WO2022208692A1 - 表示用データ生成装置、表示用データ生成方法、及び表示用データ生成プログラム - Google Patents
表示用データ生成装置、表示用データ生成方法、及び表示用データ生成プログラム Download PDFInfo
- Publication number
- WO2022208692A1 WO2022208692A1 PCT/JP2021/013692 JP2021013692W WO2022208692A1 WO 2022208692 A1 WO2022208692 A1 WO 2022208692A1 JP 2021013692 W JP2021013692 W JP 2021013692W WO 2022208692 A1 WO2022208692 A1 WO 2022208692A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- text
- display
- annotation
- information
- display data
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 26
- 238000002360 preparation method Methods 0.000 claims abstract description 113
- 230000008859 change Effects 0.000 claims description 5
- 238000003860 storage Methods 0.000 description 46
- 238000013500 data storage Methods 0.000 description 29
- 238000010586 diagram Methods 0.000 description 19
- 230000008569 process Effects 0.000 description 16
- 238000004891 communication Methods 0.000 description 13
- 208000027418 Wounds and injury Diseases 0.000 description 11
- 230000006378 damage Effects 0.000 description 11
- 208000014674 injury Diseases 0.000 description 11
- 230000006870 function Effects 0.000 description 10
- 230000004044 response Effects 0.000 description 7
- 239000003086 colorant Substances 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000012790 confirmation Methods 0.000 description 5
- 238000004040 coloring Methods 0.000 description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 230000008439 repair process Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 230000012447 hatching Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
- G09G5/00—Control arrangements or circuits for visual indicators common to cathode-ray tube indicators and other visual indicators
- G09G5/02—Control arrangements or circuits for visual indicators common to cathode-ray tube indicators and other visual indicators characterised by the way in which colour is displayed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
- G06F40/106—Display of layout of documents; Previewing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/169—Annotation, e.g. comment data or footnotes
Definitions
- the present disclosure relates to a display data generation device, a display data generation method, and a display data generation program.
- Contact center operators receive inquiries from customers about products, services, etc., and are required to provide support to solve customer problems. For the purpose of analyzing inquiries from customers and improving the quality of responses, operators create histories of responses to customers and share them within the contact center.
- Non-Patent Document 1 discloses a system that supports an operator by presenting appropriate information to the operator who is answering the call based on the needs of the customer who called the contact center (call center).
- the system disclosed in Non-Patent Document 1 displays the spoken texts of the operator and the customer on the left side of the screen, and the spoken text indicating the customer's business or the spoken text confirming the operator's business on the right side of the screen. Similar questions with high scores and their answers are displayed from FAQs retrieved from .
- keywords are extracted only for utterances in a predetermined scene, and FAQs are searched. (Scenes are utterance texts classified according to the type of scene in the dialogue between the operator and the customer.
- the operator begins with a greeting by giving his/her name, the customer speaks the subject of the call, and the operator responds to the call. After confirming the business, the operator responds to the business after confirming the contractor and contract details, and finally thanking the operator and ending the dialogue. It refers to those classified into scenes such as "correspondence”, "closing”, etc. The estimation result of such a scene is given as a label to the spoken text.
- Non-Patent Document 1 the user can use the spoken text of the operator and the customer, and the FAQ automatically retrieved from the spoken text that conveys the customer's business or the spoken text that confirms the operator's business. See similar questions with high scores) and their answers.
- labels annotation information
- scene estimation results are not presented, and it is difficult to visualize the annotation information so that the user can easily recognize it.
- An object of the present disclosure which has been made in view of the above problems, is to provide a display data generation device, a display data generation method, and a display data generation program capable of visualizing annotation information.
- an input unit that receives input of target data including a text sequence according to the present disclosure and annotation information corresponding to each text included in the text sequence, and a display device based on the annotation information annotation expression information indicating the background color of the display screen of the display device and the position and range for displaying the background color, for expressing the correspondence between the text and the annotation information when the text is displayed; Display data for determining and displaying the text sequence and the annotation information according to the sequence in the text sequence, wherein the background color indicated by the annotation expression information is displayed at the position and the annotation expression information indicated by the annotation expression information. and a display preparation unit that generates the display data to be displayed in the range.
- a method for generating display data includes the steps of receiving input of target data including a text sequence and annotation information corresponding to each text included in the text sequence; A background color of the display screen of the display device for expressing the correspondence between the text and the annotation information when the display device displays the text based on the information, and a position where the background color is displayed. and a range, and display data for displaying the text series and the annotation information according to the series in the text series, wherein the background color indicated by the annotation expression information is displayed in the annotation and generating the display data to be displayed at the position and the range indicated by the expression information.
- a display data generation program causes a computer to function as the display data generation device described above.
- annotation information can be visualized.
- FIG. 1 is an overall schematic diagram of a display data generation device according to a first embodiment
- FIG. 3 is a diagram showing an example of target data whose input is received by the input unit shown in FIG. 1
- FIG. 2 is a diagram showing an example of correspondence between annotation information and colors stored in a color storage unit shown in FIG. 1
- FIG. 2 is a diagram showing an example of display data generated by a display preparation unit shown in FIG. 1
- FIG. 2 is an example of a screen displayed by the display data output unit shown in FIG. 1
- 2 is a flow chart showing an example of the operation of the display data generating device shown in FIG. 1;
- FIG. 3 is a diagram showing an example of target data whose input is received by the input unit shown in FIG. 1
- FIG. 2 is a diagram showing an example of correspondence between annotation information and colors stored in a color storage unit shown in FIG. 1
- FIG. 2 is a diagram showing an example of display data generated by a display preparation unit shown in FIG. 1
- FIG. 2 is an example
- FIG. 4 is an overall schematic diagram of a display data generation device according to a second embodiment
- 8 is a diagram showing an example of gradation rules stored in a gradation rule storage unit shown in FIG. 7
- FIG. 8 is a diagram showing an example of display data generated by a display preparation unit shown in FIG. 7
- FIG. 8 is an example of a screen displayed by the display data output unit shown in FIG. 7
- 8 is a flow chart showing an example of the operation in the display data generation device shown in FIG. 7
- FIG. 11 is an overall schematic diagram of a display data generation device according to a third embodiment
- 13 is a diagram showing an example of target data whose input is accepted by the input unit shown in FIG. 12
- FIG. 13 is a diagram showing an example of gradation rules stored in a gradation rule storage unit shown in FIG. 12;
- FIG. 15 is a diagram for explaining in detail annotation expression information determined by the gradation rule shown in FIG. 14;
- FIG. 13 is a diagram showing an example of display data generated by a display preparation unit shown in FIG. 12;
- FIG. 13 is an example of a screen displayed by the display data output unit shown in FIG. 12;
- 13 is a flow chart showing an example of the operation of the display data generating device shown in FIG. 12;
- 8 is an example of a screen displayed by the first modified example of the display data output unit shown in FIG. 7.
- FIG. FIG. 8 is an example of a screen displayed by the second modified example of the display data output unit shown in FIG. 7.
- FIG. 8 is an example of a screen displayed by the third modified example of the display data output unit shown in FIG. 7.
- FIG. 8 is an example of a screen displayed by the fourth modified example of the display data output unit shown in FIG. 7.
- FIG. 8 is an example of a screen displayed by the fifth modified example of the display data output unit shown in FIG. 7.
- FIG. 3 is a hardware block diagram of a display data generation device; FIG.
- FIG. 1 is a schematic diagram of a display data generation device 1 according to this embodiment.
- the display data generation device 1 includes an input unit 11, a target data storage unit 12, a display rule storage unit 13, a display preparation unit 14, a display A data storage unit 15 and a display data output unit 16 are provided.
- the input unit 11 is configured by an input interface that receives input of information.
- the input interface may be a keyboard, mouse, microphone, etc., or may be an interface for accepting information received from another device via a communication network.
- the target data storage unit 12, the display rule storage unit 13, and the display data storage unit 15 are configured by, for example, ROM or storage.
- the display preparation unit 14 constitutes a control unit (controller).
- the control unit may be configured by dedicated hardware such as ASIC (Application Specific Integrated Circuit) or FPGA (Field-Programmable Gate Array), may be configured by a processor, or may be configured by including both. good too.
- the display data output unit 16 is configured by an output interface that outputs information.
- the input unit 11 receives input of target data including a text sequence and annotation information corresponding to each text included in the text sequence, as shown in FIG.
- the target data may further include a text ID (Identifier) for identifying the text.
- the target data may further include a sequential order in which each of the spoken texts is arranged.
- the series order is information indicating the order when texts included in a text series are ordered.
- the text is a text obtained by recognizing voice data, a text obtained by transcribing a voice, a text included in a chat, a text of minutes, a text of a story, or the like, but is not limited to this.
- the sequence order is information for arranging the utterances of a plurality of speakers in chronological order in a voice dialogue, chat, or the like of a plurality of speakers.
