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

Abstract

The invention discloses an information processing apparatus, an information processing method, and a computer readable storage medium. The 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 extract a plurality of pieces of data corresponding to the first keyword from the first subset under the condition that the determination unit determines that the auxiliary information is needed, and selecting, based on the input data, one or more pieces of data from the extracted pieces of data as the auxiliary information for generating response data.

Description

Technical Field

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

[0002] In many applications, a technique for automatically generating response data is required. Therefore, it is desirable to provide a technique that can facilitate the generation of more accurate response data. Summary of the Invention

[0003] A brief overview of the present disclosure is provided below to provide a basic understanding of certain aspects of the present disclosure. However, it should be understood that this overview is not an exhaustive overview of the present disclosure. It is not intended to identify key or important parts of the present disclosure, nor is it intended to limit the scope of the present disclosure. Its purpose is simply to present certain concepts of the present disclosure in a simplified form as a prelude to the more detailed description that will be given later.

[0004] An object of the present disclosure is to provide an improved information processing apparatus, information processing method, and computer-readable storage medium that can, for example, facilitate the generation of more accurate response data.

[0005] According to one aspect of the present disclosure, an information processing device is provided, comprising a determination unit configured to determine that auxiliary information for the input data is required when a first keyword extracted from 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 extract multiple pieces of data corresponding to the first keyword from the first subset when the determination unit determines that the auxiliary information is required, and select one or more pieces of data from the multiple pieces of data extracted as the auxiliary information based on the input data for generating response data.

[0006] According to another aspect of the present disclosure, an information processing method is provided, comprising: in a case where a first keyword extracted from input data is not included in a first subset corresponding to the first keyword in a predetermined data set, determining that auxiliary information for the input data is needed; and in a case where it is determined that the auxiliary information is needed, extracting multiple data corresponding to the first keyword from the first subset, and selecting one or more data from the multiple data extracted based on the input data as the auxiliary information for generating response data.

[0007] According to other aspects of the present disclosure, a computer program code and a computer program product for implementing the above-mentioned method according to the present disclosure, as well as a computer-readable storage medium having the computer program code for implementing the above-mentioned method according to the present disclosure recorded thereon are also provided.

[0008] Other aspects of the embodiments of the present disclosure are given in the following description, wherein the detailed description is used to fully disclose the preferred embodiments of the embodiments of the present disclosure without imposing limitations thereon. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The present disclosure may be better understood by referring to the detailed description given below in conjunction with the accompanying drawings, in which the same or similar reference numerals are used throughout the drawings to represent the same or similar parts. The accompanying drawings, together with the following detailed description, are incorporated into and form a part of this specification and are used to further illustrate the preferred embodiments of the present disclosure and to explain the principles and advantages of the present disclosure. Among them:

[0010] Figure 1 is a block diagram illustrating a functional configuration example of an information processing apparatus according to an embodiment of the present disclosure;

[0011] Figure 2 is a schematic diagram showing a specific architecture example of an information processing device according to the disclosed embodiment;

[0012] Figure 3A and Figure 3B Show examples of the provided prompts;

[0013] Figure 4A and Figure 4B showing an example of a portion of a predetermined data set;

[0014] Figure 5A and Figure 5B shows an example of another prompt provided;

[0015] Figure 6 shows an example of the generated code;

[0016] Figure 7A and Figure 7B An example of another prompt provided is shown;

[0017] Figure 8 is a block diagram illustrating a functional configuration example of an auxiliary information acquisition unit according to an embodiment of the present disclosure;

[0018] Figure 9 is a schematic diagram illustrating a specific architecture example of an auxiliary information acquisition unit according to an embodiment of the present disclosure;

[0019] Figures 10A to 11B An example of the generated prompt information is shown;

[0020] Figure 12 is a block diagram illustrating a functional configuration example of an information processing apparatus according to an embodiment of the present disclosure;

[0021] Figure 13 is a schematic diagram illustrating a specific architecture example of an information processing device according to the disclosed embodiment.

[0022] Figure 14 is a flowchart illustrating an example of the flow of an information processing method according to an embodiment of the present disclosure;

[0023] Figure 15 is a flowchart showing an example of the flow of an information processing method according to an embodiment of the present disclosure; and

[0024] Figure 16 : is a block diagram showing an example structure of a personal computer that can be employed in the embodiments of the present disclosure. DETAILED DESCRIPTION

[0025] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings. For the sake of clarity and conciseness, not all features of an actual implementation are described in this specification. However, it should be understood that in the process of developing any such actual implementation, many implementation-specific decisions must be made in order to achieve the developer's specific goals, such as compliance with system and business-related constraints, which may vary from implementation to implementation. In addition, it should be understood that although the development work may be very complex and time-consuming, it is a routine task for those skilled in the art who benefit from the contents of this disclosure.

[0026] For example, in this document, terms such as “first” and “second” may be used to distinguish different elements, but such terms do not limit the number, order, etc. of the elements.

