Data processing method, data processing device, program, and storage medium

Abstract

The present invention provides a data processing method, data processing device, program, and storage medium that enable users to add information they require to a knowledge system. [Solution] In the data processing method according to the embodiment, a computer receives a search query containing a search keyword from a client terminal. The computer receives search results obtained by searching for documents registered in the knowledge system using the search keyword. The computer determines a first evaluation result indicating an evaluation of the knowledge system regarding the search keyword. If the computer determines, based on the first evaluation result, that it is necessary to add a document related to the search keyword, it constructs a dialogue environment in which users can interact with each other. The computer registers a new document in the knowledge system using text data obtained from the dialogue environment.

Description

Technical Field

[0001] Embodiments of the present invention relate to a data processing method, a data processing apparatus, a program, and a storage medium.

Background Art

[0002] Conventionally, a system including a support tool that supports work using a terminal device and a knowledge system in which knowledge related to the work is accumulated has been used. A user of the support tool can acquire necessary information by appropriately referring to information registered in the knowledge system. Regarding this system, there is a demand for a technique that allows information required by a user to be appropriately added to the knowledge system.

Prior Art Literature

Patent Literature

[0003]

Patent Literature 1

Summary of the Invention

Problem to be Solved by the Invention

[0004] A problem to be solved by embodiments of the present invention is to provide a data processing method, a data processing apparatus, a program, and a storage medium that enable information required by a user to be added to a knowledge system.

Means for Solving the Problem

[0005] In the data processing method according to the embodiment, a computer receives a search query containing a search keyword from a client terminal. The computer receives search results obtained by searching for documents registered in the knowledge system using the search keyword. The computer determines a first evaluation result indicating an evaluation of the knowledge system regarding the search keyword. If the computer determines, based on the first evaluation result, that it is necessary to add a document related to the search keyword, it constructs a dialogue environment in which users can interact with each other. The computer registers a new document in the knowledge system using text data obtained from the dialogue environment. [Brief explanation of the drawing]

[0006] [Figure 1] Figure 1 is a schematic diagram showing the configuration of a data processing system according to an embodiment. [Figure 2] Figure 2 is a flowchart showing a part of the data processing method according to the embodiment. [Figure 3] Figure 3 is a flowchart showing another part of the data processing method according to the embodiment. [Figure 4] Figure 4 is a schematic diagram illustrating the GUI of the support tool. [Figure 5] Figure 5 is a schematic diagram illustrating a GUI that displays search results. [Figure 6] Figure 6 is a schematic diagram illustrating a GUI that displays search results. [Figure 7] Figure 7 is a schematic diagram illustrating a GUI that displays search results. [Figure 8] Figure 8 is a flowchart showing a data processing method related to a modified embodiment. [Figure 9] Figure 9 is a flowchart showing a data processing method related to a modified embodiment. [Figure 10] Figure 10 is a schematic diagram representing the hardware configuration. [Modes for carrying out the invention]

[0007] The embodiments of the present invention will be described below with reference to the drawings. Even when representing the same part, the dimensions and proportions may differ between drawings. In this specification and the drawings, elements similar to those already described are denoted by the same reference numerals, and detailed explanations are omitted as appropriate.

[0008] There are tools that assist users in inputting data into a computer. For example, an assistance tool displays a graphical user interface (GUI) on a monitor that accepts data input. The user enters data into designated input fields displayed on the GUI. The assistance tool generates output data based on the data in the input fields. For example, the assistance tool generates data in a predetermined format (document, table, design data, image data, etc.). The assistance tool may also output calculation results (e.g., estimated costs) based on the input data. Assistance tools can be used to efficiently carry out tasks.

[0009] Knowledge systems are sometimes used in conjunction with support tools. Knowledge systems aggregate various types of information, classifying and storing it. Knowledge systems support keyword searches, allowing users to perform keyword searches according to their search queries. The knowledge system transmits information found through keyword searches. Additionally, knowledge systems may support category searches, tag searches, and other methods.

[0010] For example, if a user encounters an unclear point while using an assistive tool, they can refer to the knowledge system. The user then obtains the necessary knowledge from the information registered in the knowledge system and uses it to input information into the assistive tool. Using the knowledge system allows users to utilize the assistive tool more smoothly.

[0011] On the other hand, if the knowledge system's information is not well-organized, users may not be able to obtain the information they need from the knowledge system. In particular, if the knowledge system is large and supports various support tools, or if the administrators of the support tools and the knowledge system are different, there may be discrepancies between the information required when using the support tools and the information registered in the knowledge system.