- the sequence order is the order in which texts are arranged in sentences in minutes, story texts, and the like.
- a sequence order can be a meaningful order for arranging text from beginning to end in a text sequence.
- the sequential order is indicated by the text ID, but this is not the only option. Note that it is not essential that the target data include the text ID, and in a configuration where the target data does not include the text ID, the utterance text may include information indicating the sequence order.
- An utterance text is a text that indicates the content of an utterance uttered by each of a plurality of speakers in a dialogue conducted by the plurality of speakers.
- One utterance text is a text output in response to speech recognition results in units of speech completion (units in which it is determined whether the operator or the customer has finished speaking, or whether the customer has finished speaking).
- the spoken text may be textual data.
- a plurality of speakers can be, for example, an operator in a call center and a customer who makes an inquiry to the call center. explain. However, in each of the embodiments described herein, the multiple speakers who utter the spoken text included in the target data are not limited to the operator and the customer.
- One utterance text is an utterance text that becomes a segment in the utterance text uttered by any one of a plurality of speakers.
- a segment of the spoken text may be determined by an arbitrary rule, may be determined by the operation of the speaker who uttered the spoken text, or may be determined by a computer that executes speech recognition using an arbitrary algorithm. good.
- the text is spoken text, it may further include speaker information indicating the speaker who uttered the spoken text.
- a text ID for identifying the speech text is called a speech ID.
- spoken text is used as an example of text, but the text included in the target data processed by the display data generation device of the present embodiment is not limited to spoken text, and may be arbitrary text. can be done.
- Annotation information refers to information (metadata) associated with each utterance text, which is attached to each utterance text.
- the annotation information may be the topic of the spoken text, the scene in which the spoken text was uttered, or some sort of classification label.
- the target data storage unit 12 stores target data whose input is accepted by the input unit 11 .
- the display rule storage unit 13 stores rules for the display preparation unit 14 to determine the annotation expression information of the spoken text based on the annotation information.
- the annotation expression information includes the background color of the display screen of the display device 4 and the position where the background color is displayed, in order to express the correspondence between the spoken text and the annotation information when the display device 4 displays the spoken text. and information indicating the range.
- the position and range of displaying the background color may include the display position and display range of the annotation information, respectively.
- the annotation expression information is the background color of annotation information.
- the display rule storage unit 13 includes a color storage unit 131.
- the color storage unit 131 stores rules indicating association between annotation information and annotation expression information.
- the color storage unit 131 stores a color scheme rule indicating the correspondence between annotation information and annotation expression information (background color of display screen).
- the annotation expression information associated with the annotation information in the color scheme rule may be determined by a computer using any algorithm, or may be determined by the administrator of the display data generation device 1 .
- the display preparation unit 14 selects the background color of the display screen of the display device 4 and the background color of the display device 4 for expressing the correspondence relationship between the text and the annotation information when the display device 4 displays the spoken text.
- Annotation expression information that indicates the position and range for displaying the background color is determined.
- the display preparation unit 14 may divide the spoken text and determine annotation expression information of the divided spoken text.
- the divided utterance texts are referred to as "divided utterance texts”.
- the divided utterance text is referred to as "divided utterance text”
- the undivided utterance text is simply referred to as "utterance text”. If there is no distinction between the segmented utterance text and the undivided utterance text, both the segmented utterance text and the undivided utterance text may simply be referred to as "utterance text.”
- the display preparation unit 14 divides the spoken text included in the target data whose input is received by the input unit 11 .
- the display preparation unit 14 can divide the spoken text by any algorithm.
- the display preparation unit 14 uniquely identifies the divided utterance texts and attaches a determination unit ID indicating the utterance text series of the divided utterance texts.
- the display preparation unit 14 may divide the spoken text into a part before the period and a part after the period.
- the utterance text corresponding to the utterance ID "1" is "I am BB from AA Insurance. Are you at home, Mr.
- the display preparation unit 14 divides this utterance text with punctuation into "I am BB from AA Insurance” and "Is Mr. CC home?" is associated with the determination unit ID "1" and the determination unit ID "2". Further, the display preparation unit 14 determines that the annotation information of the divided utterance text is the annotation information of the original utterance text. In the example shown in FIG. 4, the display preparation unit 14 determines that the topic, which is the annotation information of the utterance text corresponding to the determination unit IDs "1" and "2", is "opening".
- the display preparation unit 14 divides the spoken text into the part before the period and the part after the period, but this is not the only option.
- the display preparation unit 14 may divide the spoken text for each word, or may divide the spoken text into a part before the punctuation mark and a part after the punctuation mark.
- the display preparation unit 14 may not divide the speech text, and in such a configuration, for example, the speech text included in the target data may be an undivided speech text.
- the display preparation unit 14 forms a group (hereinafter referred to as a "speech text group") composed of speech texts that have the same annotation information and are continuous when arranged in the above-described sequence order.
- the display preparation unit 14 uses the coloring rule stored in the color storage unit 131 to determine annotation representation information indicating the color corresponding to the speech text group. Specifically, the display preparation unit 14 determines that the annotation representation information of the speech text group is the color corresponding to the annotation information of the speech text group in the coloring rule.
- the display preparation unit 14 determines whether or not the annotation expression information for all speech texts has been determined.
- the display preparation unit 24 determines that the annotation expression information for some of the spoken texts has not been determined, the display preparation unit 24 forms an utterance text group for the utterance texts for which the annotation expression information has not been determined, and creates an annotation expression for the utterance text group. Repeat the process of determining information.
- the display preparation unit 24 determines that the annotation expression information of all the uttered texts has been determined, the display data for displaying the text sequence and the annotation expression information in accordance with the sequence order in the text sequence, which is the annotation expression Display data for displaying the background color indicated by the information at the position and range indicated by the annotation expression information is generated.
- the display data can include, for example, a determination unit ID, speaker information, utterance text, annotation information, and annotation expression information, as shown in FIG.
- the display data storage unit 15 stores the display data generated by the display preparation unit 14.
- the display data output unit 16 outputs display data.
- the display data output unit 16 may output the display data to the display device 4 such as a liquid crystal panel or organic EL, or may output the display data to another device via a communication network.
- the display device 4 displays the display screen based on the display data. Specifically, as shown in FIG. 5, the display device 4 displays the speech text included in the display data in the speech text sequence described above. Then, the display device 4 displays the annotation information corresponding to the uttered text in association with the uttered text, and further displays the background of the annotation information in the color indicated by the annotation expression information included in the display data. Moreover, the display device 4 may further display one or more of the utterance ID and the speaker information in association with the utterance text and the annotation information.
- the gray color displayed in the background of "opening”, the green color displayed in the background of "accident situation”, the blue color displayed in the background of “injury situation”, and the orange color displayed in the background of “injury situation” are shown in Fig. 5. , are indicated by black and white binary hatching of different modes.
- the display device 4 can collectively display the utterances on a scene-by-scene basis. can be grasped in perspective.
- the display data output unit 16 transmits the display data to another device via the communication network, the other device, like the display device 4, displays the display screen based on the display data. indicate.
- FIG. 6 is a flow chart showing an example of the operation of the display data generation device 1 according to the first embodiment.
- the operation of the display data generation device 1 described with reference to FIG. 6 corresponds to the display method of the display data generation device 1 according to the first embodiment.
- step S11 the input unit 11 accepts input of target data including the utterance text sequence and annotation information corresponding to each text included in the utterance text sequence.
- the target data further includes an utterance ID.
- step S ⁇ b>12 the display preparation unit 14 divides the spoken text included in the target data whose input is received by the input unit 11 .
- step S13 the display preparation unit 14 forms an utterance text group composed of continuous utterance texts having the same annotation information.
- step S14 the display preparation unit 14, based on the annotation information and the sequence order, displays the display device 4 for expressing the correspondence relationship between the speech text and the annotation information when the display device 4 displays the speech text.
- the background color of the display screen of , and the annotation expression information indicating the position and range for displaying the background color are determined.
- the display preparation unit 14 determines annotation representation information indicating color, corresponding to the spoken text group, based on the annotation information.
- step S15 the display preparation unit 14 determines whether annotation expression information corresponding to all speech text groups has been determined.
- step S15 When it is determined in step S15 that the annotation expression information corresponding to some of the utterance text groups has not been determined, the process returns to step S13, and the display preparation unit 14 repeats the processing. Further, when it is determined in step S15 that the annotation expression information corresponding to all the utterance text groups has been determined, in step S16 the display preparation unit 14 converts the utterance text series and the annotation information according to the series in the utterance text series. Display data for displaying the background color indicated by the annotation expression information at the position and range indicated by the annotation expression information is generated.
- step S17 the display data storage unit 15 stores the display data.
- the display data output unit 16 outputs the display data at arbitrary timing.
