Information processing method and device, equipment and medium

Abstract

The embodiment of the invention provides an information processing method and device, equipment and a medium. According to the method, first service information related to input of a user is firstly determined, and the first service information is associated with at least one candidate service field. Next, a target business domain corresponding to the input is determined based on the first business information and the at least one candidate business domain. Second business information associated with the target business domain is then determined based on the input. By means of the method, the information processing efficiency and accuracy can be effectively improved.

Description

Technical Field

[0001] Exemplary embodiments of the present disclosure generally relate to computer technology, and more particularly, to information processing methods, devices, apparatuses, and computer-readable storage media. Background Art

[0002] Nowadays, with the development of economic globalization and the Internet, people need to use more and more information on the Internet in their lives. However, when searching for content on the Internet, it is usually difficult for users to directly obtain the required information due to the massive amount of data. Therefore, how to identify the information or objects required by users from the massive data has become a concern. Summary of the invention

[0003] In a first aspect of the present disclosure, an information processing method is provided. In the method, first business information related to a user's input is determined, the first business information is associated with at least one candidate business domain; a target business domain corresponding to the input is determined based on the first business information and the at least one candidate business domain; and second business information associated with the target business domain is determined based on the input.

[0004] In a second aspect of the present disclosure, an information processing device is provided. The device includes: a first determination module configured to determine first business information related to a user's input, the first business information being associated with at least one candidate business domain; a second determination module configured to determine a target business domain corresponding to the input based on the first business information and the at least one candidate business domain; and a third determination module configured to determine second business information associated with the target business domain based on the input.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the device executes the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] It should be understood that the contents described in this content section are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent in the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0009] Figure 1 A schematic diagram showing a process performed by an information processing device according to some embodiments of the present disclosure;

[0010] Figure 2 A schematic diagram of an information library according to some embodiments of the present disclosure is shown;

[0011] Figure 3A and Figure 3B A schematic diagram showing an example process of an information processing method according to some embodiments of the present disclosure;

[0012] Figure 4 A schematic diagram showing a general question-answer information processing process according to some embodiments of the present disclosure;

[0013] Figure 5 A schematic diagram showing an information processing process for a specified business domain according to some embodiments of the present disclosure;

[0014] Figure 6 A schematic diagram showing an information processing process of a specified document according to some embodiments of the present disclosure;

[0015] Figure 7 A flowchart of an information processing method according to some embodiments of the present disclosure is shown;

[0016] Figure 8 A schematic structural block diagram of an information processing device according to some embodiments of the present disclosure is shown; and

[0017] Fig. 9 A block diagram of a device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of 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.

[0019] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". The following may also include other explicit and implicit definitions. As used herein, the term "model" can represent the association relationship between various data. For example, the above-mentioned association relationship can be obtained based on a variety of technical solutions currently known and / or to be developed in the future.

[0020] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0021] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0022] For example, in response to receiving the user's input, a prompt message is sent to the user to clearly prompt the user that the operation performed in response to the user's input will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to the electronic device, application, server, storage medium or other software or hardware that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0023] As an optional but non-limiting embodiment, in response to receiving the user's input, the prompt information is sent to the user in a manner such as a pop-up window, and the pop-up window may present the prompt information in text form. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0024] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation to the embodiments of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the embodiments of the present disclosure.

[0025] The term "in response to" as used herein refers to a state in which a corresponding event occurs or a condition is satisfied. It will be understood that the timing of executing a subsequent action executed in response to the event or condition is not necessarily strongly related to the time when the event occurs or the condition is satisfied. For example, in some cases, the subsequent action may be executed immediately when the event occurs or the condition is satisfied; while in other cases, the subsequent action may be executed some time after the event occurs or the condition is satisfied.

[0026] The term "recall" (also called "knowledge recall") used herein refers to the process of extracting relevant information or answers from an information base. This process is often used in information processing methods, especially in the fields of natural language processing, question-answering systems, search engines, and intelligent assistants. In this process, the device quickly finds relevant and valid information by querying or searching the stored knowledge base and returns it to the user or other system.

[0027] Natural language processing plays an important role in current information processing methods. In the research on natural language processing, intelligent question and answer is a common application scenario and one of the common means of human-computer interaction. For example, intelligent customer service robots, intelligent voice assistants, etc. In the intelligent question and answer scenario, user questions can be described in natural language. The reply content to the user's question can be generated based on natural language. In addition, when the user issues a task in natural language, the information processing device in the intelligent question and answer scenario can also perform the task issued by the user.