[0012] Embodiments of the present invention relate to a method for evaluating whether information required when using a support tool is registered in a knowledge system, and for registering new information in the knowledge system as necessary.

[0013] Figure 1 is a schematic diagram showing the configuration of a data processing system according to an embodiment. As shown in Figure 1, the data processing system 1 according to this embodiment includes a client terminal 10, a data processing device 20, and a knowledge system 30. The data processing device 20 is connected to the client terminal 10 and the knowledge system 30 by a network, wired communication, or wireless communication.

[0014] The client terminal 10 is capable of executing support tool programs. The user can use the support tool on the client terminal 10 to generate data in a predetermined format. The support tool includes a function for searching the knowledge system 30 for information the user needs. The user can use this search function to retrieve the necessary information from the knowledge system 30 as needed.

[0015] The data processing device 20 is connected between the client terminal 10 and the knowledge system 30. When a user performs a search, a search query is sent from the client terminal 10 to the knowledge system 30. The data processing device 20 receives the search query sent from the client terminal 10 and sends the search query to the knowledge system 30.

[0016] The knowledge system 30 searches for registered information based on search keywords included in a search query. The knowledge system 30 transmits search results to the client terminal 10. The data processing device 20 accepts the search results transmitted from the knowledge system 30, and transmits the search results to the client terminal 10. That is, in the example illustrated in FIG. 1, the data processing device 20 is configured to mediate data communication between the client terminal 10 and the knowledge system 30.

[0017] As illustrated in FIG. 1, the data processing device 20 includes functions as a transmission / reception unit 21, an evaluation unit 22, a determination unit 23, a dialogue environment generation unit 24, and a registration unit 25.

[0018] The transmission / reception unit 21 receives data transmitted from other devices. For example, the transmission / reception unit 21 receives a search query transmitted from the client terminal 10, a search result transmitted from the knowledge system 30, and the like. Further, the transmission / reception unit 21 transmits data to other devices. For example, the transmission / reception unit 21 transmits a search query to the knowledge system 30, and transmits search results to the client terminal 10.

[0019] The evaluation unit 22 determines an evaluation of the knowledge system 30 with respect to a search keyword included in a search query. An evaluation result (a first evaluation result) indicates whether or not the knowledge system 30 has sufficient information about the search keyword.

[0020] For example, the evaluation unit 22 determines the evaluation of the knowledge system 30 as either a first evaluation or a second evaluation. The first evaluation indicates that the knowledge system 30 has sufficient information about the search keyword. The second evaluation indicates that the knowledge system 30 lacks information about the search keyword.

[0021] As an example, if, as a result of a keyword search, the number of hit documents in the knowledge system 30 is less than a predetermined threshold (e.g., zero hits), it is evaluated that the knowledge system 30 lacks information related to the search keyword.

[0022] As another example, the user may be able to review the search results on the client terminal. In this case, the user can choose to either leave a review indicating that the information is sufficient for the knowledge system 30, or leave a review indicating that the information is insufficient for the knowledge system 30. Based on the review, a decision is made to assign either a first or second rating.

[0023] The evaluation results may include any of three or more levels of evaluation. For example, the evaluation results may be expressed as a score with three or more levels. A higher score indicates that there is a lack of information about the search keyword in the knowledge system 30. A lower number of document hits results in a higher score. In this case, a relatively low score is an example of a first-level evaluation. A relatively high score is an example of a second-level evaluation.

[0024] The determination unit 23 determines, based on the evaluation results from the evaluation unit 22, whether or not it is necessary to add documents related to the search keywords to the knowledge system 30. For example, if the number of second evaluations exceeds a preset threshold, the determination unit 23 determines that it is necessary to add documents related to the search keywords to the knowledge system 30.

[0025] When the determination unit 23 determines that additional documents are needed, the dialogue environment generation unit 24 constructs a dialogue environment 40 in which users can interact with each other. Preferably, the users are individuals with sufficient knowledge of the search keywords (experts). The users may include the operators of the client terminal 10.

[0026] For example, the dialogue environment 40 may be a bulletin board where each user posts text messages. Alternatively, the dialogue environment 40 may be an email thread or a chat-style thread. The dialogue environment generation unit 24 may set up a web conference as the dialogue environment 40, and the content of the utterances in the web conference may be saved as text data.