- the display data output unit 16 may output the display data to the display device 4 such as a liquid crystal panel or organic EL, or may output the display data to another device via a communication network.
- the arbitrary timing can be, for example, the timing when a display command is input to the input unit 11 by the user's operation.
- the display device 4 displays the display screen based on the display data.
- the display device 4 displays the spoken text and the annotation information based on the display data, and displays the background color indicated by the annotation expression information at the position and range indicated by the annotation expression information.
- the display data generating device 1 executes the process of step S12 in the above description, the present invention is not limited to this.
- the display data generating device 1 does not need to execute the process of step S12.
- the display data generation device 1 generates the correspondence relationship between the spoken text and the spoken annotation information when the display device 4 displays the spoken text based on the annotation information. , and annotation expression information indicating the position and range for displaying the background color of the display screen of the display device 4 are determined. Then, the display data generation device 1 displays the utterance text sequence and the annotation information according to the sequence in the utterance text sequence, and displays the background color indicated by the annotation expression information at the position and range indicated by the annotation expression information. Generate data for Thereby, the user can intuitively grasp the annotation information from the background color of the display screen. Therefore, it is possible to quickly recognize the content of the target data including the spoken text corresponding to the annotation information.
- FIG. 7 is a schematic diagram of the display data generating device 2 according to this embodiment.
- the display data generation device 2 includes an input unit 21, a target data storage unit 22, a display rule storage unit 23, a display preparation unit 24, a display A data storage unit 25 and a display data output unit 26 are provided.
- the input unit 21 is configured by an input interface that accepts input of information, like the input unit 11 of the first embodiment.
- the target data storage unit 22, the display rule storage unit 23, and the display data storage unit 25 are similar to the target data storage unit 12, the display rule storage unit 13, and the display data storage unit 15 of the first embodiment. Consists of memory.
- the display preparation unit 24 and the display data output unit 26 constitute a control unit, like the display preparation unit 14 and the display data output unit 16 of the first embodiment.
- the input unit 21 and the target data storage unit 22 are the same as the input unit 11 and the target data storage unit 12 of the display data generation device 2 according to the first embodiment.
- the input unit 21 receives input
- the target data stored in the target data storage unit 22 is the text series included in the target data of the first embodiment and the text included in the text series. In addition to the corresponding annotation information, it also contains the sequential order.
- the display rule storage unit 23 includes a color storage unit 231 and a gradation rule storage unit 232.
- the color storage unit 231 stores coloration rules, like the color storage unit 131 of the display data generation device 1 according to the first embodiment.
- the colors corresponding to each piece of annotation information may be different or the same.
- annotation information is the topic.
- the gradation rule storage unit 232 stores gradation rules for determining annotation expression information.
- the gradation rule in the second embodiment is a rule indicating gradation corresponding to annotation information and series.
- annotation expression information is information indicating color and gradation.
- the annotation corresponding to the speech text group is a gradation that continuously changes from the color corresponding to the topic to white from the start point to the end point.
- the starting point is the column for displaying the topic when the utterance contained in the target data is displayed in the sequence direction of the utterance text sequence (the direction from top to bottom in the example shown in FIG. 10 to be referred to later).
- the end on the starting point side in the arrangement direction (the upper end in the example shown in FIG. 10).
- the end point is the end on the end point side in the arrangement direction (the lower end in the example shown in FIG. 10) in the topic display column.
- a color corresponding to a topic is a color stored corresponding to the topic in the coloring rule.
- the speech text group corresponds to
- the annotation expression information changes continuously from white to the color corresponding to the topic from the starting point to the middle point, and continuously changes from the color corresponding to the topic to white from the middle point to the end point.
- the annotation expression information is a gradation that continuously changes from white to a color corresponding to the topic from the start point to the end point.
- the speech text group corresponds to the speech text group.
- the annotation expression information to be used is without gradation.
- the gradation rule is not limited to the example shown in FIG. 8, and can be any rule that does not clearly change the color corresponding to the topic.
- the speech texts included in the speech text group do not include the first speech text in the target data and do not include the last speech text
- the speech text group corresponds to
- the annotation expression information continuously changes from the color corresponding to the topic to white from the starting point to the middle point, and continuously changes from white to the color corresponding to the topic from the middle point to the end point. It may be a gradation.
- the display preparation unit 24 determines annotation expression information of the utterance text corresponding to the utterance text sequence and the annotation information based on the annotation information and the utterance text sequence. At this time, the display preparation unit 24 may divide the utterance text and determine the annotation expression information based on the divided utterance text, the annotation information of the utterance text, and the utterance text series.
- the display preparation unit 24 divides the spoken text included in the target data whose input is received by the input unit 11, like the display preparation unit 14 of the first embodiment. Note that the display preparation unit 24 does not need to perform the process of dividing the spoken text, like the display preparation unit 14 of the first embodiment. In such a configuration, for example, the speech texts included in the target data may be divided speech texts.
- the display preparation unit 24 forms speech text groups in the same manner as the display preparation unit 14 of the first embodiment.
- the display preparation unit 24 forms a group composed of speech texts corresponding to determination unit IDs "1" to "6" whose annotation information is the same "opening".
- the display preparation unit 24 forms a group composed of uttered texts corresponding to determination unit IDs "7" and "8” whose annotation information is the same "accident situation”.
- the display preparation unit 24 forms a group composed of uttered texts corresponding to determination unit IDs "9” to "14” whose annotation information is the same "injury situation”.
- the display preparation unit 24 forms a group composed of speech texts corresponding to the determination unit ID "15" whose annotation information is the same "repair status”.
- the display preparation unit 24 determines the annotation expression information so that the background color gradually changes toward the boundary where the annotation information is different before and after the sequence in the spoken text sequence. In this embodiment, the display preparation unit 24 determines annotation expression information corresponding to the spoken text group using the coloring rule and the gradation rule.
- the display preparation unit 24 determines that the speech text included in the speech text group includes the first speech text in the target data and does not include the last speech text.
- the annotation expression information is determined to be a gradation (gradation from gray to white) that continuously changes from the color corresponding to the topic to white from the start point to the end point.
- the display preparation unit 24, as shown in FIG. A gradation that continuously changes from gray to white toward the end point is determined.
- the gray color is a color corresponding to "opening" in the coloration rule.
- the display preparation unit 24 does not include the first uttered text in the target data but includes the last uttered text in the uttered texts included in the uttered text group. If not, the annotation expression information changes continuously from white to the color corresponding to the topic from the start point to the middle point, and from the middle point to the end point, the color corresponding to the topic changes to white continuously. Determine that it is a varying gradient (a gradient with white ends and green in the center). Here, the midpoint is the middle point between the start point and the end point in the arrangement direction. As a result, as shown in FIG.
- the display preparation unit 24 makes the annotation representation information of the group composed of the utterance texts corresponding to the determination unit IDs "7" and "8" It is determined that the gradation continuously changes from white to green and continuously changes from green to white toward the end point from the middle point.
- green is a color corresponding to "accident situation” in the coloration rule.
- the display preparation unit 24 causes the annotation expression information of the group composed of the utterance texts corresponding to the determination unit IDs "9” to "14” to change continuously from white to blue toward the middle point from the start point.
- a gradation that continuously changes from blue to white toward the end point from the middle point (white at both ends and blue at the center) is determined.
- blue is a color corresponding to "injury situation” in the coloration rule.
- the display preparation unit 24 does not include the first uttered text in the target data but includes the last uttered text in the uttered texts included in the uttered text group.
- the annotation expression information corresponding to the spoken text group is a gradation that continuously changes from white to a color corresponding to the topic from the start point to the end point.
- the display preparation unit 24 changes the annotation expression information of the group composed of the speech text corresponding to the determination unit ID "15" from orange to white from the start point to the end point. Determine that it is a continuously changing gradation (white to orange gradation).
- orange is a color corresponding to "repair status" in the coloration rule.
- the display preparation unit 24 includes the first utterance text in the target data and the last utterance text in the utterance text included in the utterance text group. If so, it is determined that the annotation expression information corresponding to the spoken text group is without gradation. Note that in the example of FIG. 8, there is no utterance text group that includes the first utterance text and the last utterance text.
- the display preparation unit 24 determines whether or not the annotation expression information for all the utterance texts has been determined. When the display preparation unit 24 determines that the annotation expression information for some of the spoken texts has not been determined, the display preparation unit 24 forms an utterance text group for the utterance texts for which the annotation expression information has not been determined, and creates an annotation expression for the utterance text group. Repeat the process of determining information. Further, when the display preparation unit 24 determines that all of the uttered text annotation expression information has been determined, as shown in FIG. Generate display data associated with information.
- the display data storage unit 25 stores the display data generated by the display preparation unit 24.
- the display data output unit 26 outputs display data.
- the display data output unit 26 may output the display data to the display device 4 such as a liquid crystal panel or organic EL, or may output the display data to another device via a communication network.