[0027] It is also necessary to explain here that, in order to avoid obscuring the present disclosure due to unnecessary details, the accompanying drawings only show the device structure and / or processing steps closely related to the scheme according to the present disclosure, while other details that are not closely related to the present disclosure are omitted.

[0028] Embodiments according to various aspects of the present disclosure are described in detail below with reference to the accompanying drawings.

[0029] Embodiments of the first aspect

[0030] Figure 1 1 is a block diagram illustrating a functional configuration example of the information processing device 100 according to an embodiment of the present disclosure. Figure 2 1 is a schematic diagram showing a specific architecture example of the information processing device 100 according to the disclosed embodiment. Figure 2 In FIG, some processes are shown with dashed arrows, which means that in some examples, one or more of these processes may not be included. Figure 2 middle, Represents a large language model.

[0031] like Figure 1 As shown, the information processing device 100 according to an embodiment of the present disclosure may include a determining unit 102 and an auxiliary information acquiring unit 104 .

[0032] The determining unit 102 may be configured to determine that auxiliary information for the input data is required if a first keyword extracted from the input data (eg, a query) is not included in a first subset corresponding to the first keyword in a predetermined data set.

[0033] The auxiliary information acquisition unit 104 can be configured to extract multiple data corresponding to the first keyword from the first subset when the determination unit 102 determines that auxiliary information is needed, and select one or more data from the extracted multiple data as auxiliary information based on the input data to generate response data, so that more appropriate response data can be obtained, the accuracy of the response data finally obtained can be improved, etc.

[0034] In some examples, such as Figure 2 As shown, the auxiliary information acquisition unit 104 can select one or more pieces of data from the extracted multiple pieces of data as auxiliary information based on the input data and user feedback information, so as to obtain more appropriate response data and further improve the accuracy of the response data finally obtained.

[0035] For example, the user feedback information may include feedback information regarding the response data from a first user who input the input data. In some examples, the user feedback information may also include feedback information regarding the corresponding response data from one or more second users different from the first user, thereby increasing the amount of user feedback information and further improving the accuracy of the ultimately generated response data.

[0036] In some examples, user feedback information may include feedback information on auxiliary information, thereby improving the accuracy of the auxiliary information and, in turn, further improving 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 from a first user. The feedback information on the auxiliary information may also include feedback information on the corresponding auxiliary information from one or more second users, thereby further improving the accuracy of the auxiliary information and, in turn, further improving the accuracy of the ultimately generated response data.

[0037] In some examples, user feedback information may include feedback information on response data (e.g., feedback information on the response data from the first user, and feedback information on the corresponding response data from one or more second users) and feedback information on auxiliary information (e.g., feedback information on the auxiliary information from the first user, and feedback information on the corresponding auxiliary information from one or more second users), thereby further improving the accuracy of the response data finally generated.

[0038] For example, the information processing device 100 can be used in stores (including physical stores, online stores, etc.) to help users determine sales information, etc. For example, the predetermined data set can be customer consumption records of the store, such as service usage records, item purchase records, etc.

[0039] For example, the information processing device 100 can be used in a hospital to help users determine patient treatment information. For example, the predetermined data set can be a patient's treatment records, such as medication usage records, laboratory test records, etc. Of course, the application of the information processing device 100 is not limited to the above examples. For example, the information processing device 100 can also be used to query traffic violation information.

[0040] For example, the predetermined data set may include subsets that each correspond to a different title. For instance, the predetermined data set may include object identification information, time, target information, etc. The 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. As an example, when the information processing device 100 is used in a store or a pharmacy, the object may be a consumer, and the target information may be the name of the item purchased by the consumer and / or the name of the service used, but is not limited thereto. As another example, when the information processing device 100 is used in a hospital, the object may be a patient, and the target information may be the name of the medicine purchased by the patient, the name of the test received, etc., but is not limited thereto.

[0041] For example, the predetermined data set may be provided by a user and stored in a memory. For example, the predetermined data set may be structured data, such as an SQL database or a CSV file, but is not limited thereto.

[0042] The memory may be included in the information processing device 100 or may be accessed by the information processing device 100. In some examples, the memory stores only a portion of the predetermined data set, such as a subset of the predetermined data set that is determined to be indexed (e.g., Figure 2 As shown), thereby reducing the amount of information storage. As an example, a subset including text in a predetermined data set can be determined as a subset that needs to be indexed.

[0043] For example, a large language model can be used to determine the subset that needs to be indexed. In this case, the large language model can be fed with Figure 3A or Figure 3B The hint shown in the figure helps it determine the subset that needs to be indexed. Figure 3A and Figure 3B In the example, {df_info} represents the information of the predetermined dataset, including the title of each subset and other data of each subset except the title. {titles} is the title of each subset.

