Information processing apparatus, information processing method, and computer-readable storage medium

Abstract

To provide an information processing apparatus, an information processing method and a computer-readable storage medium.SOLUTION: An information processing apparatus may include: a determination unit configured to determine that auxiliary information for input data is required, in a case where a first keyword extracted from the input data is not included in a first subset corresponding to the first keyword in a predetermined data set; and an auxiliary information acquisition unit configured to, in a case where the determination unit determines that the auxiliary information is required, extract, from the first subset, multiple pieces of data corresponding to the first keyword, and select, based on the input data, one or more pieces of data from the extracted multiple pieces of data, as the auxiliary information, for generating response data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to the field of information processing, and more particularly to an information processing device, an information processing method, and a computer-readable storage medium. [Background technology]

[0002] Many applications require a technique for automatically generating response data, and therefore there is a need for a technique that can easily generate more accurate response data. Summary of the Invention [Problem to be solved by the invention]

[0003] The following presents a simplified summary of the disclosure in order to provide a basic understanding of aspects of the disclosure. However, this summary is not an exhaustive overview of the disclosure, and it is not intended to identify key or important portions of the disclosure or to limit the scope of the disclosure. Rather, it is intended to merely introduce concepts in a simplified form as a prelude to the more detailed description that is presented later.

[0004] An object of the present disclosure is to provide, for example, an improved information processing device, information processing method, and computer-readable storage medium that can easily generate more accurate response data. [Means for solving the problem]

[0005] One aspect of the present disclosure provides an information processing device including: a determination unit that determines that auxiliary information is needed for input data when a first keyword extracted from the input data is not included in a first subset corresponding to the first keyword in a predetermined dataset; and an auxiliary information acquisition unit that, when the determination unit determines that the auxiliary information is needed, extracts a plurality of data corresponding to the first keyword from the first subset to generate response data, and selects one or more data from the extracted plurality of data as the auxiliary information based on the input data.

[0006] Another aspect of the present disclosure provides an information processing method, comprising: determining that auxiliary information about the input data is needed if a first keyword extracted from the input data is not included in a first subset corresponding to the first keyword in a predetermined dataset; and, if it is determined that the auxiliary information is needed, extracting a plurality of data corresponding to the first keyword from the first subset to generate response data, and selecting one or more data from the extracted plurality of data as the auxiliary information based on the input data.

[0007] In other aspects of the present disclosure, there are further provided computer program code and computer program products for implementing the above-described methods of the present disclosure, as well as computer-readable storage media having computer program code recorded thereon for implementing the above-described methods of the present disclosure.

[0008] The following describes other aspects of the embodiments of the present disclosure, and in particular, describes in detail preferred embodiments of the present disclosure, but the present disclosure is not limited to these embodiments. [Brief explanation of the drawings]

[0009] The present disclosure will be better understood by reference to the detailed description set forth below in connection with the drawings, in which the same or similar reference numerals are used to denote the same or similar components in all the drawings, and which, together with the following detailed description, are incorporated into and constitute a part of this specification to further illustrate preferred embodiments of the present disclosure and to explain the principles and advantages of the present disclosure. [Figure 1] FIG. 1 is a block diagram illustrating an example of a functional configuration of an information processing device according to an embodiment of the present disclosure. [Figure 2] 1 is a schematic diagram illustrating an example of a specific architecture of an information processing device according to an embodiment of the present invention. [Figure 3A] 3A and 3B are diagrams showing examples of provided hints. [Figure 3B] 3A and 3B are diagrams showing examples of provided hints. [Figure 4A] 4A and 4B are diagrams showing an example of a portion of a predetermined data set. [Figure 4B] 4A and 4B are diagrams showing an example of a portion of a predetermined data set. [Figure 5A] 5A and 5B are diagrams showing other examples of provided hints. [Figure 5B] 5A and 5B are diagrams showing other examples of provided hints. [Figure 6] FIG. 10 is a diagram illustrating an example of generated code. [Figure 7A] 7A and 7B are diagrams showing other examples of provided hints. [Figure 7B] 7A and 7B are diagrams showing other examples of provided hints. [Figure 8] FIG. 2 is a block diagram illustrating an example of a functional configuration of an auxiliary information acquisition unit according to an embodiment of the present disclosure. [Figure 9] FIG. 10 is a schematic diagram illustrating an example of a specific architecture of an auxiliary information acquisition unit according to an embodiment of the present disclosure. [Figure 10A] 10A to 11B are diagrams showing an example of generated hint information. [Figure 10B] 10A to 11B are diagrams showing an example of generated hint information. [Figure 11A] 10A to 11B are diagrams showing an example of generated hint information. [Figure 11B] 10A to 11B are diagrams showing an example of generated hint information. [Figure 12] FIG. 1 is a block diagram illustrating an example of a functional configuration of an information processing device according to an embodiment of the present disclosure. [Figure 13] FIG. 1 is a schematic diagram illustrating an example of a specific architecture of an information processing device according to an embodiment of the present disclosure. [Figure 14] 1 is a flowchart illustrating an example of the flow of an information processing method according to an embodiment of the present disclosure. [Figure 15] 1 is a flowchart illustrating an example of the flow of an information processing method according to an embodiment of the present disclosure. [Figure 16] FIG. 1 is a block diagram illustrating an exemplary configuration of a personal computer applicable to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0010]