- the display device 4 displays the display screen based on the display data. Specifically, as shown in FIG. 10, the display device 4 displays the speech texts included in the display data in the sequence described above. Then, the display device 4 displays the annotation information corresponding to the uttered text in association with the uttered text, and further displays the background color of the annotation information with a color gradation indicated by the annotation expression information included in the display data. .
- the display device 4 may further display one or more of the utterance ID and speaker information in association with the utterance text and the annotation.
- the display data output unit 26 transmits the display data to another device via the communication network, the other device, like the display device 4, displays the display screen based on the display data. indicate.
- FIG. 11 is a flow chart showing an example of the operation of the display data generation device 2 according to the second embodiment.
- the operation of the display data generation device 2 described with reference to FIG. 11 corresponds to the display method of the display data generation device 2 according to the second embodiment.
- step S21 the input unit 21 accepts input of target data including the utterance text sequence and annotation information corresponding to each text included in the utterance text sequence.
- step S22 the display preparation unit 24 divides the spoken text included in the target data whose input is received by the input unit 21.
- step S23 the display preparation unit 24 forms an utterance text group composed of continuous utterance texts having the same annotation information.
- step S24 the display preparation unit 24, based on the annotation information and the sequence order, displays the display device 4 for expressing the correspondence relationship between the speech text and the annotation information when the display device 4 displays the speech text.
- the background color of the display screen of , and the annotation expression information indicating the position and range for displaying the background color are determined.
- the display preparation unit 24 determines annotation representation information indicating color and gradation corresponding to the spoken text group.
- step S25 the display preparation unit 24 determines whether annotation expression information corresponding to all speech text groups has been determined.
- step S25 If it is determined in step S25 that annotation expression information corresponding to some utterance text groups has not been determined, the process returns to step S23, and the display preparation unit 24 repeats the processing. Further, when it is determined in step S25 that annotation expression information corresponding to all speech text groups has been determined, in step S26 the display preparation unit 24 converts the speech text series and the annotation information according to the series in the speech text series. Display data for displaying the background color indicated by the annotation expression information at the position and range indicated by the annotation expression information is generated.
- step S27 the display data storage unit 25 stores the display data.
- the display data output unit 26 outputs display data at arbitrary timing.
- the display data output unit 26 may output the display data to the display device 4, or may output the display data to another device via the communication network.
- the arbitrary timing can be, for example, the timing when the display command is input to the input unit 21 .
- the display device 4 displays the display screen based on the display data.
- the display device 4 displays the spoken text and the annotation information based on the display data, and displays the background color indicated by the annotation expression information at the position and range indicated by the annotation expression information.
- the display data generation device 2 executes the process of step S22 in the above description, the present invention is not limited to this.
- the display data generation device 2 does not need to execute the process of step S22.
- one utterance text may not have only one topic.
- a plurality of topics may be interpreted corresponding to one utterance text, and the topic may switch in the middle of one utterance text.
- the user cannot recognize other topics corresponding to the spoken text.
- the user when dividing an utterance text whose topic is switched in the middle according to the switching and displaying the corresponding topic for each divided utterance text, the user can understand the contents of the utterance text only by referring to the divided utterance text. sometimes difficult.
- the spoken texts are collectively displayed for each label (annotation information) such as a scene estimation result, the user can recognize the spoken texts for each label.
- the spoken text does not necessarily correspond to one label, and when a plurality of labels can correspond, it is difficult to visualize the annotation information so that the user can easily recognize it. For example, there are cases where multiple interpretations of the label corresponding to one uttered text are conceivable, or cases where the uttered text is long and the corresponding label changes in the middle.
- the topic of the text is interpreted as "opening".
- the spoken text since the spoken text includes the phrase "some circumstances about the accident", it is also interpreted that the topic of the spoken text is "accident situation”.
- the two topics "opening” and "accident situation” are displayed in correspondence with the speech text, it may be difficult for the user to understand the topic of the speech text.
- the user when one of the two topics "opening” and "accident situation” is displayed in correspondence with the above-mentioned uttered text, the user cannot recognize the other topic.
- the display data generation device 2 generates annotation expression information such that the background color gradually changes toward the boundary where the annotation information is different before and after the sequence in the text sequence. decide. Thereby, the display data generation device 2 can visualize the annotation information even when a plurality of pieces of annotation information correspond to one uttered text. As a result, the user can recognize that the topic of the spoken text is the topic indicated by the color, and that the topic of the spoken text may be the topic not indicated by the color. In the example shown in FIG.
- the user can recognize that the topic of the utterance text corresponding to the utterance ID "7" may be “accident situation” and "injury situation.” For this reason, it can be understood that the object of "It was hard, wasn't it?" included in the utterance text corresponding to the utterance ID "8" following the utterance ID "7” may be the "injury situation.” Therefore, the user can intuitively grasp the speech text-related information from the background color of the information, and quickly and appropriately recognize the contents of the target data including the speech text.
- the background of the topic "opening” (utterance IDs "1" to “5") is displayed with a gradation that changes from gray to white from the start point to the end point.
- the background of the topic "accident situation” (utterance IDs "6” and “7") is displayed with a gradation that changes from white to green from the starting point toward the middle point. For this reason, the user can confirm that the topic of the utterance text corresponding to ID "5" at the end of the utterance text group corresponding to the topic "opening" (utterance IDs "1” to “5") is “opening". Together, it can be recognized that it may be an "accident situation”. This also allows the user to intuitively grasp the speech text-related information from the background color of the information and quickly and appropriately recognize the contents of the target data including the speech text.
- the display data generation device 2 displays, for example, the speech text divided into three by punctuation in gradation, as indicated by speech ID8 in FIG.
- the scope expands, making it easier to intuitively grasp the boundaries between "accident situations” and “injury situations.”
- FIG. 12 is a schematic diagram of the display data generating device 3 according to this embodiment.
- the display data generation device 3 includes an input unit 31, a target data storage unit 32, a display rule storage unit 33, a display preparation unit 34, a display A data storage unit 35 and a display data output unit 36 are provided.
- the input unit 31 is configured by an input interface that accepts input of information, like the input unit 21 of the second embodiment.
- the target data storage unit 32, the display rule storage unit 33, and the display data storage unit 35 are similar to the target data storage unit 22, the display rule storage unit 23, and the display data storage unit 25 of the second embodiment. Consists of memory.
- the display preparation unit 34 and the display data output unit 36 constitute a control unit, like the display preparation unit 24 of the second embodiment.
- the input unit 31 inputs target data including a speech text sequence and annotation information corresponding to each text included in the speech text sequence, as shown in FIG. accept.
- the target data may further include speaker information.
- the accuracy of the topic may be determined by an arbitrary algorithm for the spoken text, or may be input by the user's operation.
- the annotation information is the topic to which the content of the spoken text belongs, but this is not the only option.
- the target data storage unit 32 stores target data whose input is received by the input unit 31.
- the display rule storage unit 33 stores rules for the display preparation unit 34 to determine the annotation expression information of the uttered text based on the annotation information.
- Display rule storage unit 33 includes color storage unit 331 and gradation rule storage unit 332 .
- the color storage unit 331 is the same as the color storage unit 231 of the display data generation device 2 according to the second embodiment.
- the gradation rule storage unit 332 stores gradation rules such as those shown in FIG.
- the gradation rule in the third embodiment is a gradation determined based on annotation information, a sequence of spoken text, and accuracy of annotation information.
- FIG. 15 is a diagram showing an example of applying the gradation rule of "the last spoken text of the topic, followed by the next topic” shown in FIG. 14 when the accuracy is 60%. "The last spoken text of the topic, followed by the next topic” indicates that the topic of the spoken text is different from the topic of the spoken text next to the said spoken text.
- the annotation expression information is:
- the position from the start point to the position corresponding to the accuracy of the topic (60% position in the example of FIG. 15) is the color corresponding to the topic, and the color goes from the position to the end point. It is a gradation that changes from the color corresponding to the topic to white as much as possible.
- the starting point is the utterance contained in the target data displayed in the utterance text sequence in the arrangement direction (the direction from top to bottom in the example shown in FIG. 17 to be referred to later).
- this is the end on the starting point side in the arrangement direction (the upper end in the example shown in FIG. 17) in the topic display column (one utterance text).
- the end point is the end (the lower end in the example shown in FIG. 17) on the end point side in the arrangement direction in the topic display column (one utterance text).
- the annotation expression information corresponds to the topic. No color gradation.
- the annotation expression information is a gradation that changes from white to the color corresponding to the topic as it moves toward the position corresponding to (100-accuracy of the topic)% from the starting point. , which is the color corresponding to the topic from the position corresponding to (100-probability of topic)% to the end point.
- the first utterance text of a topic and the topic continues from the front indicates that the topic of the utterance text is different from the topic of the utterance text uttered before the topic text.