[0044] exist Figure 4A and Figure 4B In the example of a portion of the predetermined data set shown, the titles of the respective subsets are "Customer_id" ("customer identification information"), "Check-out time" ("checkout time"), and "Purchased products" ("purchased items"). In the example of determining that a subset including text is a subset to be indexed, Figure 4A and Figure 4B In the example shown, the data corresponding to the title "Purchased products" may be determined as the data that needs to be indexed.

[0045] For example, the input data may include information about the target information. As an example, the input data may include at least one of an item name, a service name, an item category, and a service category.

[0046] To better understand the embodiments of the present disclosure, the information processing device 100 will be further described below with reference to an example in which the information processing device 100 is used in a store, the object is a consumer, and the target information is the name of an item purchased by the consumer.

[0047] The information processing device 100 can operate based on various language environments. In this article, for the sake of convenience, the example of the information processing device 100 operating based on the English environment will be mainly used for explanation, and the Chinese language will be annotated in brackets after the corresponding English word / sentence when it first appears.

[0048] For example, the determination unit 102 may extract a first keyword from the input data, determine a title corresponding to the first keyword, retrieve the first keyword from a first subset corresponding to the title in a predetermined data set, and determine that auxiliary information for the input data is needed if the first keyword is not retrieved.

[0049] For example, in the case where the input data includes item names, service names, item categories and / or service categories, the first keyword may include the item names, service names, item categories and / or service categories included in the input data.

[0050] For example, the determination unit 102 can generate code (e.g., computer language code, such as Python code) based on the input data, and extract the first keyword and the title corresponding to the first subset from the code, thereby obtaining more accurate first keywords and titles, further improving the accuracy of the response data finally generated.

[0051] For example, when the determining unit 102 is implemented by a large language model, a hint may be provided to the large language model to assist the large language model in generating appropriate code. Figure 5A and Figure 5B Examples of prompts provided in English and Chinese environments are shown respectively, and Figure 6 An example of a code generated based on the input data "who bought fresh food?" is shown. Figure 5A and Figure 5B In

[15] , {file_info} represents file information, such as information about a predetermined data set.

[0052] from Figure 6 It can be seen that the generated code includes the expected first keyword "fresh food" and the title "Purchased products" corresponding to the first keyword.

[0053] For example, hints may be provided to the large language model to make the first keyword and the corresponding title extracted by the large language model from the generated code more accurate. Figure 7A and Figure 7B Examples of prompts provided in English and Chinese environments are shown respectively. Figure 7A In the case of the prompt shown, the extraction result is {"Purchased products":["fresh food"]}, which includes the expected first keyword "fresh food" and the corresponding title "Purchased products". This shows that the above method can accurately extract the first keyword and the corresponding title.

[0054] exist Figure 4AIn the example shown, since the column corresponding to "Purchased products" (an example of the first subset) shows specific item names and does not include the first keyword "fresh food," determination unit 102 may determine that auxiliary information is required. In this case, auxiliary information acquisition unit 104 may extract multiple pieces of data corresponding to the first keyword from the first subset and select one or more pieces of data from the extracted multiple pieces of data as auxiliary information based on the input data or the input data and user feedback information.

[0055] In some examples, for each of the multiple pieces of data extracted, the auxiliary information acquisition unit 104 may determine whether the piece of data matches the first keyword based on the input data or the input data and user feedback information. For example, the auxiliary information acquisition unit 104 may determine whether the piece of data matches the first keyword based on whether the piece of data belongs to the category defined by the first keyword. If it is determined that the piece of data matches the first keyword (for example, the piece of data belongs to the category defined by the first keyword), the auxiliary information acquisition unit 104 may select the piece of data as auxiliary information. On the other hand, if it is determined that the piece of data does not match the first keyword (the piece of data does not belong to the category defined by the first keyword), the auxiliary information acquisition unit 104 will not select the piece of data as auxiliary information.

[0056] The following will refer to Figure 8 and Figure 9 A specific configuration example of the auxiliary information acquisition unit 104 will be described. Figure 8 is a block diagram illustrating a functional configuration example of an auxiliary information acquisition unit according to an embodiment of the present disclosure. Figure 9 : is a schematic diagram showing a specific architecture example of an auxiliary information acquisition unit according to an embodiment of the present disclosure. Figure 8 and Figure 9 The keyword extraction subunit 1044 is shown in a dotted box in FIG. 8 , which indicates that the auxiliary information acquisition unit 104 may not include the keyword extraction subunit 1044 in some examples.

[0057] In some examples, such as Figure 8 As shown, the auxiliary information acquisition unit 104 may include a data extraction subunit 1042 , a prompt information generation subunit 1046 and a selection subunit 1048 .

