.

  In the present embodiment, it is assumed that the keyword-function table 43 includes data as shown in FIG. Referring to this figure, the functions corresponding to the selected keyword “enlarged copy” are “standard magnification”, “automatic magnification”, “zoom magnification”, “zoom program”, and “enlarged layout”.

  In the present embodiment, it is assumed that the help document 44 includes data as shown in FIG. 11, and the usage history data 42 includes data as shown in FIG.

  In step S803, the function corresponding to the selected keyword “enlarged copy” corresponds to “standard magnification”, “automatic magnification”, “zoom magnification”, “zoom program”, and “enlarged layout”. The presentation order is obtained by referring to the use frequency in FIG. For example, if the difference in frequency of use between two candidates is greater than the threshold value, the method with the lowest frequency will be ranked higher, and if the frequency of use is the same, give preference to the older of the latest history. You may rank by. As a result, the presentation in step S804 is in the presentation order as shown in FIG. In the example of FIG. 12, both the “enlarged layout” and the “zoom program” have the same frequency of use and the same order. In this case, for example, if the reading is sorted in the order of eyeballs. Good.

(Embodiment 3)
Even if the same word is used as a keyword, if there are multiple sub-functions belonging to different function groups, the description that is assigned to a frequently used group is more likely to belong to a group that is not used at all. It is considered that there is a high possibility of being demanded. In the present embodiment, a process considering such a possibility is proposed.

  FIG. 14 is a diagram showing an example of the data structure of the usage history data 42 in the present embodiment. Each function is classified into a plurality of groups (in the example of the figure, a basic function group and an application mode group are displayed). The functions (subfunctions) of each group are organized by a hierarchical structure. Further, usage frequency information is assigned to each function. The usage frequency of the functions in the upper hierarchy is the sum of the usage frequencies of the functions in the lower hierarchy. In the example of FIG. 14, the use date / time is not displayed, but it is desirable that the use date / time is also recorded.

  In the ranking of keyword candidates in this embodiment, a high ranking is given to those with a high usage frequency and those with a new usage history. This is because, as described above, a description belonging to a frequently used group is more likely to be requested for explanation than a member belonging to a group that is not used at all.

  Also, a plurality of functions having different groups and having the same use frequency may be ranked according to the use history of the hierarchy one level above. For example, in the example shown in FIG. 14, the “zoom program” and the “enlarged layout” belong to different groups, and the usage histories are both zero. In this case, the upper layer usage history is referred to. Since the usage history of “magnification”, which is the upper layer of “zoom program”, is 3130, and the usage history of “application mode”, which is the upper layer of “enlarged layout”, is 0, high ranking is given to “zoom program”. It will be. An example of presenting the operation manual search result in this case is shown in FIG. In FIG. 15, it can be seen that the display order of “zoom program” and “enlarged layout” is switched from the example of FIG. Note that the term “identical” here does not mean completely identical, but may include an error.

  In the third embodiment described above, the use history hierarchized is used to determine the presentation order of the search results, but the use history hierarchized is used to determine the presentation order of the speech recognition candidates. May be.

(Other embodiments)
In the first embodiment and the second embodiment described above, the keyword-function table 43 is used, but instead, a search result may be obtained by searching using the full-text search function.

  The search result presentation method is not limited to the image display as described above, and for example, a text reading function by speech synthesis may be used.

  As for the usage history data, the usage history data may be managed for each user, and the keyword candidates may be ranked using the usage history for each user.

  As mentioned above, although embodiment of this invention was explained in full detail, this invention may be applied to the system comprised from several apparatuses, and may be applied to the apparatus which consists of one apparatus.

  In the present invention, a program for realizing each function of the above-described embodiments is supplied directly or remotely to a system or apparatus, and a computer included in the system or apparatus reads and executes the supplied program code. Can also be achieved.

  Accordingly, since the functions and processes of the present invention are implemented by a computer, the program code itself installed in the computer also implements the present invention. That is, the computer program itself for realizing the functions and processes is also one aspect of the present invention.

  In this case, the program may be in any form as long as it has a program function, such as an object code, a program executed by an interpreter, or script data supplied to the OS.

  Examples of the recording medium for supplying the program include a flexible disk, hard disk, optical disk, magneto-optical disk, MO, CD-ROM, CD-R, and CD-RW. Examples of the recording medium include a magnetic tape, a non-volatile memory card, a ROM, a DVD (DVD-ROM, DVD-R), and the like.

  The program may be downloaded from a homepage on the Internet using a browser on a client computer. That is, the computer program itself of the present invention or a compressed file including an automatic installation function may be downloaded from a home page to a recording medium such as a hard disk. Further, it is also possible to divide the program code constituting the program of the present invention into a plurality of files and download each file from a different home page. That is, a WWW server that allows a plurality of users to download a program file for realizing the functions and processing of the present invention on a computer may be a constituent requirement of the present invention.

  Further, the program of the present invention may be encrypted and stored in a storage medium such as a CD-ROM and distributed to users. In this case, only the user who cleared the predetermined condition is allowed to download the key information to be decrypted from the homepage via the Internet, decrypt and execute the program encrypted with the key information, and install the program on the computer. May be.

