Information processing method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an information processing method and device, electronic equipment and a storage medium. The method comprises the following steps: inputting question information and associated information of the question information into a description model to obtain description information of the question information and request parameters of the question information; determining a response result corresponding to the request parameter through a service corresponding to the description information; and inputting the response result and the question information into an answer model to obtain reply information of the question information. According to the technical scheme, the service needing to be called for replying the question information is determined through the description information output by the description model, the response result determined through the service serves as reference for replying the question information through the answer model, and the accuracy of determining the reply information corresponding to the question information can be improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to computer technology, and in particular, to an information processing method and device, electronic equipment and storage medium. BACKGROUND

[0002] A large language model (LLM) can be understood as an artificial intelligence model that uses machine learning technology to understand and generate human language. Through the calling of a plug-in, the large language model can generate a corresponding reply to the input of the large language model by using the services carried by the plug-in, such as obtaining professional knowledge in a certain field through the services provided by the plug-in.

[0003] At present, the large language model supporting the plug-in function may have problems when calling the plug-in. For example, in the scenario where the large language model supports multiple plug-ins, the large language model cannot accurately determine which plug-in should be called for the input of the large language model, resulting in inaccurate replies to the input. SUMMARY

[0004] The present disclosure provides an information processing method and device, electronic equipment and storage medium, which can improve the accuracy of determining the reply information corresponding to the problem information.

[0005] In a first aspect, the embodiments of the present disclosure provide an information processing method, comprising:

[0006] inputting problem information and associated information of the problem information into a description model to obtain description information of the problem information and request parameters of the problem information;

[0007] determining a response result corresponding to the request parameters through a service corresponding to the description information;

[0008] inputting the response result and the problem information into an answering model to obtain reply information of the problem information.

[0009] In a second aspect, the embodiments of the present disclosure further provide an information processing device, comprising:

[0010] an input module configured to input problem information and associated information of the problem information into a description model to obtain description information of the problem information and request parameters of the problem information;

[0011] a determination module configured to determine a response result corresponding to the request parameters through a service corresponding to the description information;

[0012] a reply module configured to input the response result and the problem information into an answering model to obtain reply information of the problem information.

[0013] In a third aspect, the embodiments of the present disclosure further provide an electronic device, the electronic device comprising:

[0014] one or more processing devices;

[0015] a storage device configured to store one or more programs,

[0016] When the one or more programs are executed by the one or more processing devices, the one or more processing devices implement the information processing method provided by the embodiments of the present disclosure.

[0017] In a fourth aspect, the embodiments of the present disclosure further provide a storage medium containing computer executable instructions for executing the information processing method provided by the embodiments of the present disclosure when executed by a computer processor.

[0018] The technical solutions of the embodiments of the present disclosure determine the description information of the problem information and the request parameters of the problem information through the description model, determine the service to be called to reply to the problem information through the description information, determine the response result corresponding to the request parameters through the service to be called, and input the response result and the problem information into the answering model to obtain the reply information of the problem information. The service to be called to reply to the problem information is determined through the description information output by the description model, and the response result determined through the service is taken as a reference for the answering model to reply to the problem information, which can improve the accuracy of determining the reply information corresponding to the problem information. BRIEF DESCRIPTION OF DRAWINGS

[0019] The above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the original and elements are not necessarily drawn according to the scale.

[0020] Figure 1 is a flowchart of an information processing method provided by an embodiment of the present disclosure;

[0021] Figure 2 is a flowchart of another information processing method provided by an embodiment of the present disclosure;

[0022] Figure 3 is a flowchart of still another information processing method provided by an embodiment of the present disclosure;

[0023] Figure 4 is a flowchart of still another information processing method provided by an embodiment of the present disclosure;

[0024] Figure 5 is a structural schematic diagram of an information processing device provided by an embodiment of the present disclosure;

[0025] Figure 6 is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein, but rather, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes, and are not intended to limit the scope of protection of the present disclosure.

[0027] It should be understood that each step described in the method embodiments of the present disclosure can be performed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0028] The term "comprising" and variations thereof as used herein are open-ended, that is, "comprising but not limited to." The term "based on" is "based, at least in part, on." The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments." Related definitions are given below in the description of the application.