[0027] The user discusses information related to the search keywords using the dialogue environment 40. For example, they might discuss what information would be desirable to add to the knowledge system 30 regarding the support tools running on the client terminal 10. Alternatively, the user who submitted the search query on the client terminal 10 may engage in dialogue with an expert within the dialogue environment 40. In this case, the user on the client terminal 10 may ask questions to the expert, and the expert may answer those questions, thus advancing the dialogue.

[0028] The registration unit 25 registers a new document in the knowledge system 30 using text data obtained from the dialogue environment 40. The registration unit 25 may register the text data obtained from the dialogue environment 40 directly to the knowledge system 30, or it may summarize or format the obtained text data before registering it to the knowledge system 30.

[0029] Through the above process, new documents related to the search keywords are registered in the knowledge system 30. For example, if the above process results in a lack of documents related to the search keywords in the knowledge system 30, new documents will be registered to fill that gap.

[0030] Figure 2 is a flowchart showing a part of the data processing method according to the embodiment. First, the support tool is executed on the client terminal 10. While the support tool is running, the transmitting / receiving unit 21 determines whether a search query has been received (step St1). When the transmitting / receiving unit 21 receives a search query sent to the knowledge system 30, it sends the search query to the knowledge system 30 (step St2).

[0031] The knowledge system 30 performs a search on the registered data using the keywords included in the search query. The knowledge system 30 may perform an exact match search for the keywords. It may also perform an extended search or a thesaurus search that includes synonyms of the keywords. The transmitting / receiving unit 21 receives the search results from the knowledge system 30 and sends the search results to the client terminal 10 (step St3).

[0032] The evaluation unit 22 determines the evaluation of the knowledge system 30 regarding the search keyword (step St4). For example, if the evaluation result includes a first evaluation or a second evaluation, the determination unit 23 determines whether the evaluation result includes a second evaluation (step St5). If a second evaluation is not included (i.e., the knowledge system 30 has sufficient information regarding the search keyword), the process returns to step St1.

[0033] If the evaluation results include a second evaluation, the determination unit 23 increments the count for the search keyword that was the subject of the second evaluation by "+1" (step St6). The count may be performed for each search keyword. Alternatively, the count may be performed collectively for multiple search keywords that are determined to be synonyms. The user may pre-set groups of keywords for which the count will be performed collectively.

[0034] The determination unit 23 determines whether the count for the search keyword exceeds a pre-set threshold (step St7). If the count is below the threshold, the process returns to step St1. If the count exceeds the threshold, the determination unit 23 sends a notification to the dialogue environment generation unit 24.

[0035] Instead of comparing the count to a threshold, the count for each of multiple search keywords over a predetermined period may be referenced, and a ranking of the counts may be created. In this case, notifications are sent for the search keywords up to a predetermined rank, in descending order of count.

[0036] The dialogue environment generation unit 24 receives a notification and constructs a dialogue environment for users to communicate with each other (step St8). The dialogue environment generation unit 24 notifies a designated user that the dialogue environment has been constructed (step St9). Through the above process, the dialogue environment 40 is constructed as needed based on the search results.

[0037] Figure 3 is a flowchart showing another part of the data processing method according to the embodiment. In addition to the process shown in Figure 2, the process shown in Figure 3 is executed. The process in Figure 3 is executed to generate a document from the interactive environment 40.

[0038] For example, the registration unit 25 repeatedly checks the dialogue environment 40 at predetermined intervals. The registration unit 25 determines whether a predetermined amount of time has elapsed since the last check of the dialogue environment 40 (step St11). If the predetermined amount of time has elapsed, the dialogue environment 40 selects one of the multiple dialogue environments 40 (step St12).

[0039] The conditions for starting the verification of the interactive environment 40 may be set to something other than the elapsed time since the previous verification. Alternatively, the condition may be set to the elapsed time since the creation of a new interactive environment 40, or the day of the week or time for verifying the interactive environment 40 may be set in advance. The verification of the interactive environment 40 may also be started based on a command from the user.

[0040] The registration unit 25 determines whether the size of the text data obtained from the selected dialogue environment 40 exceeds a preset lower limit (step St13). If the size of the text data is less than or equal to the lower limit, it indicates that the dialogue environment 40 does not contain enough text data to generate a document.

[0041] If it is determined in step St13 that the size of the text data exceeds the lower limit, the registration unit 25 determines whether the size of the text data exceeds a preset upper limit (step St14). The upper limit compared in step St14 is greater than the lower limit compared in step St13.