- the accuracy of the topic is when it is 100%, the annotation expression information is the color corresponding to the topic and no gradation.
- the annotation expression information corresponds to the accuracy of the topic from the starting point. It is a gradation from the color of the topic before switching to white up to the position where it is switched, and it is a gradation from white to the color of the topic after switching from the position corresponding to the accuracy of the topic to the end point.
- the annotation expression information is the topic color of the speech text without gradation from the start point to the end point.
- the display preparation unit 34 determines the annotation expression information so that the background color gradually changes toward the boundary where the annotation information is different before and after the sequence in the spoken text sequence. In this embodiment, the display preparation unit 34 determines annotation expression information further based on accuracy. The display preparation unit 34 may determine annotation expression information indicating the degree of change in the background color further based on the accuracy. In the third embodiment, annotation expression information is information indicating color and gradation. At this time, the display preparation unit 34 may divide the utterance text, and determine the annotation expression information based on the divided utterance text, the annotation information of the utterance text, and the series.
- the display preparation unit 34 divides the spoken text included in the target data whose input is received by the input unit 11, like the display preparation unit 24 of the second embodiment.
- the display preparation unit 34 does not have to perform the process of dividing the spoken text, like the display preparation unit 24 of the second embodiment.
- the speech texts included in the target data may be divided speech texts.
- the display preparation unit 34 does not divide the speech text, and therefore the speech text corresponding to the determination unit ID in the display data is the same as the speech ID in the target data shown in FIG. Same as the corresponding spoken text.
- the display preparation unit 34 uses the color scheme rule and the gradation rule to determine the color and gradation corresponding to the spoken text.
- the display preparation unit 34 expresses the annotation based on the annotation information of the utterance text and the annotation information of the utterance text arranged before or after the utterance text in the utterance text sequence. Determine information. Specifically, if the speech text to be determined is “the last speech text of the topic, and the next topic continues” and the accuracy of the topic is not 100%, the display preparation unit 34 sets the annotation
- the expression information is determined to be a color corresponding to the topic up to the accuracy of the topic, and a gradation that changes from the color corresponding to the topic to white from the accuracy of the topic.
- the display preparation unit 34 determines whether the utterance text to be determined is "the last utterance text of the topic, and the next topic continues", or "the first utterance text of the topic, and the topic continues from the front". Also, when the accuracy of the topic is 100%, it is determined that the annotation expression information is the color corresponding to the topic and no gradation.
- the display preparation unit 34 sets the annotation expression information to the accuracy of the topic before switching. From the accuracy of the topic, it is determined that the gradation will be the color of the topic after switching from white.
- the display preparation unit 34 sets the annotation expression information to the color of the topic of the speech text. Determine that there is no gradation.
- the display preparation unit 34 determines whether or not the annotation expression information of all the spoken texts has been determined. When the display preparation unit 34 determines that the annotation expression information of part of the uttered texts has not been determined, it repeats the process of determining the annotation expression information of the uttered texts for the uttered texts whose annotation expression information has not been determined. Further, when the display preparation unit 34 determines that the annotation expression information for all the speech texts has been determined, it generates display data in which the annotation expression information is associated with each speech text included in the target data.
- the display data storage unit 35 stores the display data generated by the display preparation unit 34.
- the display data output unit 36 outputs display data.
- the display data output unit 36 may output the display data to the display device 4 such as a liquid crystal panel or organic EL, or may output the display data to another device via a communication network.
- the display device 4 displays the display screen based on the display data. Specifically, as shown in FIG. 17, the display device 4 associates and displays the speech text included in the display data and the annotation information corresponding to the speech text, and furthermore, displays the background color of the annotation information. Display with color gradation as indicated by the annotation expression information included in the display data. Further, the display device 4 may cause the display device 4 to further display one or more of the ID and speaker information in association with the utterance text.
- the display data output unit 36 transmits the display data to another device via the communication network, the other device, like the display device 4, displays the display screen based on the display data. indicate.
- FIG. 18 is a flow chart showing an example of the operation of the display data generation device 3 according to the third embodiment.
- the operation of the display data generation device 3 described with reference to FIG. 18 corresponds to the display method of the display data generation device 3 according to the third embodiment.
- step S31 the input unit 31 receives input of a speech text sequence, annotation information corresponding to each speech text included in the speech text sequence, and target data including accuracy of the annotation information.
- step S ⁇ b>32 the display preparation unit 34 divides the speech text included in the target data whose input is received by the input unit 31 .
- step S33 the display preparation unit 34 determines the correspondence relationship between the spoken text and the annotation information when the display device 4 displays the spoken text, based on the accuracy of the annotation information in addition to the annotation information and the sequence order.
- the background color of the display screen of the display device 4 and the annotation expression information indicating the position and range for displaying the background color are determined.
- the display preparation unit 24 determines annotation expression information indicating colors and gradations corresponding to the spoken text.
- step S34 the display preparation unit 34 determines whether or not annotation expression information for all utterance texts has been determined.
- step S34 If it is determined in step S34 that the annotation expression information for some of the spoken texts has not been determined, the process returns to step S33, and the display preparation unit 34 repeats the processing. Further, when it is determined in step S34 that the annotation expression information of all the spoken texts has been determined, in step S35 the display preparation unit 34 displays the spoken text series and the annotation information according to the series in the spoken text series. which is display data for displaying the background color indicated by the annotation expression information at the position and range indicated by the annotation expression information.
- step S36 the display data storage unit 35 stores the display data.
- the display data output unit 36 outputs the display data at arbitrary timing.
- the display data output unit 36 may output the display data to the display device 4, or may output the display data to another device via the communication network.
- the arbitrary timing can be, for example, the timing when the display command is input to the input unit 31 .
- the display device 4 displays the display screen based on the display data. Specifically, the display device 4 displays the spoken text and the annotation information based on the display data, and displays the background color indicated by the annotation expression information at the position and range indicated by the annotation expression information.
- the display data generation device 3 executes the process of step S32 in the above description, this is not the only option. For example, the display data generation device 3 does not need to execute the process of step S32.
- the target data further includes accuracy indicating the likelihood of annotation information
- the display preparation unit 34 determines annotation expression information further based on the accuracy.
- the display data generation device 2 displayed the utterance texts uttered by a plurality of speakers in the same column, but this is not the only option.
- the display data generation device 3 displays the utterance text uttered by one speaker and the utterance text uttered by the other speaker in different columns.
- the annotation information is displayed on the line where the annotation information is displayed, and the gradation is displayed in the background of the annotation information.
- the display data generating device 2 causes the display device 4 to display the spoken texts so that they are arranged in the spoken text sequence from the top to the bottom of the screen.
- the target data in this example almost simultaneously with the operator uttering the utterance text "Are you okay?" The spoken text "Yes, I'm fine.” is emitted.
- the target data includes the time when the spoken text was uttered, in the example shown in FIG. can be displayed on the same line. This allows the user to clearly understand that multiple utterance texts by multiple speakers are uttered at the same time.
- the user who refers to the utterance text based on the target data displayed by the display data generation device 2 can easily grasp the utterance text uttered by each speaker, and can efficiently understand the contents of the target data. can be recognized The same applies to the display data generation device 1 according to the first embodiment and the display data generation device 3 according to the third embodiment.
- the display preparation unit 24 of the display data generation device 2 may further determine an important speech text among the plurality of speech texts.
- the display preparation unit 24 can determine important spoken text by any algorithm.
- the display data generation device 2 may use a model generated in advance by learning based on a large amount of important spoken texts, or may store important words and phrases in the memory in advance and store them in the memory. You may determine the spoken text containing the said phrase as an important spoken text.
- the display preparation unit 24 may determine an important uttered text based on the user's operation. In such a configuration, as shown in FIG. 20, the display data output unit 26 highlights the spoken text determined to be the important spoken text and causes the display device 4 to display the highlighted spoken text.
- the display data generating device 2 causes the display device 4 to display in black characters indicating the spoken text (another spoken text) determined to be not the important spoken text, and the text is determined to be the important spoken text.
- the characters representing the spoken text may be displayed on the display device 4 in a different color (for example, red) from other spoken texts.
- important spoken text is shown in bold, but highlights are not limited to this. As a result, the user can easily grasp the important spoken text and efficiently recognize the contents of the target data.
- the display data output unit 26 of the display data generation device 2 further does not display the speech texts that have not been determined to be important speech texts, and You may display only the utterance text determined to be. As a result, the user can more easily grasp the important spoken text, and can more efficiently recognize the contents of the target data. Further, in such a configuration, the display data output unit 26 may switch between a state in which another spoken text is displayed and a state in which another spoken text is not displayed by the user's operation. For example, if the user determines that he or she cannot understand the entire target data because the other spoken text is not displayed, the user performs an operation to display the other spoken text, and the other spoken text is displayed. You can try to understand the whole of the target data by referring to it. The same applies to the display data generation device 1 according to the first embodiment and the display data generation device 3 according to the third embodiment.