[0029] It should be noted that the modification of "one" or "multiple" mentioned in the present disclosure is illustrative rather than limiting, and those skilled in the art should understand that, unless otherwise explicitly indicated in the context, it should be understood as "one or more".

[0030] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0031] Figure 1 is a flowchart of an information processing method provided by an embodiment of the present disclosure, and the embodiments of the present disclosure are applicable to the case of determining the reply information corresponding to the question information. The method can be executed by an information processing device, which can be implemented in the form of software and / or hardware, and integrated in an electronic device. Optionally, the electronic device can be a mobile terminal, a PC terminal, etc.

[0032] As shown in Figure 1 , the method comprises:

[0033] S110, input the question information and the associated information of the question information into the description model to obtain the description information of the question information and the request parameter of the question information.

[0034] The application scenario of the embodiments of the present disclosure can be considered as a scenario of determining corresponding reply information for input question information in a question and answer platform. The question and answer platform can be understood as a platform of determining corresponding answers for input questions through artificial intelligence technology, and the field of problems that can be solved by the question and answer platform is not limited.

[0035] The question information can be information of a question obtained on the question and answer platform, such as a question input by a user on the question and answer platform. The reply information can be information of a reply obtained on the question and answer platform for the question information, such as a reply for a question input by a user on the question and answer platform.

[0036] The association information can be information associated with the question information, such as professional knowledge of a field to which a question indicated by the question information belongs, historical dialogue associated with the question information in the question and answer platform, and the like. The historical dialogue can be a dialogue formed by a question and a reply in the question and answer platform.

[0037] The description model can be a model of determining description information of the question information and a request parameter of the question information. The description model can be a large language model, which is not limited here. The description information can be information of a description for the question information, and the description information can indicate a service to be called by the reply question information. The request parameter can be a parameter required by the reply question information, which can be understood as a parameter required when calling a service, such as a keyword extracted from the question information.

[0038] The service can be a service that can be provided in the question and answer platform, which can include but is not limited to retrieval of a question indicated by the question information, acquisition of materials related to the question information, and the like. The type of the service that can be provided in the question and answer platform is not limited, and any service can be carried in a corresponding plug-in, and the question and answer platform can call the corresponding service through an interface of the plug-in.

[0039] In this step, the question information and the association information of the question information are input into the description model, and the description model can output the description information of the question information and the request parameter of the question information.

[0040] In this step, the form of the description information and the request parameter output by the description model is not limited, such as a form of a keyword (also referred to as a key) and a value (also referred to as a value) corresponding to the keyword.

[0041] Exemplarily, for the description information, the key can be a classification type, and the value can be a classification value corresponding to the classification type. The classification type can be a type for classifying the question information, and different classification types can indicate different description information, i.e., different classification types indicate different services to be invoked by the reply question information. The classification value can be a value corresponding to the classification type, and any classification value has a classification type corresponding thereto uniquely, such as classification value 1 corresponding to type 1, and classification value 2 corresponding to type 2. The description information can be {“classification type”: 1} or {“classification type”: 2}.

[0042] Exemplarily, for the request parameter, the key can be the name of the request parameter, and the value can be the value corresponding to the name of the request parameter.

[0043] Optionally, in addition to representing the description information in the form of key and value, the identifier of the service to be invoked by the reply question information determined by the description model can also be directly taken as the description information.

[0044] S120, determining a response result corresponding to the request parameter through the service corresponding to the description information.

[0045] In this step, the service to be invoked by the reply question information can be determined based on the description information, the determined service is invoked, the request parameter is input into the corresponding service, and the response result of the corresponding request parameter responded by the service is obtained.

[0046] The service to be invoked by the reply question information can be one or more services, which are not limited here. For any service to be invoked by the reply question information, the request parameter required by the service to determine the response result can be determined as the request parameter required to be input into the service. For any service to be invoked by the reply question information, the determined response result can be the result of responding to the request parameter input into the service.

[0047] Exemplarily, in the case where the service is a search for the problem indicated by the question information, the request parameter input into the service can be a keyword extracted from the question information, and the response result determined by the service can be a result obtained based on the keyword search.

[0048] S130, inputting the response result and the question information into an answer model to obtain reply information of the question information.