[0042] If, in step St14, it is determined that the size of the text data exceeds the upper limit, the registration unit 25 summarizes the text contained in the dialogue environment 40 (step St15). Extractive summarization or generative summarization can be used for summarization. For example, in extractive summarization, important sentences are extracted from the text of the dialogue environment 40 by means of TF-IDF or scoring. A summary is generated by synthesizing the extracted sentences. In generative summarization, a summary is generated from the text of the dialogue environment 40 using a Sequence-to-Sequence model, a large-scale language model, etc. The summary is generated so that its size is below the upper limit.

[0043] If, in step St14, it is determined that the size of the text data does not exceed the upper limit, the registration unit 25 registers the text contained in the dialogue environment 40 to the knowledge system 30 (step St16). At this time, the text may be formatted using a Sequence-to-Sequence model, a large-scale language model, etc. For example, formatting may remove information unrelated to the search keywords. Formatting may also correct typographical errors or omissions.

[0044] If it is determined in step St13 that the size of the text data is below the lower limit, or after the processing in step St16, the registration unit 25 determines whether all dialogue environments were selected in step St12 (step St17). If there are still dialogue environments 40 that have not been selected, the registration unit 25 executes step St12 again. This selects one of the still-unselected dialogue environments 40. After that, the processing from step St13 onwards is executed again.

[0045] In the following sections, the data processing method according to the embodiment will be described with reference to specific examples.

[0046] Figure 4 is a schematic diagram illustrating the GUI of the support tool. The GUI100 shown in Figure 4 is an example of a display screen provided by the support tool. This support tool assists users in creating product specifications. GUI100 includes a display area 110, a display area 120, and a scroll bar 130.

[0047] The display area 110 shows titles 111 to 113. In the illustrated example, titles 111 to 113 indicate the general classification of the data to be entered, and relate to "Project Information" (customer name, product name, serial number), "General Specifications" (voltage, torque, weight, dimensions), and "Special" (other information, special orders from the customer). Items classified as "Project Information" include the name of the product purchaser, product name, product number, etc. Items classified as "General Specifications" include, for example, product dimensions, weight, electrical specifications (voltage, power consumption, frequency), material, performance (load capacity, waterproofing, dustproofing), function, standards, certifications, etc. "Special" refers to other items not classified as "Project Information" or "General Specifications," such as special specifications for each customer. The user can click on any of the titles 111 to 113 with the pointer to display information related to that title in the display area 120.

[0048] The display area 120 includes a title 121, an item display field 122, and a specification value input field 123. The title 121 displays the currently selected title. The item display field 122 includes major items 122a and minor items 122b. Major items 122a display a general classification of the specifications. Minor items 122b display detailed specifications within the classification of major items 122a. The specification value input field 123 is where the user enters the specification values ​​corresponding to the minor items 122b. Once the user has entered data into all the specification value input fields 123, the support tool automatically creates a specification document based on that data. The user can also move the displayed content in a predetermined direction by sliding the scroll bar 130 up and down.

[0049] For example, in the GUI 100 shown in Figure 4, when a user clicks on a string displayed in either the main item 122a or the sub-item 122b, a search query is generated. At this time, the search keywords are automatically determined based on the strings displayed in the main item 122a or the sub-item 122b, and the search query is generated. For example, the client terminal 10 generates a search query by embedding the search keywords in the web address. Therefore, the user does not need to set the search keywords. An appropriate search query is automatically generated.

[0050] For example, if a user clicks on "Dimensions" in the main item 122a of GUI100, a search query with "Dimensions" embedded as the search keyword is automatically generated. Based on this search query, the knowledge system 30 performs a keyword search.

[0051] Figures 5 to 7 are schematic diagrams illustrating a GUI that displays search results. After a search query is sent from client terminal 10, when client terminal 10 receives the search results, the GUI200 shown in Figure 5 is displayed. GUI200 may be displayed in the window where GUI100 was displayed, or a separate window for displaying GUI200 may be launched separately from the window for displaying GUI100.

[0052] GUI200 includes tabs 201, a search bar 202, icons 203, a search results display area 210, and a scroll bar 220.

[0053] Tab 201 is located in GUI200 to allow the user to switch between multiple pages that are open simultaneously. Tab 201 displays the title or icon of each page.

[0054] Search bar 202 is a text box where users can enter keywords to find the information they are looking for. The search results will display the keywords included in the search query. Users can also search for information in Knowledge System 30 themselves by clicking on search bar 202 and entering text.