[0023] Exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. For convenience of description, the specification does not include all features of actual embodiments. It should be noted that, in actual implementation, specific embodiments may be modified to achieve specific goals of developers, for example, according to system and business constraints. Although the development work is very complex and time-consuming, it is merely an example for those skilled in the art of this disclosure.

[0011] For example, in this specification, terms such as "first" and "second" may be used to distinguish between different elements, but such terms do not limit the number, order, etc. of elements.

[0012] It should be noted that, for clarity of the present disclosure, the drawings only show the components of the apparatus or process steps closely related to the present disclosure, and omit details unrelated to the present disclosure.

[0013] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings.

[0014] Example 1 FIG. 1 is a block diagram showing an example of a functional configuration of an information processing device 100 according to an embodiment of the present disclosure. FIG. 2 is a schematic diagram showing an example of a specific architecture of the information processing device 100 according to an embodiment of the present invention. In FIG. 2, some processes are indicated by dashed arrows, which means that in some examples, one or more of these processes may not be included. Also, in FIG. 2, (outside 1) TIFF2025141885000002.tif10170 shows a large-scale language model.

[0015] As shown in FIG. 1, an information processing device 100 according to an embodiment of the present disclosure may include a determining unit 102 and an auxiliary information obtaining unit 104.

[0016] The determining unit 102 may determine that auxiliary information about the input data is needed if a first keyword extracted from the input data (e.g., searched) is not included in a first subset corresponding to the first keyword in a predetermined dataset.

[0017] When the determination unit 102 determines that auxiliary information is needed, the auxiliary information acquisition unit 104 may extract a plurality of data corresponding to the first keyword from the first subset, and select one or more pieces of data as auxiliary information from the extracted plurality of pieces of data based on the input data to generate response data, thereby obtaining more appropriate response data and improving the accuracy of the finally obtained response data.

[0018] In some examples, as shown in Figure 2, the auxiliary information obtaining unit 104 may select one or more pieces of data as auxiliary information from the extracted multiple pieces of data based on the input data and user feedback information, thereby obtaining more appropriate response data and improving the accuracy of the finally obtained response data.

[0019] For example, the user feedback information may include feedback information for response data from a first user who inputs the input data. In some examples, the user feedback information may include feedback information for corresponding response data from one or more second users different from the first user. This can increase the amount of user feedback information and further improve the accuracy of the ultimately generated response data.

[0020] In some examples, the user feedback information may include feedback information on the auxiliary information. This may improve the accuracy of the auxiliary information and further improve the accuracy of the ultimately generated response data. For example, the feedback information on the auxiliary information may include feedback information on the auxiliary information provided by a first user. The feedback information on the auxiliary information may include feedback information on the corresponding auxiliary information provided by one or more second users. This may further improve the accuracy of the auxiliary information and further improve the accuracy of the ultimately generated response data.

[0021] In some examples, the user feedback information may include feedback information for the response data (e.g., feedback information for the response data by the first user, feedback information for the corresponding response data by one or more second users) and feedback information for the auxiliary information (e.g., feedback information for the auxiliary information by the first user, feedback information for the corresponding auxiliary information by one or more second users), which may further improve the accuracy of the ultimately generated response data.

[0022] For example, the information processing device 100 may be applied to a store (including a physical store, an online store, etc.) to assist a user in determining sales information, etc. For example, the predetermined data set may be a customer consumption record in the store, such as a service usage record or a product purchase record.

[0023] For example, the information processing device 100 may be applied to a hospital to assist a user in determining patient treatment information, etc. For example, the predetermined data set may be patient treatment records, such as drug use records, chemical test records, etc. Note that the application of the information processing device 100 is not limited to the above example, and for example, the information processing device 100 may be used for querying traffic violation information, etc.

[0024] For example, a predetermined data set may include multiple subsets each corresponding to a different title. For example, a predetermined data set may include object identification information, time, target information, etc. The predetermined object identification information, time, and target information may correspond to the titles "object identification information," "time," and "target information," respectively. The object and target information may vary depending on the application scenario. For example, if the information processing device 100 is applied to a store or a pharmacy, the object may be a consumer, and the target information may be, but is not limited to, the name of a product purchased by the consumer and / or the name of a service used by the consumer. For another example, if the information processing device 100 is applied to a hospital, the object may be a patient, and the target information may be, but is not limited to, the name of a medicine purchased by the patient, the name of a chemical test taken by the patient, etc.