[0049] The answer model can be a model for determining the reply information corresponding to the question information, and the answer model can be a large language model, which is not limited here.

[0050] In this step, the response result and the question information are input to the answering model, and the answering model can output the reply information of the question information.

[0051] In this step, the response result and the question information are input to the answering model, and the answering model can output the reply information of the question information.

[0052] The technical solution of the embodiment of the present disclosure determines the description information of the question information and the request parameter of the question information through the description model, determines the service to be called to reply to the question information through the description information, determines the response result corresponding to the request parameter through the service to be called, and inputs the response result and the question information to the answering model to obtain the reply information of the question information. The service to be called to reply to the question information is determined through the description information output by the description model, and the response result determined through the service is used as a reference for the answering model to reply to the question information, which can improve the accuracy of determining the reply information corresponding to the question information.

[0053] In one embodiment, the question and answer platform of the embodiment of the present disclosure can be an ancient book platform. The ancient book platform can be a platform that provides ancient book browsing and realizes question and answer related to ancient books. For example, the question information is obtained through the ancient book platform, the ancient book platform determines the reply information corresponding to the question information through the information processing method provided by the present disclosure, and visual display of the reply information is performed.

[0054] The following is described taking the ancient book platform as an example of the question and answer platform of the embodiment of the present disclosure:

[0055] In one embodiment, the question information includes information of a question obtained on the ancient book platform, and the service includes a service provided by the ancient book platform.

[0056] The question information can include information of a question obtained on the ancient book platform, such as information of a question related to a browsed ancient book obtained in the process of browsing the ancient book.

[0057] The service provided by the ancient book platform is not limited, such as but not limited to: keyword search, semantic search, dictionary search, translation search, full-text search, and the like related to ancient books. The keyword search is a search based on a keyword. The semantic search is a search based on semantics. The dictionary search is a search based on a dictionary, which can be a dictionary related to a browsed ancient book. The translation search can be a search based on a translation of an ancient book. The full-text search can be a search based on the full text of an ancient book.

[0058] In an embodiment, the association information comprises a chapter of the ancient book to which the question information is associated and a dialogue information to which the question information is associated.

[0059] The chapter of the ancient book to which the question information is associated can be understood as a context of the chapter of the ancient book browsed in the ancient book platform. The dialogue information to which the question information is associated can be information of a dialogue formed based on a question and a reply generated in the history of the browsed ancient book in the ancient book platform.

[0060] In an embodiment, the description information indicates one of the following:

[0061] a service processing the question information;

[0062] a service processing the question information and arrangement information between services.

[0063] In the case where the description information indicates the service processing the question information, the service processing the question information can be one, i.e., the description information indicates which service should be called to process the question information.

[0064] In the case where the description information indicates the service processing the question information and the arrangement information between services, the service processing the question information can be multiple. The arrangement information can be information of arrangement of multiple services called to reply the question information, and the arrangement can be understood as arrangement of order of calling of the multiple services. Exemplarily, the arrangement information can indicate a calling order of the multiple services called by the ancient book platform, such as whether the multiple services are called in parallel or in series.

[0065] Exemplarily, the description information can be {“classification type”: 2}, indicating that the classification type adopted is type 2 corresponding to classification value 2. Type 2 can indicate that the multiple services called to process the question information include keyword retrieval and semantic retrieval, and the multiple services are called in parallel.

[0066] In an embodiment, the request parameter comprises a keyword extracted from the question information or comprises a keyword extracted from the question information and the dialogue information.

[0067] The request parameter comprises a keyword extracted from the question information obtained from the ancient book platform or comprises a keyword extracted from the question information and the dialogue information associated with the question information, and the keyword is not limited.

[0068] Exemplarily, the request parameter can be {“keyword field”: keyword}, and the keyword field is the name key of the request parameter, and the keyword is the value value corresponding to the name of the request parameter.

[0069] Optionally, the request parameter can further include an ancient book name, an author name of the ancient book, or the like extracted from the question information or extracted from the question information and the dialogue information.

[0070] On the basis of the above-mentioned embodiments, variant embodiments of the above-mentioned embodiments are proposed, and it should be noted that, in order to make the description brief, only differences from the above-mentioned embodiments are described in the variant embodiments.