[0055] Icon 203 is positioned adjacent to the search bar 202. Users can search for information in the knowledge system 30 by confirming keywords entered in the search bar 202 or by clicking icon 203.

[0056] The search results display area 210 shows the results of the search using the keywords entered in the search bar 202. For each document, the search results display area 210 shows the document title 211, snippet 212 (a portion of the text within the document), date 213, and the number of search hits 214. In the illustrated example, the date 213 shows the date the document was posted (uploaded) to the knowledge system 30.

[0057] The scroll bar 220 is displayed to allow users to view content that does not fit within the display area on the screen. Users can move the displayed content in a predetermined direction by sliding the scroll bar 220 up and down.

[0058] In addition, if GUI200 is able to accept reviews (feedback) regarding the search results, message 231, icon 232, and icon 233 will be displayed, as shown in Figure 5.

[0059] Message 231 includes a question for the user. Icon 232 is an icon to provide feedback that the user has found the information they need. Icon 233 is an icon to provide feedback that the user has not found the information they need. In response to a click on icon 232, the evaluation unit 22 generates an evaluation result indicating that there is sufficient information in the knowledge system 30 regarding the search keyword. In response to a click on icon 233, the evaluation unit 22 generates an evaluation result indicating that there is insufficient information in the knowledge system 30 regarding the search keyword.

[0060] In GUI200, when information in any document is clicked and selected, the details of that document are displayed. For example, as shown in Figure 6, a new page is opened in GUI200. A tab 201a corresponding to that page is added to the top of GUI200. The central display area 240 of GUI200 displays the document title 241 and the document's text data 242.

[0061] Figure 7 shows another example of search results. For example, if a keyword search yields 0 results, a message 215 indicating that no documents matching the keyword were found will be displayed in the search results display area 210, as shown in Figure 7.

[0062] The advantages obtained by the embodiment will be explained. In this embodiment of the present invention, when a search query is sent from the client terminal 10 and a document in the knowledge system 30 is retrieved according to the search query, the data processing device 20 determines an evaluation of the knowledge system 30 regarding the search keyword. This evaluation result indicates whether or not the knowledge system 30 has sufficient information regarding the search keyword. Based on the evaluation result, if the data processing device 20 determines that additional documents regarding the search keyword are necessary, it constructs a dialogue environment 40 that allows users to interact with each other. This enables users who have knowledge related to the search keyword to engage in dialogue about that keyword. The data processing device 20 also registers a new document in the knowledge system 30 using text data obtained from the dialogue environment 40. As a result, a new document is automatically registered for search keywords for which additional documents have been determined to be necessary. According to this embodiment, the information required by the user of the client terminal 10 can be automatically determined, and a new document related to that information can be registered in the knowledge system 30.

[0063] When the conversational environment 40 is established, the data processing device 20 sends a notification to pre-registered users. For example, experts are pre-registered for each support tool used by the client terminal 10. When a search query is sent while using any of the support tools, and the conversational environment 40 is established based on the search results, a notification is sent to the user associated with the support tool being used. The notification may be sent by email, or it may be sent to a specific terminal associated with a pre-registered user.

[0064] Furthermore, according to the embodiment, if the size of the text data obtained from the dialogue environment exceeds a predetermined upper limit, a summary of that text data is created. For example, if conversations between users are repeated and the dialogue text is lengthy, it becomes difficult for others to grasp the necessary information related to the search keywords. By creating a summary, others can more easily find the necessary information related to the search keywords.

[0065] (modified version) Figures 8 and 9 are flowcharts showing a data processing method related to a modified embodiment. When a search query is sent from the client terminal 10, the process shown in Figure 8 may be executed. Specifically, when the data processing device 20 receives a search query, it determines whether the search query contains information that identifies a document (step St21). For example, for each item displayed in the support tool, a corresponding document may be pre-registered in the knowledge system 30. In this case, when the support tool generates a search query, information to uniquely identify the corresponding document is included in the search query. For example, a unique string (ID) that indicates the corresponding document, or a URL indicating the location of the data on the web server may be used as information to identify the document.

[0066] If the search query does not contain specific information about the document, the search query will contain keywords. In this case, the data processing device 20 will execute the process shown in step St2 in Figure 2. After step St2, evaluation decisions, construction of the interactive environment, etc., will be performed as appropriate according to the flowchart shown in Figure 2.

[0067] If the search query contains information that identifies a document, the transmission / reception unit 21 sends the search query to the knowledge system 30 (step St22). The knowledge system 30 searches the registered data for the document identified by the information contained in the search query. The transmission / reception unit 21 receives the search results from the knowledge system 30 and sends the search results to the client terminal 10 (step St23).