[0058] The data extraction subunit 1042 can be configured to extract multiple pieces of data corresponding to the first keyword from the first subset. Figures 3A to 7BIn the described example, the data extraction subunit 1042 can extract multiple data corresponding to the first keyword "fresh food" from the column corresponding to the title "Purchased products" (an example of the first subset), and the obtained results are: "Broccoli", "Cabbages", "Watermelon", "Eggs", "Bananas", "Potatoes", "Onions", "Orange Juice", "Apples", "Eggplants", "Oranges", "Prawn Crackers", "Pears", "Chestnuts", "Iced Tea", "Cookies"... ("Broccoli", "Cabbage", "Watermelon", "Eggs", "Bananas", "Potatoes", "Onions", "Orange Juice", "Apples", "Eggplant", "Oranges", "Prawn Crackers", "Pears", "Chestnuts", "Iced Tea", "Cookies"...).

[0059] The prompt information generating subunit 1046 may be configured to generate prompt information based on the input data.

[0060] The selection subunit 1048 may be configured to select one or more pieces of data as auxiliary information from the multiple pieces of data extracted by the data extraction subunit 1042 based on the prompt information generated by the prompt information generation subunit 1046. The auxiliary information obtained in this manner may further improve the accuracy of the ultimately generated response data.

[0061] In some examples, the auxiliary information acquisition unit 104 may further include a keyword extraction subunit 1044. The keyword extraction subunit 1044 may be configured to extract a second keyword from the user feedback information. The user feedback information may include one or more pieces of feedback information.

[0062] For example, the second keyword may include an item name and / or a service name. For example, for the feedback information “Orange Juice do not belong to fresh food”, the extracted second keyword is “Orange Juice”.

[0063] The prompt information generating subunit 1044 may be configured to generate prompt information based on the matching results of the second keyword and the plurality of extracted data and the input data. The auxiliary information obtained based on the prompt information obtained in this way may further improve the accuracy of the ultimately generated response data.

[0064] In some examples, for each piece of data, if the data and the second keyword include words related to the same category, the data can be considered to match the second keyword. Figures 3A to 7B In the example described above, for each piece of data, if the item name included in the data belongs to the same category as the item name included in the second keyword, the data can be considered to match the second keyword. For example, in the above-mentioned example of multiple pieces of data corresponding to the first keyword "fresh food", "Orange Juice" and "Iced Tea" belong to the same category as the second keyword "Orange Juice" extracted from the feedback information "Orange Juice does not belong to fresh food". Therefore, "Orange Juice" and "Iced Tea" can be considered to match the second keyword "Orange Juice", while the other data do not match the second keyword "Orange Juice".

[0065] For example, when the auxiliary information acquisition unit 104 is implemented by a large language model, a prompt can be provided to the large language model so that it can more accurately determine whether each piece of data matches the second keyword. For example, the prompt provided can be "Do {keyword_from_retrieval} and {keyword_from_feedback} belong to abroad category?" ("Do {keyword_from_retrieval} and {keyword_from_feedback} belong to the same category?"). Wherein, {keyword_from_retrieval} and {keyword_from_feedback} represent the data extracted by the data extraction subunit 1042 and the second keyword extracted by the keyword extraction subunit 1044, respectively.

[0066] In some examples, for each piece of data extracted, if the data matches the second keyword, the prompt information includes feedback information corresponding to the data in the user feedback information. In addition, if none of the multiple pieces of data extracted match the second keyword, the prompt information does not include the user feedback information. Figure 10A and Figure 10B The prompt information including the user feedback information and the prompt information including the corresponding feedback information are shown respectively. Figure 11A and Figure 11B Shown respectively with Figure 10A and Figure 10B Corresponding Chinese. Figures 10A to 11BIn

[15] , "keyword_from_user_query" indicates the first keyword extracted from the input data.

[0067] exist Figure 10B and Figure 11B "Example" can be feedback information in the user feedback information corresponding to data in the extracted multiple data items that matches the second keyword. For example, in the example of multiple data items corresponding to the first keyword "fresh food" mentioned above, the data "Orange Juice" matches the second keyword "Orange Juice" extracted from the feedback information "Orange Juice does not belong to fresh food." Therefore, the prompt information can include the feedback information "Orange Juice does not belong to fresh food" corresponding to the data "Orange Juice" in the user feedback information.

[0068] Embodiments of the second aspect

[0069] Figure 12 12 is a block diagram illustrating a functional configuration example of the information processing device 1200 according to an embodiment of the present disclosure. Figure 13 1 is a schematic diagram showing a specific architecture example of the information processing device 1200 according to the disclosed embodiment. Figure 12 and Figure 13 As shown, the information processing device 1200 according to an embodiment of the present disclosure may include a determining unit 1202 , an auxiliary information acquiring unit 1204 , and a response generating unit 1206 .

[0070] For example, the determination unit 1202 and the auxiliary information acquisition unit 1204 may have configurations similar to those of the determination unit 102 and the auxiliary information acquisition unit 104 described above in the embodiment of the first aspect, so the specific details can be found in the above description and will not be described in detail below.