[0071] Figure 2 is a flowchart of another information processing method provided by the embodiment of the disclosure, and the embodiment of the disclosure is a further refinement of determining a response result corresponding to the request parameter for a service corresponding to the description information on the basis of the above-mentioned embodiments.

[0072] As shown in Figure 2 , the method comprises:

[0073] S210, input the question information and the associated information of the question information to the description model to obtain the description information of the question information and the request parameter of the question information.

[0074] In this step, the ancient book platform can input the question information and the associated information to the description model, and obtain the description information and the request parameter returned by the description model.

[0075] S220, according to the order corresponding to the arrangement information indicated by the description information, call the service corresponding to the description information.

[0076] In this step, the ancient book platform can determine the service corresponding to the processing of the question information and the arrangement information between the corresponding services indicated by the description information, and according to the scheduling order of the services indicated by the arrangement information to be called, such as parallel calling or serial calling of multiple services, the calling is realized through the calling interface of the corresponding service.

[0077] S230, obtain the response result corresponding to the request parameter in the service response.

[0078] In this step, the ancient book platform can transmit the request parameter required by the service response to the service when calling any service, and obtain the response result corresponding to the request parameter in the service response. The ancient book platform can integrate the response results of the called multiple services as the final response result input to the answer model.

[0079] S240, input the response result and the question information to the answer model to obtain the reply information of the question information.

[0080] The technical solution of this disclosure, through a description model—that is, a single large language model—determines the service corresponding to the problem information, the orchestration information between the corresponding services, and the request parameters required to call the service, thereby improving the accuracy and stability of service calls and parameter extraction. Simultaneously, because service calls and parameter extraction are implemented by a separate description model, response time can be reduced.

[0081] In one embodiment, after determining the response result corresponding to the request parameters through the service corresponding to the description information, the method further includes:

[0082] The response results and the question information are input into the association model to obtain the sorted response results associated with the question information.

[0083] The association model can be a model that ranks the response results of the association of problem information. The association model can be a large language model, which is not limited here.

[0084] In this step, after obtaining the response results of multiple services called, the ancient book platform can input the question information and the obtained response results into the association model; the association model can sort, score, filter and other processes on the multiple response results, and return the processed response results as the final response results to the ancient book platform; the ancient book platform inputs the final response results and the question information into the answer model to obtain the reply information for the question information.

[0085] The methods for sorting, scoring, and filtering multiple response results are not limited. For example, multiple response results can be scored according to their relevance to the question information, with higher scores indicating greater relevance; the scores can then be sorted from highest to lowest; and scores below a set threshold can be filtered out. The score threshold can be determined based on actual needs.

[0086] Figure 3 This is a flowchart illustrating another information processing method provided in this disclosure. This disclosure is an exemplary description based on the above embodiments, using an ancient book platform.

[0087] like Figure 3 As shown, it includes the following steps:

[0088] Input the question information from the ancient book platform, the context of the ancient book chapter being viewed (i.e. the ancient book chapters included in the associated information of the question information), and the dialogue information associated with the question information into the description model to obtain the description information of the question information and the request parameters of the question information.

[0089] The response result corresponding to the request parameters is determined by the services described in the services provided by the ancient book platform; the services provided by the ancient book platform may include, but are not limited to: full-text search, semantic search, dictionary search, and full-text retrieval.

[0090] The response result and question information are input into the answer model to obtain the response information to the question information, as well as links to relevant materials. The links to relevant materials can be understood as paths to obtain relevant materials, which may include the materials mentioned in the response information.

[0091] Figure 4 This is a flowchart illustrating yet another information processing method provided in this disclosure. Figure 4 The process shown is... Figure 3 Further details of the process shown.

[0092] like Figure 4 As shown, it includes the following steps:

[0093] S1. The ancient book platform inputs the question information, the ancient book chapters associated with the question information, and the dialogue information associated with the question information into the description model.

[0094] S2. The description model determines the description information and request parameters of the problem information, and feeds back the determined content to the ancient book platform.

[0095] In this step, the description model can classify the problem information and determine the corresponding descriptive information, namely the classification type key and the corresponding classification value. The classification value indicates the corresponding classification type, and the classification type indicates the service that handles the problem information and the orchestration information between those services. The description model can also determine the request parameters corresponding to the problem information, namely the request parameter name key and the corresponding request parameter value.