  Further, the functions of the above-described embodiments may be realized by the computer executing the read program. Note that an OS or the like running on the computer may perform part or all of the actual processing based on the instructions of the program. Of course, also in this case, the functions of the above-described embodiments can be realized.

  Furthermore, the program read from the recording medium may be written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer. Based on the instructions of the program, a CPU or the like provided in the function expansion board or function expansion unit may perform part or all of the actual processing. In this way, the functions of the above-described embodiments may be realized.

It is a block diagram which shows the hardware structural example of the image processing apparatus in embodiment. It is a functional block diagram concerning a help function of an image processing device in an embodiment. It is a flowchart which shows the operation manual search process in embodiment. It is a figure which shows the example of a data structure of the keyword-function table in Embodiment 1. It is a figure which shows the example of a data structure of the function manual in Embodiment 1. FIG. It is a figure which shows the example of a data structure of the usage history data in Embodiment 1. FIG. It is a figure which shows the example of presentation of the speech recognition result in Embodiment 1. FIG. It is a figure which shows the example of presentation of the operation manual search result in Embodiment 1. FIG. 10 is a flowchart illustrating search result presentation processing according to the second embodiment. It is an example of selection of a voice recognition result in Embodiment 2. It is a figure which shows the example of the data of the keyword-function table in Embodiment 2. 10 is a diagram illustrating an example of a help document in Embodiment 2. FIG. It is a figure which shows the example of the usage log data in Embodiment 2. It is a figure which shows the example of presentation of the operation manual search result in Embodiment 2. FIG. It is a figure which shows the example of a data structure of the usage history data in Embodiment 3. It is a figure which shows the example of presentation of the operation manual search result in Embodiment 3.

Claims (7)

Storage means for storing a document in which a description is described for each function;
History management means that retains history data including the frequency of use for each function and updates the frequency of use of the function according to the use of the function;
Voice receiving means for receiving voice information;
Multiple keywords for identifying the function as the recognition target words, performs voice recognition processing on a single keyword voice generated by a user received by the speech reception means, a plurality for selection by the user Speech recognition means for outputting recognition result candidates of
Based on the historical data, the determined frequency of use of speech recognition means of said plurality of output from the recognition result of each corresponding function for the candidate, the plurality of recognition results as the frequency of use gives a higher ranking in ascending order Ranking means for ranking candidates ;
Presenting means for presenting the plurality of recognition result candidates to the user in descending order of ranking given by the ranking means;
Selection means for selecting any one of the plurality of recognition result candidates presented by the presentation means based on a user's selection instruction as a keyword ;
Help providing means for providing, as help information, a description of a function corresponding to the keyword selected by the selection means based on the document stored in the storage means;
An information processing apparatus comprising: When there are a plurality of functions corresponding to at least one of the plurality of recognition result candidates , the ranking unit obtains a total use frequency of the functions corresponding to each of the plurality of recognition result candidates , and uses the frequency. The information processing apparatus according to claim 1 , wherein the plurality of recognition result candidates are ranked so that a higher rank is given in ascending order . When there are a plurality of functions corresponding to the keyword selected by the selection means, the help providing means obtains the use frequency of each function corresponding to the keyword selected by the selection means based on the history data. , the frequency of use is low order, the information processing apparatus according to claim 1 or 2, characterized in that to provide a description of the respective functions to the user. The history data has a format in which each function is classified into a plurality of groups, the functions of each group are organized by a hierarchical structure, and information on the frequency of use is given to each function,
The ranking means obtains the usage frequency of the corresponding function for each of the plurality of recognition result candidates output from the speech recognition means based on the history data, and gives a higher ranking in ascending order of the usage frequency. The information processing apparatus according to claim 1 , wherein the plurality of recognition result candidates are ranked. For the functions corresponding to the plurality of recognition result candidates among the functions corresponding to the plurality of recognition result candidates and having the same use frequency, the ranking means uses the function of the higher layer of each function. The information processing apparatus according to claim 4 , wherein the plurality of recognition result candidates are ranked so that a higher ranking is given in ascending order of frequency . A document storing an explanatory text for each function, and a memory for storing history data including the frequency of use for each function;
History management means for updating the frequency of use of the function in the history data stored in the memory according to the use of the function;
Voice receiving means for receiving voice information;
An information processing method executed by an information processing apparatus having
Multiple keywords for identifying the function as the recognition target words, performs voice recognition processing on a single keyword voice generated by a user received by the speech reception means, a plurality for selection by the user A speech recognition step for outputting a recognition result candidate of
Based on the historical data, the determined frequency of use of speech recognition step by the function corresponding to the respective outputted the plurality of recognition result candidates, the plurality of recognition results as the frequency of use gives a higher ranking in ascending order A ranking step for ranking candidates ;
Presenting the plurality of recognition result candidates to the user in descending order of ranking given by the ranking means;
A selection step of selecting any one of the plurality of recognition result candidates presented by the presenting means as a keyword based on a user's selection instruction;
A help providing step of providing, as help information, a description of the function corresponding to the keyword selected in the selection step based on the document stored in the memory;
An information processing method characterized by comprising: A program for causing an information processing apparatus to execute the information processing method according to claim 6 .

Images