[0071] The response generation unit 1206 can be configured to generate response data for the input data. For example, in the case where the determination unit 1202 determines that auxiliary information is not required, the response generation unit 1206 can generate response data based on the input data. In some examples, the response generation unit 1206 can retrieve the first keyword from the target data set and generate response data based on the input data and the retrieved data. For example, in the above combination Figures 3A to 7BIn the example described, for the input data "Who bought Apples?", since the column corresponding to "Purchased products" (an example of the first subset) includes the first keyword "Apples," determination unit 1202 may determine that auxiliary information is not required. Response generation unit 1206 may retrieve the first keyword "Apples" from the target dataset and use the Customer_id in the retrieved data (e.g., data containing the first keyword "Apples") as response data.

[0072] On the other hand, if the determination unit 1202 determines that auxiliary information is required, the response generation unit 1206 may generate response data based on the auxiliary information acquired by the auxiliary information acquisition unit 1204 and the input data. In some examples, the response generation unit 1206 may generate a third keyword based on the auxiliary information, retrieve corresponding data from the target dataset based on the third keyword, and generate response data based on the input data and the retrieved data. As an example, if the target dataset is the same as the predetermined dataset, the response generation unit 1206 may use the auxiliary information as the third keyword.

[0073] For example, combining the above Figures 3A to 7BIn the described example, for the input data "who bought fresh food?", since the column corresponding to "Purchased products" (an example of the first subset) shows specific item names, which does not include the first keyword "fresh food", the determination unit 1202 can determine that auxiliary information is needed. In one example, the auxiliary information generated by the auxiliary information acquisition unit 1204 is: “Broccoli”, “Cabbages”, “Watermelon”, “Eggs”, “Bananas”, “Potatoes”, “Onions”, “Oranges”, “Apples”, “Eggplants”, “Pears”, “Chestnuts”, Peaches”, and the response generation unit 1206 can use the auxiliary information as the third keyword. On the other hand, in a comparative example without auxiliary information, the generated third keyword is: “PotatoChips”, “Potato Sticks”, “Broccoli”, “Cabbages”, “Watermelon”, “Eggs”, “Bananas”, “Potatoes”, “Onions”, “Oranges”, “Apples”, “Eggplants”, “Pears”, “Chestnuts”, Peaches”. As can be seen, in the comparison example without auxiliary information, the third keyword includes "Potato Chips" and "Potato Sticks," which do not belong to the category "fresh food," so the resulting response data is inaccurate. On the other hand, in the example with auxiliary information, the third keyword all belongs to the category "fresh food," so the resulting response data is more accurate.

[0074] Embodiments of the third aspect

[0075] Figure 14 1400 is a flowchart showing an example of the process of the information processing method 1400 according to an embodiment of the present disclosure. Figure 14 As shown, the information processing method 1400 according to an embodiment of the present disclosure may start at S1401 and end at S1409.

[0076] For example, the information processing method 1400 may include a determining step S1402 and an auxiliary information acquiring step S1404.

[0077] In 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 data set, it is determined that auxiliary information specific to the input data is required. For example, determining step S1402 may be performed by determining unit 102 in information processing apparatus 100 according to an embodiment of the first aspect. For details, see the above description of determining unit 102. The following is a brief description.

[0078] In auxiliary information acquisition step S1404, if it is determined in step S1402 that auxiliary information is required, multiple pieces of data corresponding to the first keyword are extracted from the first subset, and one or more pieces of data are selected from the extracted multiple pieces of data based on the input data as auxiliary information for use in generating response data. This allows for obtaining more appropriate response data, improving the accuracy of the ultimately obtained response data, etc. For example, auxiliary information acquisition step S1404 may be performed by auxiliary information acquisition unit 104 in information processing device 100 according to an embodiment of the first aspect. For details, refer to the above description of auxiliary information acquisition unit 104, and only a brief description is provided below.

[0079] In the determination step S1402, a code may be generated based on the input data, and the first keyword and the title corresponding to the first subset may be extracted from the code, thereby obtaining more accurate first keywords and titles, further improving the accuracy of the ultimately generated response data.

[0080] As an example, in the auxiliary information acquisition step S1404, multiple pieces of data corresponding to the first keyword can be extracted from the first subset, prompt information can be generated based on the input data, and based on the generated prompt information, one or more pieces of data can be selected from the extracted multiple pieces of data as auxiliary information. The auxiliary information obtained in this way can further improve the accuracy of the ultimately generated response data.

[0081] As another example, in the auxiliary information acquisition step S1404, multiple pieces of data corresponding to the first keyword can be extracted from the first subset, a second keyword can be extracted from the user feedback information, prompt information can be generated based on the matching results between the second keyword and the multiple pieces of data extracted and the input data, and based on the generated prompt information, one or more pieces of data can be selected from the multiple pieces of data extracted as auxiliary information. The auxiliary information obtained in this way can further improve the accuracy of the ultimately generated response data.