- annotation information is a topic, but it is not limited to this.
- the annotation information may be a "scene" indicating the scene in which the spoken text is uttered.
- the "scene” is the utterance text classified according to the type of scene in the dialogue between the operator and the customer. For example, the operator begins with a greeting by giving his/her own name, then the customer calls and talks about the business, the operator confirms the business, and after confirming the contractor and contract details, the operator responds to the business.
- each item may include "opening”, “inquiry comprehension”, “identity verification”, “response”, and “closing”.
- the display data output unit 26 of the display data generation device 2 displays the speech text included in the target data, and causes the display device 4 to display the background of the speech text, which is the part related to the information, in color gradation. good.
- the informational part is the background of the spoken text.
- the display data output unit 26 may cause the display device 4 to display a "whole call” button and buttons indicating each item included in a scene that is annotation information.
- the input unit 21 receives information indicating that the "whole call” button has been pressed. Then, the display device 4 displays the entire speech text included in the target data based on the information. Further, when the "opening" button is pressed by the user's operation, the input unit 21 receives information indicating the pressing of the "opening” button. Then, the display device 4 displays the utterance text whose scene is "opening", which is included in the target data, based on the information.
- the display device 4 may display detailed information about "understand inquiry” when the "understand inquiry” button is pressed by the user's operation.
- the detailed information about the "query grasp” is at least one of the "subject”, “issue”, and “issue confirmation” generated by an arbitrary algorithm based on the utterance text corresponding to the "query grasp” scene. can contain.
- the display device 4 may display an operation object for changing the "subject", the “issue”, and the “issue confirmation” together with the "issue” and the “issue confirmation”. . Note that the display device 4 may display the detailed information on the "inquiry comprehension” even when the "whole call” button is pressed by the user's operation.
- the display device 4 may display detailed information on "identity confirmation” when the "identity confirmation” button is pressed by the user's operation.
- Detailed information about “identity verification” is at least one of customer's "name”, “address”, and “phone number” generated by any algorithm based on the spoken text corresponding to the "identity verification” scene.
- the display data output unit 26 is an operation object for changing "name”, “address” and “telephone number” as well as “name”, “address” and “telephone number”. may be displayed on the display device 4. Note that the display data output unit 26 may cause the display device 4 to display the detailed information regarding the "personal identification” even when the "whole call” button is pressed by the user's operation.
- the display device 4 may display the time zone in which the utterance text included in the target data was issued along with the display of the utterance text included in the target data.
- the display device 4 may display an audio reproduction button (an arrow indicated by a triangle in FIG. 22) for reproducing audio data corresponding to the uttered text near the uttered text. In such a configuration, the display data generation device 2 reproduces the audio data when the user presses the audio reproduction button.
- the display data generation device 1 according to the first embodiment and the display data generation device 3 according to the third embodiment can also execute the aspect described with reference to FIG. 22 in the same manner.
- the annotation information is "scene", but as shown in FIG. It may be both the "dialogue action type” shown.
- "scenes” include “opening", “injury”, “self-driving”, “grade”, “insurance”, “repair status”, "accident It may include “Status", “Contact”, and “Closing”.
- the display device 4 that has output the display data from the display data generation device 2 may display the background color of the speech text included in the target data in gradation.
- the "dialogue action type” may include "interview”, “explanation”, “question”, and "answer”.
- the display device 4 may display a "whole call” button, a button indicating each item included in the annotation information "scene”, and a button indicating each item included in the annotation information "dialogue act type”. good.
- a button indicating each item included in the annotation information "dialogue act type” are composed of check buttons so that one or two or more buttons can be selected, but this is not the only option. Aspect buttons can be employed as appropriate.
- the "Answer” button is checked, and only utterance texts whose "dialogue act type” is associated with "Answer” as annotation information are displayed.
- the display device 4 displays the speaker information and the time zone in which the speech text included in the target data was uttered along with the display of the speech text included in the target data. may be displayed.
- the display device 4 may display an audio reproduction button (an arrow indicated by a triangle in FIG. 23) for reproducing audio data corresponding to the spoken text in the vicinity of the portion where the spoken text is displayed. .
- the display data generation device 2 reproduces the audio data when the user presses the audio reproduction button.
- the display data generation device 1 according to the first embodiment and the display data generation device 3 according to the third embodiment can similarly execute the aspects described with reference to FIG.
- the colors corresponding to the annotation information stored in the color storage unit 331 are different from each other, but this is not the only option. good too.
- the display data output unit 36 generates annotation representation information indicating colors and gradations generated by the display preparation unit 34 based on the gradation rules stored in the gradation rule storage unit 232.
- the background can be displayed on the display device 4 with color gradation. Therefore, the user can recognize that the topic corresponding to the utterance text group is not one but can be interpreted as a plurality of topics.
- the display data generation device 2 does not need to include the color storage unit 231, so the memory capacity can be reduced. The same applies to the third embodiment.
- the display modes, gradation rules, etc. described in the above-described first to third embodiments are examples, and the present invention is not limited to these.
- the display data generation devices 1 to 3 according to the first to third embodiments may further include various functions used when the operator creates histories of responses.
- the display data generation devices 1 to 3 further include a function of displaying spoken texts for each topic, a function of editing spoken texts and topics, a search function of searching spoken texts, a comparison function of comparing target data, and the like.
- FIG. 24 is a block diagram showing a schematic configuration of a computer 100 functioning as the display data generation device 1.
- the computer 100 may be a general-purpose computer, a dedicated computer, a workstation, a PC (Personal Computer), an electronic notepad, or the like.
- Program instructions may be program code, code segments, etc. for performing the required tasks.
- a computer 100 capable of executing program instructions in order to function as the display data generation device 2, it is also possible to use a computer 100 capable of executing program instructions, and in order to function as the display data generation device 3, it is possible to use a computer 100 that executes program instructions.
- a capable computer 100 can also be used.
- the computer 100 includes a processor 110, a ROM (Read Only Memory) 120, a RAM (Random Access Memory) 130, a storage 140, an input section 150, an output section 160, and a communication interface ( I/F) 170.
- the processor 110 is specifically a CPU (Central Processing Unit), MPU (Micro Processing Unit), GPU (Graphics Processing Unit), DSP (Digital Signal Processor), SoC (System on a Chip), etc. may be configured by a plurality of processors of
- the processor 110 controls each component and executes various arithmetic processes. That is, processor 110 reads a program from ROM 120 or storage 140 and executes the program using RAM 130 as a work area. The processor 110 executes control of each configuration and various arithmetic processes according to programs stored in the ROM 120 or the storage 140 . In this embodiment, the ROM 120 or storage 140 stores a program according to the present disclosure.
- the program may be recorded on a recording medium readable by the computer 100.
- a program can be installed in the computer 100 by using such a recording medium.
- the recording medium on which the program is recorded may be a non-transitory recording medium.
- the non-transitory recording medium is not particularly limited, but may be, for example, a CD-ROM, a DVD-ROM, a USB (Universal Serial Bus) memory, or the like.
- this program may be downloaded from an external device via a network.
- the ROM 120 stores various programs and various data.
- RAM 130 temporarily stores programs or data as a work area.
- the storage 140 is configured by a HDD (Hard Disk Drive) or SSD (Solid State Drive) and stores various programs including an operating system and various data.
- the input unit 150 includes one or more input interfaces that receive user's input operations and acquire information based on the user's operations.
- the input unit 150 is a pointing device, keyboard, mouse, etc., but is not limited to these.
- the output unit 160 includes one or more output interfaces that output information.
- the output unit 160 controls a display that outputs information as video or a speaker that outputs information as audio, but is not limited to these.
- the communication interface 170 is an interface for communicating with other devices such as external devices, and uses standards such as Ethernet (registered trademark), FDDI, and Wi-Fi (registered trademark), for example.
- a display data generation device comprising a control unit, The control unit Receiving input of target data including a text sequence and annotation information corresponding to each text included in the text sequence; Displaying the background color of the display screen of the display device and the background color for expressing the correspondence relationship between the text and the annotation information when the display device displays the text based on the annotation information.
- display data for determining annotation expression information indicating the position and range to be displayed, and displaying the text series and the annotation information according to the series in the text series, wherein the background color indicated by the annotation expression information is
- a display data generation device for generating the display data to be displayed at the position and the range indicated by the annotation expression information.
- (Appendix 6) The display according to any one of additional items 1 to 5, wherein the display data includes the annotation information, and the position and range of displaying the background color include the display position and display range of the annotation information, respectively.
- data generator for (Appendix 7) receiving input of target data including a text sequence and annotation information corresponding to each text included in the text sequence; Displaying the background color of the display screen of the display device and the background color for expressing the correspondence relationship between the text and the annotation information when the display device displays the text based on the annotation information.