[0025] For example, the predetermined data set may be provided by a user and stored in memory, for example, the predetermined data set may be structured data such as, but not limited to, an SQL database or a CSV file.

[0026] The memory may be built into the information processing device 100 or may be accessed by the information processing device 100. In some examples, the memory may store only a portion of a predetermined dataset, for example, only a subset of the predetermined dataset that has been determined to require indexing (as shown in FIG. 2). This can reduce the amount of information storage. As an example, a subset of the predetermined dataset that includes text may be determined to require indexing.

[0027] For example, a large-scale language model may determine the subsets that need to be indexed. In this case, hints shown in FIG. 3A or 3B may be input to the large-scale language model to assist in determining the subsets that need to be indexed. In FIG. 3A and FIG. 3B, {df_info} represents information about a given dataset, including the titles of each subset and other data other than the titles of each subset. {titles}({title}) is the title of each subset.

[0028] 4A and 4B, the titles of the subsets are "Customer_id," "Checkout time," and "Purchased products," respectively. In an example of determining a subset that includes text as a subset that needs to be indexed, for the example shown in FIGS. 4A and 4B, data corresponding to the title "Purchased products" may be determined as data that needs to be indexed.

[0029] For example, the input data may include information related to the target information. As an example, the input data may include at least one of a product name, a service name, a product category, and a service category.

[0030] To better understand the embodiments of the present disclosure, the following will further describe the information processing device 100 by taking an example in which the information processing device 100 is applied to a store, the object is a consumer, and the target information is the name of the item purchased by the consumer.

[0031] The information processing device 100 may operate based on various language environments. For example, for convenience of explanation, this specification will explain an example in which the information processing device 100 operates in an English environment, and when a corresponding English word / sentence appears for the first time, the Chinese version will be written in parentheses after the English word / sentence.

[0032] For example, the determining unit 102 may extract a first keyword from the input data, determine a title corresponding to the first keyword, search for the first keyword from a first subset corresponding to the title in a predetermined dataset, and determine that auxiliary information about the input data is needed if the first keyword is not obtained by the search.

[0033] For example, if the input data includes a product name, a service name, a product category, and / or a service category, the first keyword may include the product name, the service name, the product category, and / or the service category included in the input data.

[0034] For example, the determining unit 102 may generate a code (e.g., a computer language code such as a Python code) based on the input data, and extract the first keywords and titles corresponding to the first subset from the code, thereby obtaining more accurate first keywords and titles and further improving the accuracy of the finally generated response data.

[0035] For example, if the decision unit 102 is implemented by a large-scale language model, hints may be provided to the large-scale language model to assist it in generating appropriate codes. Figures 5A and 5B show examples of hints provided in English and Chinese environments, respectively, and Figure 6 shows an example of a code generated based on the input data "who bought fresh food?" In Figures 5A and 5B, {file_info} represents file information, such as information about a predetermined dataset.

[0036] As can be seen from FIG. 6, the generated code includes the desired first keyword "fresh food" and the title "Purchased products" that corresponds to the first keyword.

[0037] For example, hints may be provided to the large-scale language model so that the large-scale language model extracts more accurate first keywords and corresponding titles from the generated code. Figures 7A and 7B show examples of hints provided in English and Chinese environments, respectively. When the hint shown in Figure 7A is provided, the extraction result is {"Purchased products":["fresh food"]}, which includes the desired first keyword "fresh food" and the corresponding title "Purchased products." In other words, accurate first keywords and corresponding titles can be extracted in this way.

[0038] 4A, the column corresponding to "Purchased products" (an example of the first subset) includes specific product names that do not include the first keyword "fresh food," so the determining unit 102 may determine that auxiliary information is needed. In this case, the auxiliary information acquiring unit 104 may extract a plurality of data corresponding to the first keyword from the first subset, and select one or more data from the extracted plurality of data as auxiliary information based on the input data or the input data and user feedback information.

[0039] In some examples, for each data item among the extracted multiple data items, the auxiliary information acquiring unit 104 may determine whether the data item matches a first keyword based on the input data or the input data and user feedback information. For example, the auxiliary information acquiring unit 104 may determine whether the data item matches a first keyword based on whether the data item belongs to a category defined by the first keyword. If the auxiliary information acquiring unit 104 determines that the data item matches the first keyword (e.g., the data item belongs to a category defined by the first keyword), it may select the data item as auxiliary information. On the other hand, if the auxiliary information acquiring unit 104 determines that the data item does not match the first keyword (e.g., the data item does not belong to a category defined by the first keyword), it does not select the data item as auxiliary information.