[0082] For example, the user feedback information includes at least one of the following: feedback information of the first user who inputs the input data on the response data; feedback information of the first user on the auxiliary information; feedback information of one or more second users different from the first user on the corresponding response data; and feedback information of one or more second users on the corresponding auxiliary information.

[0083] For example, the input data includes at least one of the following: an item name, a service name, an item category, and a service category. The second keyword includes an item name and / or a service name, and each of the extracted pieces of data includes an item name and / or a service name.

[0084] For example, for each piece of data extracted, if the data matches the second keyword, the prompt information may include feedback information corresponding to the data in the user feedback information. In addition, if none of the multiple pieces of data extracted match the second keyword, the prompt information may not include any information in the user feedback information.

[0085] Embodiments of the fourth aspect

[0086] Figure 15 : is a flowchart showing an example of the process of the information processing method according to an embodiment of the present disclosure. Figure 15 As shown, the information processing method 1500 according to an embodiment of the present disclosure may start at S1501 and end at S1509.

[0087] like Figure 15 As shown, the information processing method 1500 according to an embodiment of the present disclosure may include a determining step S1502 , an auxiliary information acquiring step S1504 , and a response generating step S1506 .

[0088] For example, the determination step S1502 and the auxiliary information acquisition step S1504 may be similar to the determination step S1402 and the auxiliary information acquisition step S1404 described above in the embodiment of the third aspect, so the specific details can be found in the above description and will not be described in detail below.

[0089] In the response generation step S1506, response data may be generated for the input data. For example, if it is determined that auxiliary information is not required, the response data may be generated based on the input data. On the other hand, if it is determined that auxiliary information is required, the response data may be generated based on the auxiliary information obtained in the auxiliary information acquisition step S1504 and the input data.

[0090] For example, the response generation step S1506 can be performed by the response generation unit 1206 in the information processing device 1200 according to the embodiment of the second aspect. Therefore, the specific details can be found in the above description of the response generation unit 1206, which will not be described again below.

[0091] Note that although the above describes an example in which the technology of the present disclosure can be implemented using a large language model, the technology of the present disclosure can be implemented in other ways, such as by writing corresponding computer program code. In addition, when the technology of the present disclosure is implemented using a large language model, the various functional modules can be implemented using the same large language model or different large language models.

[0092] It should be noted that although the functional configuration and operation of the information processing device and method according to the embodiments of the present disclosure are described above, this is only an example and not a limitation, and those skilled in the art may modify the above embodiments according to the principles of the present disclosure, for example, the functional modules in each embodiment may be added, deleted or combined, and such modifications shall fall within the scope of the present disclosure.

[0093] In addition, it should be pointed out that the method embodiment here corresponds to the above-mentioned device embodiment. Therefore, for the contents not described in detail in the method embodiment, please refer to the description of the corresponding parts in the device embodiment, and the description will not be repeated here.

[0094] It should be understood that the machine-executable instructions in the storage medium and program products according to the embodiments of the present disclosure can also be configured to execute the above-mentioned information processing method. Therefore, the content not described in detail here can refer to the description of the previous corresponding parts and will not be repeated here.

[0095] Accordingly, the storage medium for carrying the program product including the machine-executable instructions is also included in the disclosure of the present invention, including but not limited to a floppy disk, an optical disk, a magneto-optical disk, a memory card, a memory stick, and the like.

[0096] In addition, it should be noted that the above series of processes and devices can also be implemented by software and / or firmware. In the case of implementation by software and / or firmware, the data is transmitted from a storage medium or a network to a computer with a dedicated hardware structure, such as Figure 16 The general-purpose personal computer 1600 shown is installed with programs constituting the software. When various programs are installed, the computer can execute various functions and the like.

[0097] exist Figure 16In the embodiment, a central processing unit (CPU) 1601 executes various processes according to a program stored in a read-only memory (ROM) 1602 or a program loaded from a storage device 1608 to a random access memory (RAM) 1603. In the RAM 1603, data required when the CPU 1601 executes various processes and the like is also stored as needed.

[0098] The CPU 1601, the ROM 1602, and the RAM 1603 are connected to one another via a bus 1604. An input / output interface 1605 is also connected to the bus 1604.

[0099] The following components are connected to the input / output interface 1605: an input device 1606 including a keyboard, a mouse, etc.; an output device 1607 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage device 1608 including a hard disk, etc.; and a communication device 1609 including a network interface card such as a LAN card, a modem, etc. The communication device 1609 performs communication processing via a network such as the Internet.

[0100] A drive 1610 is also connected to the input / output interface 1605 as needed. A removable medium 1611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 1610 as needed so that a computer program read therefrom is installed in the storage device 1608 as needed.

[0101] In the case of realizing the above-described series of processing by software, a program constituting the software is installed from a network such as the Internet or a storage medium such as the removable medium 1611 .