[0068] Subsequently, the data processing device 20 determines an evaluation of the search (step St24). For example, the evaluation result (second evaluation result) includes a third or fourth evaluation. A third evaluation indicates that appropriate information was registered in the knowledge system 30 with respect to the searched item. A fourth evaluation indicates that appropriate information was not registered in the knowledge system 30 with respect to the searched item. For example, if the search query contains information that identifies a document, but the document is not identified, a fourth evaluation is determined. If the document is uniquely identified, a third evaluation is determined.

[0069] If a document is uniquely identified, it may be reviewed by a user. For example, if the necessary information is obtained from the searched document, a positive review is given. If the necessary information is not obtained from the searched document, a negative review is given. The evaluation unit 22 determines an evaluation based on the results of the review.

[0070] The determination unit 23 determines whether the evaluation result includes the fourth evaluation (step St25). If the fourth evaluation is not included, the process returns to step St1. If the evaluation result includes the fourth evaluation, the determination unit 23 increments the count for the item that was the subject of the fourth evaluation by "+1" (step St26). The determination unit 23 determines whether the count for that item exceeds a pre-set threshold (step St27). If the count is less than or equal to the threshold, the process returns to step St1. If the count exceeds the threshold, the determination unit 23 sends a notification to the dialogue environment generation unit 24.

[0071] The dialogue environment generation unit 24 receives the notification and constructs the dialogue environment 40 (step St28). The dialogue environment generation unit 24 notifies the designated user that the dialogue environment 40 has been constructed (step St29).

[0072] According to the process shown in Figure 8, when improvements are needed regarding specific information in a document, or regarding the document identified by that specific information, the interactive environment 40 is established. For example, if the specific information sent in a search query is incorrect, the interactive environment 40 discusses what information should be corrected to. If a negative review has been made by a user, the interactive environment 40 discusses how the document registered in the knowledge system 30 should be corrected.

[0073] Through the above process, the data processing device 20 executes appropriate processing according to the information contained in the search query. Furthermore, if the information identifying the document is incorrect, or if the information about the identified document is insufficient, the device can prompt for correction.

[0074] When a document is generated from the interactive environment, the process shown in Figure 9 may be executed instead of the process shown in Figure 3. In the process shown in Figure 3, all documents are updated based on the existing interactive environment 40. On the other hand, in the process shown in Figure 9, documents that were generated in the past and have not been substantially changed are not updated.

[0075] Specifically, after steps St11 and St12 are executed, the registration unit 25 determines whether the last update date and time of the selected dialogue environment 40 is after the last confirmation of the dialogue environment 40 (step St12a). If the last update date and time is before the last confirmation, there is no need to update the document based on that dialogue environment 40. In this case, the registration unit 25 proceeds to step St17.

[0076] If the last update date is after the previous check, it indicates that the interactive environment 40 was built after the previous check or that new information has been added to the interactive environment 40. In this case, the registration unit 25 determines whether a document based on the interactive environment 40 is registered in the knowledge system 30 (step St12b). If a document based on the interactive environment 40 is not registered in the knowledge system 30, step St13 is executed, similar to the flowchart described in Figure 3.

[0077] If a document based on the interactive environment 40 is registered in the knowledge system 30, the registration unit 25 determines whether the difference between the data size of the interactive environment 40 at the time of the previous check and the data size of the interactive environment 40 at the time of the current check exceeds a pre-set threshold (step St12c). If the difference is less than or equal to the threshold, it indicates that less information has been added compared to the time of the previous check. In this case, the registration unit 25 does not update the document for that interactive environment 40 and proceeds to step St17.

[0078] If the difference exceeds a threshold, it indicates that a sufficient amount of information has been added compared to the previous check. In this case, steps St14 and later are executed for the text data of that interactive environment 40. As a result, a new document is generated based on the text data contained in the interactive environment 40 to which the information has been added, and the document registered in the knowledge system 30 is updated.

[0079] The process shown in Figure 9 reduces the amount of computation required to register documents in the knowledge system 30 compared to the process shown in Figure 3.

[0080] Figure 10 is a schematic diagram representing the hardware configuration. For example, the computer 90 shown in Figure 10 is used as the client terminal 10 and data processing device 20. The computer 90 includes a processing circuit 91, ROM 92, RAM 93, storage device 94, input interface 95, output interface 96, and communication interface 97.