[0040] A specific configuration example of the auxiliary information acquiring unit 104 will be described below with reference to Figures 8 and 9. Figure 8 is a block diagram showing an example of the functional configuration of the auxiliary information acquiring unit according to an embodiment of the present disclosure. Figure 9 is a schematic diagram showing an example of a specific architecture of the auxiliary information acquiring unit according to an embodiment of the present disclosure. In Figures 8 and 9, the keyword extraction subunit 1044 is shown in a dashed frame, which means that the auxiliary information acquiring unit 104 does not necessarily include the keyword extraction subunit 1044.

[0041] In some examples, as shown in FIG. 8, the auxiliary information obtaining unit 104 may include a data extracting subunit 1042, a hint generating subunit 1046 and a selecting subunit 1048.

[0042] The data extraction subunit 1042 may extract a plurality of data corresponding to a first keyword from the first subset. For example, in the example described with reference to FIGS. 3A to 7B above, the data extraction subunit 1042 may extract a plurality of data corresponding to a first keyword "fresh food" from a column (an example of the first subset) corresponding to the title "Purchased products." The obtained results are "Broccoli," "Cabbages," "Watermelon," "Eggs," "Bananas," "Potatoes," "Onions," "Orange Juice," "Apples," "Eggplants," "Oranges," "Prawn Crackers," "Pears," "Chestnuts," "Iced Tea," and "Cookies."

[0043] The hint generation subunit 1046 may generate hints based on the input data.

[0044] The selection subunit 1048 may select one or more pieces of data as auxiliary information from the plurality of pieces of data extracted by the data extraction subunit 1042 based on the hint information generated by the hint information generation subunit 1046. The auxiliary information thus obtained can further improve the accuracy of the finally generated response data.

[0045] In some examples, the auxiliary information obtaining unit 104 may further include a keyword extracting subunit 1044. The keyword extracting subunit 1044 may extract a second keyword from the user feedback information. The user feedback information may include one or more pieces of feedback information.

[0046] For example, the user feedback information may include a product name and / or a service name. For example, if the user feedback information is "Orange Juice does not belong to fresh food," the extracted second keyword is "Orange Juice."

[0047] The hint information generating subunit 1046 may generate hint information based on the matching result between the second keyword and the extracted multiple data and the input data, and the auxiliary information obtained based on the hint information thus obtained can further improve the accuracy of the finally generated response data.

[0048] In some examples, for each piece of data, if the data and the second keyword contain words related to the same category, the data may be considered to match the second keyword. For example, in the examples described above with reference to FIGS. 3A to 7B, for each piece of data, if the product name included in the data and the product name included in the second keyword belong to the same category, the data may be considered to match the second keyword. For example, in the example of multiple pieces of data corresponding to the first keyword "fresh food" described above, "Orange Juice" and "Iced Tea" belong to the same category as the second keyword "Orange Juice" extracted from the feedback information "Orange Juice do not belong to fresh food," so "Orange Juice" and "Iced Tea" may be considered to match the second keyword "Orange Juice," and other data may be considered not to match the second keyword "Orange Juice."

[0049] For example, if the auxiliary information acquiring unit 104 is realized by a large-scale language model, a hint may be provided to the large-scale language model so that the large-scale language model can more accurately determine whether each data matches the second keyword. For example, the provided hint may be “Do {keyword_from_retrieval} and {keyword_from_feedback} belong to a broad category?”, where {keyword_from_retrieval} and {keyword_from_feedback} represent the data extracted by the data extracting subunit 1042 and the second keyword extracted by the keyword extracting subunit 1044, respectively.

[0050] In some examples, for each data item among the extracted data items, if the data item matches the second keyword, the hint information includes feedback information corresponding to the data item among the user feedback information. On the other hand, if none of the extracted data items matches the second keyword, the hint information does not include user feedback information. Figures 10A and 10B show hint information without user feedback information and hint information with corresponding feedback information, respectively, and Figures 11A and 11B show Chinese equivalents to Figures 10A and 10B, respectively. In Figures 10 to 11B, "keyword_from_user_query" represents the first keyword extracted from the input data.

[0051] 10B and 11B, "example" may be feedback information corresponding to data that matches the second keyword among the plurality of data extracted in the user feedback information. For example, in the above-mentioned example of the plurality of data corresponding to the first keyword "fresh food," the data "Orange Juice" matches the second keyword "Orange Juice" extracted from the feedback information "Orange Juice do not belong to fresh food." Therefore, the hint information may include feedback information "Orange Juice do not belong to fresh food" that corresponds to the data "Orange Juice" in the user feedback information.

[0052] <Example 2> Fig. 12 is a block diagram illustrating an example of a functional configuration of an information processing device 1200 according to an embodiment of the present disclosure. Fig. 13 is a schematic diagram illustrating an example of a specific architecture of the information processing device 1200 according to an embodiment of the present disclosure. As shown in Figs. 12 and 13, the information processing device 1200 according to an embodiment of the present disclosure may include a determination unit 1202, an auxiliary information acquisition unit 1204, and a response generation unit 1206.