[0028] Conventional platforms that provide data products usually have a variety of products. The usage help documents of these products are usually complicated. Therefore, the workload of manual customer service is large. In this case, customer service personnel need to learn more about related products and technologies in order to meet customer needs.

[0029] Existing automatic reply systems usually have limitations in keyword matching and lack contextual understanding and semantic analysis. In addition, existing automatic reply systems are often unable to distinguish some highly similar keywords or information fragments, which will lead to low accuracy and poor usability of information processing results, or even completely wrong. For example, a data platform may provide a variety of data applications and product ecosystems, including data insight products, data analysis products, and experimental evaluation products. These products provide users with a variety of functions. However, in the process of knowledge recall and document recognition, conventional information processing methods are usually unable to make effective judgments for similar information in different products, resulting in inaccurate information processing results.

[0030] In order to at least partially solve the above problems and other potential problems, the present disclosure proposes a solution for information processing. The solution of the present disclosure determines the target business field corresponding to the user input based on the business information related to the user input, and determines the business information corresponding to the input associated with the target business field, thereby improving the efficiency of information processing and the accuracy of processing results.

[0031] For the convenience of explanation, the following Figure 1 The information processing process of is discussed as an example. Specifically, Figure 1A schematic diagram of an information processing process 100 performed by an information processing device 101 according to some embodiments of the present disclosure is shown. The information processing device 101 may be any type of mobile terminal, fixed terminal or portable terminal, including any device that can use Internet services, such as a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a PDA, etc. In addition, the information processing device 101 may also be implemented as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, and content distribution networks.

[0032] like Figure 1 As shown, the information processing device 101 may first obtain a user input 110. In some embodiments, the user input 110 may include a question described in a natural language, for example, to inquire about certain functions or features of a product.

[0033] As mentioned above, since the document structures of various products may be highly similar, conventional information processing methods may have a low accuracy rate in finding the product functions or features that customers need. Specifically, since the documents of various products may include information related to quick start, function introduction, frequently asked questions, and learning courses, and the organization of these documents (e.g., content) is very similar, if the user requests information related to quick start of a certain product, conventional information processing methods may provide information related to quick start of another product. This may cause the response provided to the user to include erroneous information, which seriously reduces the user's experience.

[0034] Different from this, in the embodiment of the present disclosure, the information processing device 101 first determines the first business information 120 related to the user's input 110, and the first business information 120 is information associated with one or more candidate business fields. The first business information 120 can be stored in the information processing device 101. As an alternative, the first business information 120 is information that the information processing device 101 can access, and does not need to be stored in other information storage devices, for example, it can be stored in another device. In addition, the one or more candidate business fields can be part or all of all business fields that the information processing device 101 can access.

[0035] In some implementations, the information processing device 101 may determine the first business information 120 related to the input 110 in the information library. In this case, the information library includes candidate business information associated with multiple candidate business fields. For example, the information library may include a large amount of candidate business information, and these candidate business information are respectively associated with multiple candidate business fields. In other words, for multiple candidate business fields, the information library includes candidate business information in each candidate business field. The information processing device 101 may access the information library and determine the first business information 120 related to the input 110 based on the input 110. In some implementations, the information processing device 101 may search the information library based on the input 110 to determine the first business information 120.

[0036] Figure 2 A schematic diagram of an information base 200 according to some embodiments of the present disclosure is shown. The information base 200 may include information of one or more business fields, such as documents of products belonging to different business fields, such as product A, product B, or product C. The documents of each product may include a lot of business information, such as information related to quick start, function introduction, common problems, and learning courses.

[0037] Continue to return Figure 1 , the information processing device 101 determines the target business domain corresponding to the input 110 based on the first business information 120 and at least one candidate business domain. Specifically, the information processing device 101 can determine the target business domain in at least one candidate business domain based on the first business information 120. The target business domain can be considered as the domain that the user expects to be involved in this information processing process. Next, the information processing device 101 determines the second business information 130 associated with the target business domain based on the input 110.

[0038] In addition, the information processing device 101 may determine a response to the input 110 based on the second business information 130. For example, the information processing device 101 may generate a response based on the second business information 130 using natural language processing technology. In addition, the response may be presented to the user in the form of natural language, for example. In some cases, the response may also be an answer to a question in the input 110.