[0081] ROM92 stores programs that control the operation of computer 90. ROM92 contains the programs necessary for computer 90 to perform each of the processes described above. RAM93 functions as a memory area where the programs stored in ROM92 are loaded.

[0082] The processing circuit 91 includes an arithmetic processing unit such as a CPU or GPU. The processing circuit 91 uses RAM 93 as work memory and executes a program stored in at least one of ROM 92 or storage device 94. During program execution, the processing circuit 91 controls each component via the system bus 98 and performs various processes.

[0083] The memory device 94 stores data necessary for program execution and data obtained through program execution.

[0084] The input interface (I / F) 95 can connect the computer 90 and the input device 95a. The input I / F 95 is, for example, a serial bus interface such as USB. The processing circuit 91 can read various data from the input device 95a via the input I / F 95.

[0085] The output interface (I / F) 96 can connect the computer 90 and the output device 96a. The output I / F 96 is a video output interface such as a Digital Visual Interface (DVI) or a High-Definition Multimedia Interface (HDMI®). The processing circuit 91 can transmit data to the output device 96a via the output I / F 96 and display an image on the output device 96a.

[0086] The communication interface (I / F) 97 can connect the computer 90 to a server 97a located outside the computer 90. The communication I / F 97 is, for example, a network card such as a LAN card. The processing circuit 91 can read various data from the server 97a via the communication I / F 97.

[0087] The storage device 94 includes one or more selected from Hard Disk Drives (HDDs) and Solid State Drives (SSDs). The input device 95a includes one or more selected from a mouse, keyboard, microphone (voice input), and touchpad. The output device 96a includes one or more selected from a monitor, projector, printer, and speaker. Devices that have the functions of both input device 95a and output device 96a, such as a touch panel, may also be used.

[0088] The functions of the data processing device 20 may be implemented by a single computer 90, or by the cooperation of multiple computers 90. In the example shown in Figure 1, the data processing device 20 is configured to mediate data communication between the client terminal 10 and the knowledge system 30. The data processing device 20 may be configured integrally with the knowledge system 30, and is not limited to this example. For example, the knowledge system 30 may be capable of performing the functions of the data processing device 20 in addition to retrieving information.

[0089] The processing of the various data described above may be recorded as a program that can be executed by a computer on a magnetic disk (flexible disk and hard disk, etc.), an optical disk (CD-ROM, CD-R, CD-RW, DVD-ROM, DVD±R, DVD±RW, etc.), a semiconductor memory, or another non-transitory computer-readable storage medium.

[0090] For example, data on a recording medium is read by a computer (or embedded system). The recording format (storage format) on the recording medium is arbitrary. For example, a computer reads a program from the recording medium and causes the CPU to execute instructions based on this program. The acquisition (or reading) of the program by the computer may be done via a network.

[0091] Embodiments of the present invention include the following features. (Feature 1) Computers Receive search queries containing search keywords sent from the client terminal. The search results obtained by searching for documents registered in the knowledge system using the aforementioned search keywords are received. A first evaluation result is determined that indicates an evaluation of the knowledge system regarding the aforementioned search keywords. Based on the first evaluation result, if it is determined that additional documentation related to the search keywords is necessary, a dialogue environment where users can interact with each other will be constructed. Using the text data obtained from the aforementioned dialogue environment, a new document is registered in the aforementioned knowledge system. Data processing method. (Feature 2) The data processing method according to Feature 1, wherein the first evaluation result is determined based on the number of hits for documents registered in the knowledge system using the search keywords, and one or more selected from reviews of the search results transmitted from the client terminal. (Feature 3) The first evaluation result includes a first evaluation indicating that the knowledge system has sufficient information regarding the search keywords, or a second evaluation indicating that the knowledge system lacks sufficient information regarding the search keywords. The data processing method according to feature 1 or 2, wherein the computer determines that it is necessary to add documents related to the search keyword when the number of evaluations exceeds a predetermined threshold. (Feature 4) When the aforementioned interactive environment is established, the computer sends a notification to a pre-registered user. The data processing method according to any one of features 1 to 3, wherein the computer generates a summary of the text data if the size of the text data obtained from the dialogue environment exceeds a preset threshold, and registers the summary as a new document in the knowledge system. (Feature 5) The aforementioned computer, Determine whether the received search query contains specific information for identifying the document. If the search query includes the search keyword, the search keyword is sent to the knowledge system. If the search query includes the specified information, the specified information is sent to the knowledge system. A data processing method described in one of the features 1-4. (Feature 6) The aforementioned computer, The search results obtained by searching for documents registered in the knowledge system using the aforementioned specific information are received. A second evaluation result is determined, which indicates an evaluation of the knowledge system regarding the search using the aforementioned specific information. Based on the second evaluation result, if it is determined that the specific information or the document identified by the specific information requires improvement, a dialogue environment will be constructed that allows users to interact with each other. The data processing method described in Feature 5. (Feature 7) The data processing method according to feature 6, wherein the second evaluation result is determined based on one or more selected from the presence or absence of a document identified by the specific information and a review of the identified document transmitted from the client terminal. (Feature 8) A data processing device comprising a computer that performs the data processing method described in any one of features 1 to 7. (Feature 9) A program that causes the computer to execute the data processing method described in any one of features 1 to 7. (Feature 10) A storage medium containing the program described in Feature 9.