[0053] For example, the determination unit 1202 and the auxiliary information acquisition unit 1204 may have the same configuration as the determination unit 102 and the auxiliary information acquisition unit 104 described in the above Example 1, and the details thereof may refer to the above description, and the detailed description will be omitted below.

[0054] The response generation unit 1206 may generate response data for the input data. For example, if the determining unit 1202 determines that auxiliary information is not required, the response generation unit 1206 may generate response data based on the input data. In some examples, the response generation unit 1206 may search for a first keyword from the target dataset and generate response data based on the input data and the searched data. For example, in the example described with reference to FIGS. 3A to 7B above, for the input data "who bought Apples?", the determining unit 1202 may determine that auxiliary information is not required because the first keyword "Apples" is included in the column corresponding to "Purchased products" (an example of the first subset). The response generation unit 1206 may search for the first keyword "Apples" from the target dataset and use Customer_id in the searched data (e.g., data including the first keyword "Apples") as response data.

[0055] On the other hand, if the determining unit 1202 determines that auxiliary information is needed, the answer generating unit 1206 may generate answer data based on the auxiliary information acquired by the auxiliary information acquiring unit 1204 and the input data. In some examples, the answer generating unit 1206 may generate a third keyword based on the auxiliary information, search for corresponding data from the target dataset based on the third keyword, and generate answer data based on the input data and the searched data. As an example, if the target dataset is the same as the predetermined dataset, the answer generating unit 1206 may use the auxiliary information as the third keyword.

[0056] For example, in the example described with reference to FIGS. 3A to 7B above, for the input data “who bought fresh food?”, the column corresponding to “Purchased products” (an example of the first subset) indicates specific product names that do not include the first keyword “fresh food,” so the determining unit 1202 may determine that auxiliary information is needed. In one example, the auxiliary information generated by the auxiliary information acquiring unit 1204 is “Broccoli,” “Cabbages,” “Watermelon,” “Eggs,” “Bananas,” “Potatoes,” “Onions,” “Oranges,” “Apples,” “Eggplants,” “Pears,” “Chestnuts,” and “Peaches,” and the response generating unit 1206 may use the auxiliary information as the third keyword. On the other hand, in the comparative example without auxiliary information, the generated third keywords are "Potato Chips," "Potato Sticks," "Broccoli," "Cabbages," "Watermelon," "Eggs," "Bananas," "Potatoes," "Onions," "Oranges," "Apples," "Eggplants," "Pears," "Chestnuts," and "Peaches." As can be seen from the above, in the comparative example without auxiliary information, the third keywords include "Potato Chips" and "Potato Sticks," which do not belong to "fresh food," so the finally generated response data is inaccurate. On the other hand, in the example with auxiliary information, the third keywords all belong to "fresh food," so the finally generated response data is more accurate.

[0057] Example 3 14 is a flowchart illustrating an example of the flow of an information processing method 1400 according to an embodiment of the present disclosure. As shown in FIG. 14, the information processing method 1400 according to an embodiment of the present disclosure may start in step S1401 and end in step S1409.

[0058] For example, the information processing method 1400 may include a determining step S1402 and an auxiliary information obtaining step S1404.

[0059] In the determining step S1402, if the first keyword extracted from the input data is not included in the first subset corresponding to the first keyword in the predetermined dataset, it is determined that auxiliary information about the input data is needed. For example, the determining step S1402 may be performed by the determining unit 102 of the information processing device 100 according to the first embodiment. For details, refer to the description of the determining unit 102 above. The description will be simplified here.

[0060] In the auxiliary information acquisition step S1404, if it is determined in the determination step S1402 that auxiliary information is necessary, a plurality of data corresponding to the first keyword is extracted from the first subset to generate response data, and one or more data are selected as auxiliary information from the extracted plurality of data based on the input data. This makes it possible to acquire more appropriate response data and improve the accuracy of the finally acquired response data. For example, the auxiliary information acquisition step S1404 may be performed by the auxiliary information acquisition unit 104 of the information processing device 100 according to the first embodiment. The details thereof may refer to the description of the determination unit 102 above, and the description thereof will be simplified here.

[0061] In the determining step S1402, a code may be generated based on the input data, and a title corresponding to the first keyword and the first subset may be extracted from the code, thereby obtaining more accurate first keywords and titles and further improving the accuracy of the finally generated response data.

[0062] For example, in the auxiliary information acquisition step S1404, a plurality of data items corresponding to the first keyword may be extracted from the first subset, hint information may be generated based on the input data, and one or more pieces of data items may be selected as auxiliary information from the extracted plurality of data items based on the generated hint information. By acquiring the auxiliary information in this manner, the accuracy of the finally generated response data may be further improved.