- Display data generation method including (Appendix 8) A non-temporary storage medium storing a program executable by a computer, the non-temporary storage medium storing the program causing the computer to function as the display data generating device according to any one of additional items 1 to 6. storage medium.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
Description
図1を参照して第1の実施形態の全体構成について説明する。図1は、本実施形態に係る表示用データ生成装置1の概略図である。
図1に示されるように、第1の実施形態に係る表示用データ生成装置1は、入力部11と、対象データ記憶部12と、表示ルール記憶部13と、表示準備部14と、表示用データ記憶部15と、表示用データ出力部16とを備える。入力部11は、情報の入力を受け付ける入力インターフェースによって構成される。入力インターフェースは、キーボード、マウス、マイクロフォン等であってもよいし、他の装置から通信ネットワークを介して受信した情報を受け付けるためのインターフェースであってもよい。対象データ記憶部12、表示ルール記憶部13、及び表示用データ記憶部15は、例えば、ROM又はストレージによって構成される。表示準備部14は、制御部(コントローラ)を構成する。制御部は、ASIC(Application Specific Integrated Circuit)、FPGA(Field-Programmable Gate Array)等の専用のハードウェアによって構成されてもよいし、プロセッサによって構成されてもよいし、双方を含んで構成されてもよい。表示用データ出力部16は、情報を出力する出力インターフェースによって構成される。
ここで、第1の実施形態に係る表示用データ生成装置1の動作について、図6を参照して説明する。図6は、第1の実施形態に係る表示用データ生成装置1における動作の一例を示すフローチャートである。図6を参照して説明する表示用データ生成装置1における動作は第1の実施形態に係る表示用データ生成装置1の表示方法に相当する。
図7を参照して第2の実施形態の表示用データ生成装置2の全体構成について説明する。図7は、本実施形態に係る表示用データ生成装置2の概略図である。
図7に示されるように、第2の実施形態に係る表示用データ生成装置2は、入力部21と、対象データ記憶部22と、表示ルール記憶部23と、表示準備部24と、表示用データ記憶部25と、表示用データ出力部26とを備える。入力部21は、第1の実施形態の入力部11と同様に、情報の入力を受け付ける入力インターフェースによって構成される。対象データ記憶部22、表示ルール記憶部23、及び表示用データ記憶部25は、第1の実施形態の対象データ記憶部12、表示ルール記憶部13、及び表示用データ記憶部15と同様に、メモリによって構成される。また、表示準備部24及び表示用データ出力部26は、第1の実施形態の表示準備部14及び表示用データ出力部16と同様に、制御部を構成する。
ここで、第2の実施形態に係る表示用データ生成装置2の動作について、図11を参照して説明する。図11は、第2の実施形態に係る表示用データ生成装置2における動作の一例を示すフローチャートである。図11を参照して説明する表示用データ生成装置2における動作は第2の実施形態に係る表示用データ生成装置2の表示方法に相当する。
図12を参照して第3の実施形態の表示用データ生成装置3の全体構成について説明する。図12は、本実施形態に係る表示用データ生成装置3の概略図である。
図12に示されるように、第3の実施形態に係る表示用データ生成装置3は、入力部31と、対象データ記憶部32と、表示ルール記憶部33と、表示準備部34と、表示用データ記憶部35と、表示用データ出力部36とを備える。入力部31は、第2の実施形態の入力部21と同様に、情報の入力を受け付ける入力インターフェースによって構成される。対象データ記憶部32、表示ルール記憶部33、及び表示用データ記憶部35は、第2の実施形態の対象データ記憶部22、表示ルール記憶部23、及び表示用データ記憶部25と同様に、メモリによって構成される。また、表示準備部34及び表示用データ出力部36は、第2の実施形態の表示準備部24と同様に、制御部を構成する。
ここで、第3の実施形態に係る表示用データ生成装置3の動作について、図18を参照して説明する。図18は、第3の実施形態に係る表示用データ生成装置3における動作の一例を示すフローチャートである。図18を参照して説明する表示用データ生成装置3における動作は第3の実施形態に係る表示用データ生成装置3の表示方法に相当する。
上述した表示用データ生成装置1として機能させるために、それぞれプログラム命令を実行可能なコンピュータ100を用いることも可能である。図24は、表示用データ生成装置1としてそれぞれ機能するコンピュータ100の概略構成を示すブロック図である。ここで、コンピュータ100は、汎用コンピュータ、専用コンピュータ、ワークステーション、PC(Personal Computer)、電子ノートパッド等であってもよい。プログラム命令は、必要なタスクを実行するためのプログラムコード、コードセグメント等であってもよい。同様にして、表示用データ生成装置2として機能させるために、それぞれプログラム命令を実行可能なコンピュータ100を用いることも可能であり、表示用データ生成装置3として機能させるために、それぞれプログラム命令を実行可能なコンピュータ100を用いることも可能である。
図24に示すように、コンピュータ100は、プロセッサ110と、ROM(Read Only Memory)120と、RAM(Random Access Memory)130と、ストレージ140と、入力部150と、出力部160と、通信インターフェース(I/F)170と、を備える。各構成は、バス180を介して相互に通信可能に接続されている。プロセッサ110は、具体的にはCPU(Central Processing Unit)、MPU(Micro Processing Unit)、GPU(Graphics Processing Unit)、DSP(Digital Signal Processor)、SoC(System on a Chip)等であり、同種又は異種の複数のプロセッサにより構成されてもよい。
制御部を備える表示用データ生成装置であって、
前記制御部は、
テキスト系列、及び前記テキスト系列に含まれるテキストそれぞれに対応するアノテーション情報を含む対象データの入力を受け付け、
前記アノテーション情報に基づいて、表示装置が前記テキストを表示する際の、前記テキストと前記アノテーション情報との対応関係を表現するための、前記表示装置の表示画面の背景色、並びに該背景色を表示する位置及び範囲を示すアノテーション表現情報を決定し、前記テキスト系列及び前記アノテーション情報を、前記テキスト系列における系列に従って表示させるための表示用データであって、前記アノテーション表現情報が示す前記背景色を、前記アノテーション表現情報が示す前記位置及び前記範囲に表示させるための前記表示用データを生成する表示用データ生成装置。
(付記項2)
前記制御部は、前記テキスト系列における系列の前後で前記アノテーション情報が異なる境界に向けて徐々に前記背景色が変化するように、前記アノテーション表現情報を決定する、付記項1に記載の表示用データ生成装置。
(付記項3)
前記対象データは、前記アノテーション情報の確からしさを示す確度をさらに含み、
前記制御部は、前記確度にさらに基づいて前記アノテーション表現情報を決定する、付記項2に記載の表示用データ生成装置。
(付記項4)
前記制御部は、前記確度にさらに基づいて前記背景色が変化する度合いを示す前記アノテーション表現情報を決定する、付記項3に記載の表示用データ生成装置。
(付記項5)
前記制御部は、前記発話テキストを分割し、前記分割された発話テキストの前記アノテーション表現情報を決定する、付記項1から4のいずれか一項に記載の表示用データ生成装置。
(付記項6)
前記表示用データは、前記アノテーション情報を含み、前記背景色を表示する位置及び範囲は、それぞれ前記アノテーション情報の表示位置及び表示範囲を含む、付記項1から5のいずれか一項に記載の表示用データ生成装置。
(付記項7)
テキスト系列、及び前記テキスト系列に含まれるテキストそれぞれに対応するアノテーション情報を含む対象データの入力を受け付けるステップと、
前記アノテーション情報に基づいて、表示装置が前記テキストを表示する際の、前記テキストと前記アノテーション情報との対応関係を表現するための、前記表示装置の表示画面の背景色、並びに該背景色を表示する位置及び範囲を示すアノテーション表現情報を決定し、前記テキスト系列及び前記アノテーション情報を、前記テキスト系列における系列に従って表示させるための表示用データであって、前記アノテーション表現情報が示す前記背景色を、前記アノテーション表現情報が示す前記位置及び前記範囲に表示させるための前記表示用データを生成するステップと、
を含む表示用データ生成方法。
(付記項8)
コンピュータによって実行可能なプログラムを記憶した非一時的記憶媒体であって、前記コンピュータを付記項1から6のいずれか一項に記載の表示用データ生成装置として機能させる、プログラムを記憶した非一時的記憶媒体。
4 表示装置
11、21、31 入力部
12、22、32 対象データ記憶部
13、23、33 表示ルール記憶部
14、24,34 表示準備部
15、25、35 表示用データ記憶部
16、26、36 表示用データ出力部
131、231、331 色記憶部
232、332 グラデーションルール記憶部
100 コンピュータ
110 プロセッサ
120 ROM
130 RAM
140 ストレージ
150 入力部
160 出力部
170 通信インターフェース(I/F)
180 バス
Claims (8)
- テキスト系列、及び前記テキスト系列に含まれるテキストそれぞれに対応するアノテーション情報を含む対象データの入力を受け付ける入力部と、
前記アノテーション情報に基づいて、表示装置が前記テキストを表示する際の、前記テキストと前記アノテーション情報との対応関係を表現するための、前記表示装置の表示画面の背景色、並びに該背景色を表示する位置及び範囲を示すアノテーション表現情報を決定し、前記テキスト系列及び前記アノテーション情報を、前記テキスト系列における系列に従って表示させるための表示用データであって、前記アノテーション表現情報が示す前記背景色を、前記アノテーション表現情報が示す前記位置及び前記範囲に表示させるための前記表示用データを生成する表示準備部と、
を備える表示用データ生成装置。 - 前記表示準備部は、前記テキスト系列における系列の前後で前記アノテーション情報が異なる境界に向けて徐々に前記背景色が変化するように、前記アノテーション表現情報を決定する、請求項1に記載の表示用データ生成装置。
- 前記対象データは、前記アノテーション情報の確からしさを示す確度をさらに含み、
前記表示準備部は、前記確度にさらに基づいて前記アノテーション表現情報を決定する、請求項2に記載の表示用データ生成装置。 - 前記表示準備部は、前記確度にさらに基づいて前記背景色が変化する度合いを示す前記アノテーション表現情報を決定する、請求項3に記載の表示用データ生成装置。
- 前記表示準備部は、前記テキストを分割し、前記分割されたテキストの前記アノテーション表現情報を決定する、請求項1から4のいずれか一項に記載の表示用データ生成装置。
- 前記表示用データは、前記アノテーション情報を含み、前記背景色を表示する位置及び範囲は、それぞれ前記アノテーション情報の表示位置及び表示範囲を含む、請求項1から5のいずれか一項に記載の表示用データ生成装置。
- テキスト系列、及び前記テキスト系列に含まれるテキストそれぞれに対応するアノテーション情報を含む対象データの入力を受け付けるステップと、