[0096] Description information and request parameters can be represented together using a lightweight data exchange format, such as {"Category Type": Category value, "Keyword Field": Keyword, "Ancient Book Name Field": Ancient Book Name, "Author Field": Author's Name}. Here, the "Category Type" field corresponds to an integer type, the "Keyword Field" field corresponds to a string type, the "Ancient Book Name Field" field corresponds to a string type, and the "Author Field" field corresponds to a string type.

[0097] For example, if the question information indicates a request to obtain content similar to the input classical Chinese text fragment, or a request to obtain the source of the input classical Chinese text fragment, then the corresponding classification value can be determined, and keywords related to the input classical Chinese text fragment can be extracted as the keyword field.

[0098] In this step, the description model can also combine pre-defined prompts to determine the description information corresponding to the question information, which is not limited here.

[0099] Optionally, the description model has learning capabilities and can be trained based on known problem information, the corresponding description information, and request parameters to improve the accuracy of the description model's output.

[0100] In this embodiment of the disclosure, the description model determines the description information and request parameters corresponding to the problem information. This can be understood as a pre-judgment similar to that of a plugin call in a large language model, and the plugin call is implemented based on the result of the pre-judgment.

[0101] S3. The ancient book platform calls the service corresponding to the description information from the services provided by the ancient book platform, according to the order of the arrangement information indicated by the description information, and obtains the response result of the corresponding request parameters of the service response.

[0102] S4. The ancient book platform inputs the obtained response results and problem information into the association model.

[0103] S5, the association model sorts, scores, filters and processes multiple response results, and returns the processed response results as the final response results to the ancient book platform.

[0104] S6. The ancient book platform inputs the final response results and question information into the answer model.

[0105] S7. The response model uses the final response result as supplementary context for processing the question information, generates an enhanced response, i.e., a reply to the question information, and feeds back the determined reply information to the ancient book platform.

[0106] In this embodiment of the disclosure, the plugin function (i.e. service invocation) of the large language model is realized by jointly implementing the description model, the association model and the response model. In the ancient book platform, the plugin function implemented by multiple models can realize functions such as semantic retrieval and ancient text translation.

[0107] In this embodiment of the disclosure, by determining the description information of the problem information through a description model, the problem of selecting and orchestrating plugin calls in a large language model can be solved, and a custom workflow for orchestrating calls to multiple plugin service interfaces can be defined. Since the selection and orchestration of plugin calls uses a separate description model, it has the following advantages:

[0108] 1. Easy to iterate and maintain: Due to the single function of the description model, it is easy to perform iterative debugging.

[0109] 2. Improve understandability and stability: Given the current imperfections in the calling capabilities of some large model plugins, the description model, i.e., the large language model, determines the selection and orchestration of plugin calls. Based on the advantages of the large language model itself, the judgment results of the description model are more accurate and stable.

[0110] 3. Optimize call latency: Currently, the latency of calling the plugin using the large model is 6-9 seconds, while the latency of calling the plugin using the description model is only 1-2 seconds, reducing waiting time.

[0111] In this embodiment of the disclosure, the request parameters corresponding to the problem information are determined by describing the model, which can solve the problem of constructing the request parameters for plugin calls and supports the construction of various types of request parameters, including numerical values, arrays, and composite types.

[0112] In this embodiment of the disclosure, the final response result is input into the answer model to enhance the answer, which can improve the accuracy of the generated response information.

[0113] The technical solution of this disclosure achieves good results in the intelligent question-answering scenario of an ancient book platform. The intelligent question-answering utilizes the platform's self-built dictionary function to aid in a deeper understanding of classical Chinese texts, and uses the platform's search function to facilitate further reading. It resolves issues such as parameter extraction errors, plugin judgment errors, and plugin arrangement errors that exist in multi-plugin scenarios when the large language model has built-in plugin functionality. It can accurately determine the services to be called for processing problem information, the arrangement methods between services, and correctly construct request parameters. When determining the response information, it incorporates the response information returned by the ancient book backend service, effectively connecting the large model with the content ecosystem of ancient books.

[0114] Figure 5 This is a schematic diagram of the structure of an information processing device provided in an embodiment of this disclosure, as shown below. Figure 5 As shown, the device includes: an input module 510, a determination module 520, and a response module 530.