[0039] In the process of determining the target business domain, the information processing device 101 can determine the degree of relevance of each candidate business domain in at least one candidate business domain with the input 110 based on the first business information 120. Additionally, the information processing device 101 can determine the target business domain from at least one candidate business domain based on the degree of relevance. For example, if the first business information 120 determined by the information processing device 101 based on the input 110 includes business information associated with multiple candidate business domains, the information processing device 101 can determine the number of business information of each of the multiple candidate business domains, and can determine the candidate business domain whose number of business information exceeds a threshold number (or whose number of business information is the largest) as the target business domain. It should be understood that the above is merely an example for determining the target business domain, which is exemplary and not restrictive, and the scope of the present disclosure is not limited in this respect.

[0040] As an alternative, the information processing device 101 may use a pre-trained domain determination model to determine the target business domain. Specifically, the information processing device 101 may determine the target business domain by applying the first business information 120 and at least one candidate business domain to the domain determination model. The domain determination model may be obtained by training with reference business information and multiple reference candidate business domains as inputs and with reference target business domains as outputs. In addition or alternatively, the domain determination model may also be trained in other ways to be used, for example, to determine the target business domain corresponding to the input 110 based on the user's input 110.

[0041] In some embodiments, input 110 may include business domain information. Specifically, the business domain information may indicate a specific business domain. For example, a user may select a specific business domain. Alternatively, the information processing device 101 may ask a question to the user or provide the user with an option to obtain business domain information. In this case, the specific business domain may be considered to be a domain that the user expects to be involved in this information processing process. The information processing device 101 may determine business information associated with the business domain indicated by the business domain information from an information library based on input 110. Additionally, the information library includes candidate business information associated with multiple candidate business domains.

[0042] Additionally or alternatively, in some embodiments, the input 110 may include a question raised by a user (hereinafter also referred to as a first question), and the information processing device 101 may further update or optimize the first question. For example, the information processing device 101 may obtain an updated or optimized question, also referred to as a second question, by applying the input 110 to an information processing model. For example, the first question in the input 110 may have grammatical errors or its expression may be unclear. In this case, the information processing device 101 may use the information processing model to obtain the second question, thereby improving the efficiency of subsequent processes.

[0043] Based on the optimized second question, the information processing device 101 can determine a response to the second question from the second business information 130. Specifically, the response can be determined based on the search enhancement generation. For example, the information processing device 101 can generate the response by using the information processing model in combination with the second business information 130. In some cases, the response can also include an answer to the first question, or an extended question to the input 110, the first question and / or the second question, etc.

[0044] In this way, the information processing device 101 can determine the target business domain corresponding to the input 110, effectively reducing the amount of information to be processed, thereby effectively improving the efficiency of the information processing process and the accuracy of the information processing results. In addition, the business domain corresponding to the input 110 can also be input or selected by the user, which can further improve the efficiency and accuracy of the information processing process.

[0045] Combine the following Figure 3A-Figure 6 The process executed by the information processing device 101 according to the embodiment of the present application is described.

[0046] Figure 3A Schematic diagram of an example process 300A of an information processing method according to some embodiments of the present disclosure is shown. Specifically, process 300A includes scene processing and recall range determination processes of the information processing method. In some embodiments, process 300A can be performed by information processing device 101. It should be understood that although process 300A is described below using information processing device 101 as an example, this is merely exemplary and is not intended to impose any limitation on the embodiments of the present disclosure. Figure 3A As shown in , the information processing method according to some embodiments of the present disclosure may include three scenarios: specified domain, general question and answer, and specified document.

[0047] In the specified domain scenario 301, the user has specified a business domain related to the input (also referred to as a "problem domain"), which can be considered as the target business domain described above. For example, the information processing device 101 can obtain the business domain related to the input through direct user input, asking questions to the user, or providing options to the user, and the scope of subsequent dialogue and knowledge recall will be limited to this business domain. Specifically, the information processing device 101 can provide the user with a domain selector card 302, which corresponds to multiple business domains (or subdomains). If the user selects a specific business domain or subdomain in box 304, the information processing device 101 performs a card callback in box 306 and recommends questions to the user in box 308. In some embodiments, the information about the questions recommended by the information processing device 101 to the user includes information about the specific business domain (represented as "BIZ_TYPE").

[0048] Next, in box 310, the information processing device 101 combines the user's input with the information about the specific business field (i.e., "Query+BIZ_TYPE"), and uses the combined information to obtain business information (also referred to as "knowledge information" or "knowledge"). Specifically, the information processing device 101 determines the specific business field as the field where information processing will be performed next for the user's input. In addition, in box 314, the information processing device 101 uses the business information corresponding to the specific business field as a designated knowledge group to determine the business information to be displayed to the customer as a response, and the information related to the designated knowledge group includes information related to the business field (i.e., ds=BIZ_TYPE). Additionally, in box 312, the information processing device 101 will also recommend recall FAQs to the user so that the user can further obtain relevant information.