[0102] It should be understood by those skilled in the art that such storage media is not limited to Figure 16 The removable medium 1611 shown has a program stored therein and is distributed separately from the device to provide the program to the user. Examples of removable medium 1611 include magnetic disks (including floppy disks (registered trademark)), optical disks (including compact disk read-only memories (CD-ROMs) and digital versatile disks (DVDs)), magneto-optical disks (including minidiscs (MDs) (registered trademark)), and semiconductor memories. Alternatively, the storage medium may be ROM 1602, a hard disk included in storage device 1608, or the like, in which the program is stored and distributed to the user along with the device containing it.

[0103] The preferred embodiments of the present disclosure are described above with reference to the accompanying drawings, but the present disclosure is of course not limited to the above examples. Those skilled in the art may obtain various changes and modifications within the scope of the appended claims, and it should be understood that these changes and modifications will naturally fall within the technical scope of the present disclosure.

[0104] For example, a plurality of functions included in one unit in the above embodiments may be implemented by separate devices. Alternatively, a plurality of functions implemented by a plurality of units in the above embodiments may be implemented by separate devices, respectively. In addition, one of the above functions may be implemented by a plurality of units. Needless to say, such a configuration is included in the technical scope of the present disclosure.

[0105] In this specification, the steps described in the flowchart include not only processing executed in time series in the order described, but also processing executed in parallel or individually rather than necessarily in time series. In addition, even in the steps processed in time series, it goes without saying that the order can be changed as appropriate.

[0106] The various techniques described in this specification can be performed independently of each other unless a conflict arises. Of course, any of the various techniques can be performed in combination. In one example, part or all of the techniques described in any embodiment can be performed in combination with part or all of the techniques described in another embodiment. In addition, any part or all of the techniques described above can be performed in combination with another technique not described above.

[0107] Additionally, the technology according to the present disclosure can also be configured as follows.

[0108] Note 1. An information processing device comprising:

[0109] a determining unit configured to determine that auxiliary information for the input data is required if 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

[0110] An auxiliary information acquisition unit is configured to extract multiple data corresponding to the first keyword from the first subset when the determination unit determines that the auxiliary information is needed, and select one or more data from the extracted multiple data as the auxiliary information based on the input data for generating response data.

[0111] Supplement 2. The information processing device according to Supplement 1, wherein the determining unit is further configured to generate a code based on the input data, and extract the first keyword and the title corresponding to the first subset from the code,

[0112] The predetermined data set includes a plurality of subsets each corresponding to a different title.

[0113] Supplement 3. The information processing device according to Supplement 2, wherein the auxiliary information acquisition unit includes:

[0114] a data extraction subunit, configured to extract a plurality of pieces of data corresponding to the first keyword from the first subset;

[0115] a prompt information generating subunit, configured to generate prompt information based on the input data; and

[0116] The selection subunit is configured to select the one or more pieces of data as the auxiliary information from the plurality of pieces of data extracted by the data extraction subunit based on the prompt information.

[0117] Note 4. The information processing device according to Note 3, wherein the auxiliary information acquisition unit further comprises: a keyword extraction subunit configured to extract a second keyword from the user feedback information, and

[0118] The prompt information generating subunit is further configured to generate the prompt information based on the matching results between the second keyword and the plurality of pieces of data extracted by the data extracting subunit and the input data.

[0119] Supplement 5. The information processing device according to Supplement 4, wherein, for each piece of the extracted data, when the data matches the second keyword, the prompt information includes feedback information corresponding to the data in the user feedback information, and

[0120] Wherein, when none of the multiple pieces of data match the second keyword, the prompt information does not include the user feedback information.

[0121] Supplementary Note 6. The information processing device according to Supplementary Note 4 further includes a response generation unit configured to:

[0122] generating the response data based on the input data and the auxiliary information if the auxiliary information is required; and

[0123] The response data is generated based on the input data without requiring the auxiliary information.

[0124] Supplement 7. The information processing device according to Supplement 4, wherein the input data includes at least one of the following: an item name, a service name, an item category, and a service category,

[0125] The second keyword includes the name of the item and / or the name of the service, and

[0126] Each of the extracted pieces of data includes an item name and / or a service name.

[0127] Supplement 8. The information processing device according to any one of Supplements 4 to 7, wherein the user feedback information includes at least one of the following:

[0128] Feedback information of the first user who inputs the input data on the response data;

[0129] Feedback information of the first user on the auxiliary information;

[0130] Feedback information of one or more second users different from the first user on the corresponding response data; and

[0131] Feedback information of the one or more second users on the corresponding auxiliary information.

[0132] Note 9: The information processing device according to Note 6, wherein the determination unit, the auxiliary information acquisition unit and the response generation unit are implemented by the same or different large language models.

[0133] Note 10. An information processing method comprising:

[0134] determining that auxiliary information for the input data is required if 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

[0135] If it is determined that the auxiliary information is needed, multiple pieces of data corresponding to the first keyword are extracted from the first subset, and one or more pieces of data are selected from the extracted multiple pieces of data as the auxiliary information based on the input data for generating response data.