[0063] As another example, in the auxiliary information acquisition step S1404, a plurality of data items corresponding to a first keyword may be extracted from the first subset, a second keyword may be extracted from the user feedback information, hint information may be generated based on the matching result between the second keyword and the extracted plurality of data items and the input data, and one or more data items may be selected as auxiliary information from the extracted plurality of data items based on the generated hint information. By acquiring auxiliary information in this manner, the accuracy of the finally generated response data may be further improved.

[0064] For example, the user feedback information includes at least one of feedback information on response data by a first user who inputted the input data, feedback information on auxiliary information by the first user, feedback information on corresponding response data by one or more second users different from the first user, and feedback information on corresponding auxiliary information by one or more second users.

[0065] For example, the input data includes at least one of a product name, a service name, a product category, and a service category. The second keyword includes a product name and / or a service name. Each of the extracted data includes a product name and / or a service name.

[0066] For example, for each piece of extracted data, if the data matches the second keyword, the hint information may include feedback information corresponding to the data in the user feedback information, whereas if none of the extracted data matches the second keyword, the hint information may not include any information in the user feedback information.

[0067] Example 4 15 is a flowchart illustrating an example of the flow of an information processing method according to an embodiment of the present disclosure. As shown in FIG. 15, an information processing method 1500 according to an embodiment of the present disclosure may start in step S1501 and end in step S1509.

[0068] As shown in FIG. 15, the information processing method 1500 may include a determining step S1502, an auxiliary information obtaining step S1504, and a response generating step S1506.

[0069] For example, the decision step S1502 and the auxiliary information acquisition step S1504 may be similar to the decision step S1402 and the auxiliary information acquisition step S1404 described in Example 3 above, so the above description may be referred to for details, and the description will be simplified here.

[0070] In response generation step S1506, response data for the input data may be generated. For example, if it is determined that auxiliary information is not required, response data may be generated based on the input data. On the other hand, if it is determined that auxiliary information is required, response data may be generated based on the auxiliary information acquired in auxiliary information acquisition step S1504 and the input data.

[0071] For example, the response generation step S1506 may be executed by the response generation unit 1206 of the information processing device 1200 according to the second embodiment, and the details thereof may refer to the description of the response generation unit 1206 above, and the description thereof will be simplified here.

[0072] Although the above describes an example in which the technology of the present disclosure may be realized by a large-scale language model, the technology of the present disclosure may be realized by other methods, for example, by writing corresponding computer program code, etc. Furthermore, when the technology of the present disclosure is realized by a large-scale language model, each functional module may be realized by the same large-scale language model or different large-scale language models.

[0073] Although the functional configurations and operations of the information processing device and information processing method according to the embodiments of the present disclosure have been described above, these functional configurations and operations are merely exemplary and do not limit the present disclosure. Those skilled in the art may modify the above embodiments in accordance with the principles of the present disclosure, for example, by adding, deleting, or combining functional modules in each embodiment, and these modifications are within the scope of the present disclosure.

[0074] Furthermore, since the device embodiments herein correspond to the method embodiments described above, for the contents not described in detail in the device embodiments, reference may be made to the corresponding explanations in the method embodiments described above, and such explanations will be omitted here.

[0075] The present disclosure also provides a storage medium and a program product, and the device-executable instructions in the storage medium and the program product according to the embodiments of the present disclosure may implement the above-described method. For the content not described in detail herein, please refer to the corresponding description of the above-described method embodiment, and the description thereof will be omitted here.

[0076] Accordingly, the present disclosure further includes a storage medium having recorded thereon a program product containing machine-executable instructions, including, but not limited to, a floppy disk, an optical disk, a magneto-optical disk, a memory card, a memory stick, and the like.

[0077] The above processes and devices may be realized by software and / or firmware. When implemented by software and / or firmware, a program constituting software for implementing the above method may be installed from a storage medium or a network onto a computer having a dedicated hardware configuration, such as a general-purpose personal computer 1600 shown in Fig. 16, and the computer can execute various functions when various programs are installed.

[0078] 16, a central processing unit (CPU) 1601 executes various processes according to programs stored in a read-only memory (ROM) 1602 or programs loaded from a storage unit 1608 into a random access memory (RAM) 1603. The RAM 1603 stores data necessary for the CPU 1601 to execute various processes as needed.

[0079] The CPU 1601, ROM 1602, and RAM 1603 are connected to one another via a bus 1604. An input / output interface 1605 is also connected to the bus 1604.

[0080] An input unit 1606 (including a keyboard, a mouse, etc.), an output unit 1607 (including a display, such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.), a storage unit 1608 (including, for example, a hard disk, etc.), and a communication unit 1609 (including, for example, a network interface card, such as a LAN card, a modem, etc.) are connected to the input / output interface 1605. The communication unit 1609 executes communication processing via a network, for example, the Internet.