[0115] The input module 510 is used to input the problem information and the associated information of the problem information into the description model to obtain the description information of the problem information and the request parameters of the problem information.

[0116] The determining module 520 is used to determine the response result corresponding to the request parameters based on the service corresponding to the description information;

[0117] The response module 530 is used to input the response result and the question information into the answer model to obtain the response information of the question information.

[0118] The technical solution provided in this disclosure involves an input module that inputs question information and its associated information into a description model to obtain description information and request parameters for the question information. A determination module then uses the service corresponding to the description information to determine the response result corresponding to the request parameters. Finally, a response module inputs the response result and the question information into a response model to obtain response information for the question information. By determining the service to be invoked in response to the question information using the description information output by the description model, and using the response result determined by the service as a reference for the response model, the accuracy of determining the response information corresponding to the question information can be improved.

[0119] In one embodiment, the description information indicates one of the following:

[0120] Services for processing the aforementioned problem information;

[0121] The services that process the aforementioned problem information and the orchestration information between these services.

[0122] In one embodiment, the determining module 520 is specifically used for:

[0123] The services corresponding to the description information are invoked in the order indicated by the arrangement information.

[0124] Obtain the response result corresponding to the request parameters of the service response.

[0125] In one embodiment, the problem information includes information about problems obtained from the ancient book platform, and the service includes services provided by the ancient book platform.

[0126] In one embodiment, the associated information includes the ancient book chapters associated with the question information within the ancient book platform and the dialogue information associated with the question information.

[0127] In one embodiment, the request parameters include keywords extracted from the question information or keywords extracted from both the question information and the dialogue information.

[0128] In one embodiment, the device further includes a sorting module for:

[0129] After determining the response result corresponding to the request parameters through the service corresponding to the description information, the response result and the problem information are input into the association model to obtain the sorted response result associated with the problem information.

[0130] The information processing apparatus provided in this disclosure can execute the information processing method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects for executing the method.

[0131] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0132] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Refer to the following... Figure 6 It illustrates an electronic device suitable for implementing embodiments of the present disclosure (e.g., Figure 6 A structural diagram of the terminal device or server in the 500.

[0133] An electronic device provided in this disclosure includes:

[0134] One or more processing devices;

[0135] Storage device for storing one or more programs.

[0136] When the one or more programs are executed by the one or more processing devices, the one or more processing devices implement the information processing method provided in any embodiment of this disclosure.

[0137] The terminal devices in this disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0138] like Figure 6 As shown, electronic device 500 may include a processing unit (e.g., central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. An edit / output (I / O) interface 505 is also connected to bus 504.

[0139] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0140] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.

[0141] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0142] The electronic device provided in this embodiment and the information processing method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0143] This disclosure provides a computer storage medium storing a computer program that, when executed by a processor, implements the information processing method provided in the above embodiments.

[0144] It should be noted that the computer-readable medium described above in this disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination thereof.

[0145] The computer storage medium may be a storage medium for computer-executable instructions, which, when executed by a computer processor, are used to perform the methods provided in this disclosure.

[0146] Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0147] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0148] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0149] The aforementioned computer-readable medium carries one or more programs. When the aforementioned one or more programs are executed by the electronic device, the electronic device causes the electronic device to: input problem information and associated information of the problem information into a description model to obtain description information of the problem information and request parameters of the problem information; determine the response result corresponding to the request parameters through the service corresponding to the description information; and input the response result and the problem information into a response model to obtain reply information of the problem information.

[0150] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0151] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0152] The modules or units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules or units do not necessarily limit the specific unit itself.

[0153] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0154] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0155] According to one or more embodiments of this disclosure, Example 1 provides an information processing method, including:

[0156] Input the problem information and its associated information into the description model to obtain the description information and the request parameters of the problem information;

[0157] The response result corresponding to the request parameters is determined based on the service corresponding to the description information;

[0158] The response result and the question information are input into the answer model to obtain the response information for the question information.

[0159] According to one or more embodiments of this disclosure, Example 2 describes the method described in Example 1.

[0160] The description information indicates one of the following:

[0161] Services for processing the aforementioned problem information;

[0162] The services that process the aforementioned problem information and the orchestration information between these services.