[0092] According to the embodiments described above, a data processing method, a data processing device, a program, and a storage medium are provided that enable users to add information they require to a knowledge system.

[0093] In this specification, "or" indicates that "at least one" of the items listed in the text may be adopted.

[0094] Although several embodiments of the present invention have been illustrated above, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. Furthermore, the embodiments described above can be implemented in combination with each other. [Explanation of Symbols]

[0095] 1: Data processing system, 10: Client terminal, 20: Data processing device, 21: Send / receive unit, 22: Evaluation unit, 23: Judgment unit, 24: Dialogue environment generation unit, 25: Registration unit, 30: Knowledge system, 40: Dialogue environment, 100: GUI, 110: Display area, 111~113: Title, 120: Display area, 121: Title, 122: Item display field, 122a: Major item, 122b: Minor item, 123: Specification value display field, 130: Scroll bar, 200: GUI, 201,201a: Tab, 202: Search bar, 203: Icon, 210: Search results display field, 211: Title, 212: Snippet, 213: Date, 214: Number of hits, 215: Message, 220: Scroll bar, 231: Message, 232,233: Icon, 240: Display area, 241: Title, 242: Text data

Claims

1. Computers Receive search queries containing search keywords sent from the client terminal. The search results obtained by searching for documents registered in the knowledge system using the aforementioned search keywords are received. A first evaluation result is determined that indicates an evaluation of the knowledge system regarding the aforementioned search keywords. Based on the first evaluation result, if it is determined that additional documentation related to the search keywords is necessary, a dialogue environment where users can interact with each other will be constructed. Using the text data obtained from the aforementioned dialogue environment, a new document is registered in the aforementioned knowledge system. Data processing method.

2. The data processing method according to claim 1, wherein the first evaluation result is determined based on one or more selected from the number of hits of documents registered in the knowledge system using the search keywords and reviews of the search results transmitted from the client terminal.

3. The first evaluation result includes a first evaluation indicating that the knowledge system has sufficient information regarding the search keywords, or a second evaluation indicating that the knowledge system lacks sufficient information regarding the search keywords. The data processing method according to claim 1, wherein the computer determines that it is necessary to add documents related to the search keyword when the number of evaluations exceeds a preset threshold.

4. When the aforementioned interactive environment is established, the computer sends a notification to a pre-registered user. The data processing method according to claim 1, wherein the computer generates a summary of the text data if the size of the text data obtained from the dialogue environment exceeds a preset threshold, and registers the summary as a new document in the knowledge system.

5. The aforementioned computer, Determine whether the received search query contains specific information for identifying the document. If the search query includes the search keyword, the search keyword is sent to the knowledge system. If the search query includes the specified information, the specified information is sent to the knowledge system. The data processing method according to claim 1.

6. The aforementioned computer, The search results obtained by searching for documents registered in the knowledge system using the aforementioned specific information are received. A second evaluation result is determined, which indicates an evaluation of the knowledge system regarding the search using the aforementioned specific information. Based on the second evaluation result, if it is determined that the specific information or the document identified by the specific information requires improvement, a dialogue environment will be constructed that allows users to interact with each other. The data processing method according to claim 5.

7. The data processing method according to claim 6, wherein the second evaluation result is determined based on one or more selected from the presence or absence of a document identified by the specific information and a review of the identified document transmitted from the client terminal.

8. A data processing device comprising a computer that performs the data processing method according to any one of claims 1 to 7.

9. A program that causes the computer to execute the data processing method described in any one of claims 1 to 7.

10. A storage medium storing the program described in claim 9.

Images