[0081] If necessary, the driver 1610 may be connected to the input / output interface 1605. The removable medium 1611 is, for example, a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and is set up in the driver 1610 as necessary, and a computer program read from the removable medium 1611 is installed in the storage unit 1608 as necessary.

[0082] When the above processing is performed by software, a program constituting the software is installed via a network, such as the Internet, or a storage medium, such as a removable medium 1611 .

[0083] 16, which stores the program and provides the program to the user separately from the device. Removable medium 1611 includes, for example, a magnetic disk (including a floppy disk (registered trademark)), an optical disk (including an optical disk-read only memory (CD-ROM) and a digital versatile disk (DVD)), a magneto-optical disk (a minidisk (MD) (registered trademark)), and a semiconductor memory. Alternatively, the storage medium may be ROM 1602, a hard disk included in storage unit 1608, or the like, which stores the program and is provided to the user together with the device containing the program.

[0084] Although the preferred embodiments of the present disclosure have been described above with reference to the drawings, the above embodiments and examples are illustrative and not limiting. Those skilled in the art may make various modifications, improvements, and equivalent changes to the present disclosure within the spirit and scope of the claims. These modifications, improvements, and equivalent changes are intended to fall within the scope of protection of the present disclosure.

[0085] For example, the functions included in one unit in the above embodiments may be realized by separate devices. Furthermore, the functions realized by the multiple units in the above embodiments may each be realized by a separate device. Furthermore, one of the above functions may be realized by multiple units. These configurations are within the scope of the present disclosure.

[0086] Furthermore, the methods of the present disclosure are not limited to being performed in the chronological order described in the specification, and may be performed sequentially, in parallel, or independently in other chronological orders, and therefore the order of performing the methods described herein does not limit the technical scope of the present disclosure.

[0087] The various techniques described herein may be implemented independently of one another unless a contradiction arises. Note that any of the various techniques may also be implemented in combination. In one example, some or all of the techniques described herein may be implemented in combination with some or all of the techniques described in other embodiments. Furthermore, some or all of the techniques described herein may be implemented in combination with other techniques not described above.

[0088] Furthermore, the following supplementary notes are also disclosed regarding the embodiments including the above-described examples, but the present invention is not limited to these supplementary notes. (Appendix 1) a determining unit for determining that auxiliary information about the input data is needed when a first keyword extracted from the input data is not included in a first subset corresponding to the first keyword in a predetermined dataset; an auxiliary information acquisition unit that, when the determination unit determines that the auxiliary information is necessary, extracts a plurality of data corresponding to the first keyword from the first subset to generate response data, and selects one or more data from the extracted plurality of data as the auxiliary information based on the input data. (Appendix 2) The determining unit generates a code based on the input data, and extracts the first keyword and a title corresponding to the first subset from the code; 2. The information processing device according to claim 1, wherein the predetermined data set includes a plurality of subsets each corresponding to a different title. (Appendix 3) The auxiliary information acquisition unit: a data extraction subunit for extracting a plurality of data corresponding to the first keyword from the first subset; a hint information generating subunit for generating hint information based on the input data; a selection subunit that selects, as the auxiliary information, the one or more pieces of data from the plurality of pieces of data extracted by the data extraction subunit based on the hint information. (Appendix 4) The auxiliary information obtaining unit further includes a keyword extracting subunit for extracting a second keyword from the user feedback information; The information processing device described in Appendix 3, wherein the hint information generation subunit generates the hint information based on the matching result between the second keyword and each of the plurality of data extracted by the data extraction subunit and the input data. (Appendix 5) For each data item among the extracted plurality of data items, if the data item matches the second keyword, the hint information includes feedback information corresponding to the data item among the user feedback information; 5. The information processing device according to claim 4, wherein if none of the plurality of data matches the second keyword, the hint information does not include the user feedback information. (Appendix 6) Further comprising a response generation unit, the response generation unit comprising: If the auxiliary information is required, generating the response data based on the input data and the auxiliary information; 5. The information processing device according to claim 4, wherein, if the auxiliary information is not required, the response data is generated based on the input data. (Appendix 7) the input data includes at least one of a product name, a service name, a product category, and a service category; the second keyword includes a product name and / or a service name; 5. The information processing device according to claim 4, wherein each of the extracted data includes a product name and / or a service name. (Appendix 8) The user feedback information feedback information on the response data from a first user who inputs the input data; feedback information from the first user regarding the auxiliary information; feedback information in response to corresponding response data by one or more second users different from the first user; and 8. The information processing device according to any one of appendices 4 to 7, further comprising at least one of feedback information for the corresponding auxiliary information by the one or more second users. (Appendix 9) 7. The information processing device according to claim 6, wherein the determination unit, the auxiliary information acquisition unit and the response generation unit are realized by the same or different large-scale language models. (Appendix 10) determining that auxiliary information about the input data is needed if a first keyword extracted from the input data is not included in a first subset corresponding to the first keyword in a predetermined dataset; If it is determined that the auxiliary information is necessary, extracting a plurality of data corresponding to the first keyword from the first subset to generate response data, and selecting one or more data from the extracted plurality of data as the auxiliary information based on the input data. (Appendix 11) generating a code based on the input data, and extracting from the code a title corresponding to the first keyword and the first subset; 11. The information processing method of claim 10, wherein the predetermined data set includes multiple subsets each corresponding to a different title. (Appendix 12) generating hint information based on the input data; The information processing method according to claim 11, further comprising selecting the one or more pieces of data from the extracted plurality of pieces of data as the auxiliary information based on the hint information. (Appendix 13) extracting a second keyword from the user feedback information; The information processing method according to claim 12, wherein the hint information is generated based on a matching result between the second keyword and each of the extracted data, and the input data. (Appendix 14) For each data item among the extracted plurality of data items, if the data item matches the second keyword, the hint information includes feedback information corresponding to the data item among the user feedback information; An information processing method according to claim 13, wherein if none of the plurality of data matches the second keyword, the hint information does not include the user feedback information. (Appendix 15) generating the response data based on the input data and the auxiliary information if the auxiliary information is required; 14. The information processing method of claim 13, further comprising: if the auxiliary information is not required, generating the response data based on the input data. (Appendix 16) the input data includes at least one of a product name, a service name, a product category, and a service category; the second keyword includes a product name and / or a service name; An information processing method according to claim 13, wherein each of the extracted data includes a product name and / or a service name. (Appendix 17) The user feedback information feedback information on the response data from a first user who inputs the input data; feedback information from the first user regarding the auxiliary information; feedback information in response to corresponding response data by one or more second users different from the first user; and 17. The information processing method according to any one of appendices 13 to 16, including at least one of feedback information for the corresponding auxiliary information by the one or more second users. (Appendix 18) 18. A computer-readable storage medium having stored thereon instructions that, when executed by a computer, cause the computer to perform an information processing method according to any one of claims 10 to 17.