[0136] Supplement 11. The information processing method according to Supplement 10 further comprises: generating a code based on the input data, and extracting the first keyword and the title corresponding to the first subset from the code,

[0137] The predetermined data set includes a plurality of subsets each corresponding to a different title.

[0138] Note 12. The information processing method according to Note 11 further comprises: generating prompt information based on the input data,

[0139] The one or more pieces of data are selected from the extracted multiple pieces of data as the auxiliary information based on the prompt information.

[0140] Note 13. The information processing method according to Note 12 further includes: extracting a second keyword from the user feedback information,

[0141] The prompt information is generated based on the matching results between the second keyword and the extracted multiple pieces of data and the input data.

[0142] Note 14. The information processing method according to Note 13, wherein, for each piece of the extracted data, when the data matches the second keyword, the prompt information includes feedback information corresponding to the data in the user feedback information, and

[0143] Wherein, when none of the multiple pieces of data match the second keyword, the prompt information does not include the user feedback information.

[0144] Note 15. The information processing method according to Note 13 further includes:

[0145] generating the response data based on the input data and the auxiliary information if the auxiliary information is required; and

[0146] The response data is generated based on the input data without requiring the auxiliary information.

[0147] Note 16. The information processing method according to Note 13, wherein the input data includes at least one of the following: an item name, a service name, an item category, and a service category, the second keyword includes the item name and / or the service name, and

[0148] Each of the extracted pieces of data includes an item name and / or a service name.

[0149] Note 17. The information processing method according to any one of Notes 13 to 16, wherein the user feedback information includes at least one of the following:

[0150] Feedback information of the first user who inputs the input data on the response data;

[0151] Feedback information of the first user on the auxiliary information;

[0152] Feedback information of one or more second users different from the first user on the corresponding response data; and

[0153] Feedback information of the one or more second users on the corresponding auxiliary information.

[0154] Note 18. A computer-readable storage medium storing instructions, wherein when the instructions are executed by a computer, the computer executes the information processing method according to any one of Notes 10 to 17.

Claims

1. An information processing device, comprising: a determining unit configured to determine that auxiliary information for the input data is required if 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; as well as An auxiliary information acquisition unit is configured to extract multiple data corresponding to the first keyword from the first subset when the determination unit determines that the auxiliary information is needed, and select one or more data from the extracted multiple data as the auxiliary information based on the input data for generating response data.

2. The information processing apparatus according to claim 1 , wherein the determining unit is further configured to generate a code based on the input data, and extract the first keyword and the title corresponding to the first subset from the code, in, The predetermined data set includes a plurality of subsets each corresponding to a different topic.

3. The information processing device according to claim 2, wherein: The auxiliary information acquisition unit includes: a data extraction subunit, configured to extract a plurality of pieces of data corresponding to the first keyword from the first subset; a prompt information generating subunit, configured to generate prompt information based on the input data; and The selection subunit is configured to select the one or more pieces of data as the auxiliary information from the plurality of pieces of data extracted by the data extraction subunit based on the prompt information.

4. The information processing device according to claim 3, wherein: The auxiliary information acquisition unit further includes: a keyword extraction subunit configured to extract a second keyword from the user feedback information, and The prompt information generating subunit is further configured to generate the prompt information based on the matching results between the second keyword and the plurality of pieces of data extracted by the data extracting subunit and the input data.

5. The information processing apparatus according to claim 4, wherein: For each piece of the extracted data, when the data matches the second keyword, the prompt information includes feedback information corresponding to the data in the user feedback information, and Wherein, when none of the multiple pieces of data match the second keyword, the prompt information does not include the user feedback information.

6. The information processing apparatus according to claim 4, further comprising a response generating unit configured to: generating the response data based on the input data and the auxiliary information if the auxiliary information is required; and The response data is generated based on the input data without requiring the auxiliary information.

7. The information processing apparatus according to claim 4, wherein: The input data includes at least one of the following: item name, service name, item category and service category, The second keyword includes the name of the item and / or the name of the service, and Each of the extracted pieces of data includes an item name and / or a service name.

8. The information processing device according to any one of claims 4 to 7, wherein: The user feedback information includes at least one of the following: Feedback information of the first user who inputs the input data on the response data; Feedback information of the first user on the auxiliary information; Feedback information of one or more second users different from the first user on the corresponding response data; as well as Feedback information of the one or more second users on the corresponding auxiliary information.

9. An information processing method comprising: determining that auxiliary information for the input data is required if 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; as well as If it is determined that the auxiliary information is needed, multiple pieces of data corresponding to the first keyword are extracted from the first subset, and one or more pieces of data are selected from the extracted multiple pieces of data as the auxiliary information based on the input data for generating response data. 10 . A computer-readable storage medium storing instructions, which, when executed by a computer, cause the computer to execute the information processing method according to claim 9 .

Images