[0163] According to one or more embodiments of this disclosure, Example 3 describes the method described in Example 2.

[0164] Determining the response result corresponding to the request parameters through the service corresponding to the description information includes:

[0165] The services corresponding to the description information are invoked in the order indicated by the arrangement information.

[0166] Obtain the response result corresponding to the request parameters of the service response.

[0167] According to one or more embodiments of this disclosure, Example 4 describes the method according to any one of Examples 1-3.

[0168] The problem information includes information about problems obtained from the ancient book platform, and the service includes the services provided by the ancient book platform.

[0169] According to one or more embodiments of this disclosure, Example 5 describes the method described in Example 1.

[0170] The associated information includes the ancient book chapters associated with the question information within the ancient book platform and the dialogue information associated with the question information.

[0171] According to one or more embodiments of this disclosure, Example 6 describes the method described in Example 5.

[0172] The request parameters include keywords extracted from the question information or keywords extracted from both the question information and the dialogue information.

[0173] According to one or more embodiments of this disclosure, Example 7 describes the method described in Example 1.

[0174] After determining the response result corresponding to the request parameters through the service corresponding to the description information, the method further includes:

[0175] The response results and the question information are input into the association model to obtain the sorted response results associated with the question information.

[0176] According to one or more embodiments of this disclosure, Example 8 provides an information processing apparatus, including:

[0177] The input module is used to input the problem information and the associated information of the problem information into the description model to obtain the description information of the problem information and the request parameters of the problem information.

[0178] The determining module is used to determine the response result corresponding to the request parameters based on the service corresponding to the description information;

[0179] The response module is used to input the response result and the question information into the answer model to obtain the response information for the question information.

[0180] According to one or more embodiments of this disclosure, Example 9 provides an electronic device, the electronic device comprising:

[0181] One or more processing devices;

[0182] Storage device for storing one or more programs.

[0183] When the one or more programs are executed by the one or more processing devices, the one or more processing devices implement the information processing method as described in any of Examples 1-7.

[0184] According to one or more embodiments of the present disclosure, Example 10 provides a storage medium containing computer-executable instructions that, when executed by a computer processor, are used to perform an information processing method as described in any of Examples 1-7.

[0185] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0186] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0187] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. An information processing method, characterized in that, include: Input the problem information and its associated information into the description model to obtain the description information and the request parameters of the problem information; The response result corresponding to the request parameters is determined based on the service corresponding to the description information; The response result and the question information are input into the answer model to obtain the response information for the question information.

2. The method according to claim 1, characterized in that, The description information indicates one of the following: Services for processing the aforementioned problem information; The services that process the aforementioned problem information and the orchestration information between these services.

3. The method according to claim 2, characterized in that, Determining the response result corresponding to the request parameters through the service corresponding to the description information includes: The services corresponding to the description information are invoked in the order indicated by the arrangement information. Obtain the response result corresponding to the request parameters of the service response.

4. The method according to any one of claims 1-3, characterized in that, The problem information includes information about problems obtained from the ancient book platform, and the service includes the services provided by the ancient book platform.

5. The method according to claim 1, characterized in that, The associated information includes the ancient book chapters associated with the question information within the ancient book platform and the dialogue information associated with the question information.

6. The method according to claim 5, characterized in that, The request parameters include keywords extracted from the question information or keywords extracted from both the question information and the dialogue information.

7. The method according to claim 1, characterized in that, After determining the response result corresponding to the request parameters through the service corresponding to the description information, the method further includes: The response results and the question information are input into the association model to obtain the sorted response results associated with the question information.

8. An information processing device, characterized in that, include: The input module is used to input the problem information and the associated information of the problem information into the description model to obtain the description information of the problem information and the request parameters of the problem information. The determining module is used to determine the response result corresponding to the request parameters based on the service corresponding to the description information; The response module is used to input the response result and the question information into the answer model to obtain the response information for the question information.

9. An electronic device, characterized in that, The electronic device includes: One or more processing devices; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processing devices, the one or more processing devices implement the information processing method as described in any one of claims 1-7.

10. A storage medium comprising computer-executable instructions, which, when executed by a computer processor, are used to perform the information processing method as described in any one of claims 1-7.

Images