Claims

1. a determining unit for determining that auxiliary information about the input data is needed when a first keyword extracted from the input data is not included in a first subset corresponding to the first keyword in a predetermined dataset; an auxiliary information acquisition unit that, when the determination unit determines that the auxiliary information is necessary, extracts a plurality of data corresponding to the first keyword from the first subset to generate response data, and selects one or more data from the extracted plurality of data as the auxiliary information based on the input data.

2. The determining unit generates a code based on the input data, and extracts from the code a title corresponding to the first keyword and the first subset; The information processing apparatus according to claim 1 , wherein the predetermined data set includes a plurality of subsets each corresponding to a different title.

3. The auxiliary information acquisition unit: a data extraction subunit for extracting a plurality of data corresponding to the first keyword from the first subset; a hint information generating subunit for generating hint information based on the input data; The information processing apparatus according to claim 2 , further comprising: a selection subunit that selects, as the auxiliary information, the one or more pieces of data from the plurality of pieces of data extracted by the data extraction subunit based on the hint information.

4. The auxiliary information obtaining unit further includes a keyword extracting subunit for extracting a second keyword from the user feedback information; The information processing apparatus according to claim 3 , wherein the hint information generating subunit generates the hint information based on a matching result between the second keyword and each of the plurality of data extracted by the data extracting subunit and the input data.

5. For each data item among the extracted plurality of data items, if the data item matches the second keyword, the hint information includes feedback information corresponding to the data item among the user feedback information; The information processing apparatus according to claim 4 , wherein, when none of the plurality of pieces of data matches the second keyword, the hint information does not include the user feedback information.

6. Further comprising a response generation unit, the response generation unit comprising: If the auxiliary information is required, generating the response data based on the input data and the auxiliary information; The information processing apparatus according to claim 4 , wherein, when the auxiliary information is not necessary, the response data is generated based on the input data.

7. the input data includes at least one of a product name, a service name, a product category, and a service category; the second keyword includes a product name and / or a service name; The information processing device according to claim 4 , wherein each of the extracted data includes a product name and / or a service name.

8. The user feedback information feedback information on the response data from a first user who inputs the input data; feedback information on the auxiliary information by the first user; feedback information in response to corresponding response data by one or more second users different from the first user; and The information processing device according to claim 4 , further comprising at least one of feedback information for the corresponding auxiliary information by the one or more second users.

9. determining that auxiliary information about the input data is needed if a first keyword extracted from the input data is not included in a first subset corresponding to the first keyword in a predetermined dataset; If it is determined that the auxiliary information is necessary, extracting a plurality of data corresponding to the first keyword from the first subset to generate response data, and selecting one or more data from the extracted plurality of data as the auxiliary information based on the input data.

10. 10. A computer-readable storage medium having stored thereon instructions that, when executed by a computer, cause the computer to perform the information processing method of claim 9.

Images