前記アノテーション情報に基づいて、表示装置が前記テキストを表示する際の、前記テキストと前記アノテーション情報との対応関係を表現するための、前記表示装置の表示画面の背景色、並びに該背景色を表示する位置及び範囲を示すアノテーション表現情報を決定し、前記テキスト系列及び前記アノテーション情報を、前記テキスト系列における系列に従って表示させるための表示用データであって、前記アノテーション表現情報が示す前記背景色を、前記アノテーション表現情報が示す前記位置及び前記範囲に表示させるための前記表示用データを生成するステップと、
を含む表示用データ生成方法。 - コンピュータを、請求項1から6のいずれか一項に記載の表示用データ生成装置として機能させるための表示用データ生成プログラム。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/013692 WO2022208692A1 (ja) | 2021-03-30 | 2021-03-30 | 表示用データ生成装置、表示用データ生成方法、及び表示用データ生成プログラム |
JP2023509990A JPWO2022208692A1 (ja) | 2021-03-30 | 2021-03-30 | |
US18/552,865 US20240194165A1 (en) | 2021-03-30 | 2021-03-30 | Display data generation device, display data generation method, and display data generation program |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/013692 WO2022208692A1 (ja) | 2021-03-30 | 2021-03-30 | 表示用データ生成装置、表示用データ生成方法、及び表示用データ生成プログラム |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022208692A1 true WO2022208692A1 (ja) | 2022-10-06 |
Family
ID=83458404
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/013692 WO2022208692A1 (ja) | 2021-03-30 | 2021-03-30 | 表示用データ生成装置、表示用データ生成方法、及び表示用データ生成プログラム |
Country Status (3)
Country | Link |
---|---|
US (1) | US20240194165A1 (ja) |
JP (1) | JPWO2022208692A1 (ja) |
WO (1) | WO2022208692A1 (ja) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05143588A (ja) * | 1991-10-30 | 1993-06-11 | Oki Techno Syst Raboratori:Kk | 文書編集装置 |
JP2011008355A (ja) * | 2009-06-23 | 2011-01-13 | Omron Corp | Fmeaシートの作成支援システムおよび作成支援用のプログラム |
WO2016056402A1 (ja) * | 2014-10-10 | 2016-04-14 | 大日本印刷株式会社 | 文章表示装置、プログラム及び制御方法 |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6138130A (en) * | 1995-12-08 | 2000-10-24 | Inventure Technologies, Inc. | System and method for processing data in an electronic spreadsheet in accordance with a data type |
GB2340008A (en) * | 1998-07-24 | 2000-02-09 | Ibm | Method and tool for generating and displayin a descriptive annotation of selec ted application data |
CA2436609C (en) * | 2000-12-08 | 2011-10-25 | Fujitsu Limited | Sequence analysis method and apparatus |
RU2004133946A (ru) * | 2004-11-23 | 2006-05-10 | Самсунг Электроникс Ко., Лтд. (KR) | Способ формирования адаптивной контекстной справки |
JP5617603B2 (ja) * | 2010-12-21 | 2014-11-05 | ソニー株式会社 | 表示制御装置、表示制御方法、及び、プログラム |
US9317861B2 (en) * | 2011-03-30 | 2016-04-19 | Information Resources, Inc. | View-independent annotation of commercial data |
US10606618B2 (en) * | 2016-01-19 | 2020-03-31 | Adp, Llc | Contextual assistance system |
US10146758B1 (en) * | 2016-09-30 | 2018-12-04 | Amazon Technologies, Inc. | Distributed moderation and dynamic display of content annotations |
US10776619B2 (en) * | 2018-09-27 | 2020-09-15 | The Toronto-Dominion Bank | Systems and methods for augmenting a displayed document |
-
2021
- 2021-03-30 JP JP2023509990A patent/JPWO2022208692A1/ja active Pending
- 2021-03-30 US US18/552,865 patent/US20240194165A1/en active Pending
- 2021-03-30 WO PCT/JP2021/013692 patent/WO2022208692A1/ja active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05143588A (ja) * | 1991-10-30 | 1993-06-11 | Oki Techno Syst Raboratori:Kk | 文書編集装置 |
JP2011008355A (ja) * | 2009-06-23 | 2011-01-13 | Omron Corp | Fmeaシートの作成支援システムおよび作成支援用のプログラム |
WO2016056402A1 (ja) * | 2014-10-10 | 2016-04-14 | 大日本印刷株式会社 | 文章表示装置、プログラム及び制御方法 |
Also Published As
Publication number | Publication date |
---|---|
US20240194165A1 (en) | 2024-06-13 |
JPWO2022208692A1 (ja) | 2022-10-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10950219B2 (en) | Systems and methods for providing a virtual assistant | |
US11450311B2 (en) | System and methods for accent and dialect modification | |
JP5684082B2 (ja) | 対話支援装置、方法及びプログラム | |
US10755595B1 (en) | Systems and methods for natural language processing for speech content scoring | |
US20200193972A1 (en) | Systems and methods for selecting accent and dialect based on context | |
CN111739556B (zh) | 一种语音分析的系统和方法 | |
KR101615848B1 (ko) | 유사상황 검색을 통한 대화 스티커 추천방법 및 컴퓨터 프로그램 | |
US20140141392A1 (en) | Systems and Methods for Evaluating Difficulty of Spoken Text | |
Jesse et al. | Suprasegmental lexical stress cues in visual speech can guide spoken-word recognition | |
US9805740B2 (en) | Language analysis based on word-selection, and language analysis apparatus | |
JP2015118710A (ja) | 対話装置、方法及びプログラム | |
WO2022208692A1 (ja) | 表示用データ生成装置、表示用データ生成方法、及び表示用データ生成プログラム | |
JP7135372B2 (ja) | 学習支援装置、学習支援方法およびプログラム | |
JP6641680B2 (ja) | 音声出力装置、音声出力プログラムおよび音声出力方法 | |
JP6746886B2 (ja) | 学習支援装置及びその学習支援装置用のプログラム | |
JP7125630B2 (ja) | 要点抽出装置、要点抽出方法、及びプログラム | |
JP6383748B2 (ja) | 音声翻訳装置、音声翻訳方法、及び音声翻訳プログラム | |
JP2023155121A (ja) | プレゼンテーション評価装置 | |
JP2019207647A (ja) | 対話型業務支援システム | |
JP2023156220A (ja) | プレゼンテーション評価装置 | |
US11485022B2 (en) | Dialogue apparatus and control program for dialogue apparatus | |
WO2022185363A1 (ja) | ラベル付与支援装置、ラベル付与支援方法およびプログラム | |
US11902466B2 (en) | Captioned telephone service system having text-to-speech and answer assistance functions | |
WO2022185364A1 (ja) | 学習装置、学習方法およびプログラム | |
CN112541651B (zh) | 电子设备、发音学习方法、服务器装置、发音学习处理系统及记录介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21934862 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2023509990 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18552865 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21934862 Country of ref document: EP Kind code of ref document: A1 |