[0049] In this way, the information processing device 101 can narrow the scope of information processing by the business field specified by the user, thereby reducing the amount of information and improving information processing efficiency. In addition, the information processing device 101 can improve the accuracy of information processing results by performing information processing in the business field specified by the user.

[0050] In the general question-and-answer scenario 316, in box 322, the information processing device 101 may only obtain the user's input. In some implementations, the input is described in natural language, and the information processing device 101 needs to process the user's input first to determine the user's intention. If the information processing device 101 can determine the business domain, the knowledge recall process is performed. If the information processing device 101 cannot determine the business domain, the information processing device 101 may ask a counter-question or reply to the user's input based on world knowledge (i.e., knowledge that is not related to the business domain and business information in all the knowledge accessible to the information processing device 101).

[0051] Specifically, in box 324, the information processing device 101 performs intent recognition after receiving the user's input. In some embodiments, the user's input may include content related to small talk and "world knowledge". In other words, the user's input may not include content corresponding to the above-mentioned business areas. In this case, the information processing device 101 can determine whether the user's input includes small talk content 318 and / or content 320 related to world knowledge. If the information processing device 101 determines whether the user's input includes small talk content 318 and / or content 320 related to world knowledge, in box 326 the information processing device 101 can reply to the user's input through network search or based on a language model.

[0052] Alternatively or additionally, if the information processing device 101 determines that the user's input corresponds to a problem in the above-mentioned business domain, the information processing device 101 uses long and short memory to identify the problem domain in box 328. In some implementations, in box 330, the information processing device 101 can identify the business domain corresponding to the user's input, that is, the target business domain described above. In this case, in box 332, the information processing device 101 combines the target business domain with the user's input (that is, "Query+BIZ_TYPE"), and in box 314 determines the business information associated with the target business domain as a designated knowledge group for knowledge recall. If the information processing device 101 cannot identify the business domain corresponding to the user's input, in box 334, the information processing device 101 can continue to process the user's input (that is, "Query"). In box 336, the information processing device 101 can determine all the information that can be accessed as the scope of knowledge recall for this information processing.

[0053] In this way, the information processing device 101 can determine the business field corresponding to the user's input, narrow the scope of information processing, thereby reducing the amount of information, improving information processing efficiency and enhancing the user's experience. In addition, the information processing device 101 can also determine the user's intention, thereby determining the specific scope of knowledge recall, improving the efficiency and accuracy of information processing.

[0054] In the designated document scenario 338, in box 344, the user's input includes at least one document. Alternatively, the user's input may include relevant information of at least one document, such as the identification of the document, etc. In addition, the scope of subsequent dialogue and knowledge recall will be limited to the at least one document. The information processing device 101 will generate a response to the user's input based on the information in the document. For example, the document input by the user includes information related to the activity push 340 and the course push 342. In box 346, the information processing device 101 performs intent recognition after receiving the user's input. If the user's input is about chatting or world knowledge, then in box 352, the information processing device 101 generates a reply to the user's input by searching in the designated document and / or using a language model. Alternatively, if the user's input is about the above-mentioned business field or business information, then in box 348, the information processing device 101 will combine the user's input and the business field and / or business information corresponding to the document (i.e., "Query+BIZ_TYPE"). Furthermore, in block 350 , the information processing device 101 determines the document designated by the user as the recall scope of knowledge.

[0055] Additionally, the information processing device 101 enters “recall” at 303 , whereby the information processing device 101 may perform knowledge recall according to the results of the scenario processing and recall scope determination in process 300A.

[0056] In this way, the information processing device 101 can generate a reply to the user's input based on the information in the document provided by the user. In addition, the information processing device 101 can also determine the user's intention, thereby determining the specific scope of knowledge recall, thereby improving the efficiency and accuracy of information processing.

[0057] Figure 3B A schematic diagram of an example process 300B of an information processing method according to some embodiments of the present disclosure is shown. Specifically, process 300B includes a knowledge recall process of the information processing method. In some implementations, process 300B is executed after process 300A, and the scope of knowledge recall in process 300B can be determined in process 300A. In some embodiments, process 300B can be executed by information processing device 101. It should be understood that although process 300B is described below using information processing device 101 as an example, this is merely exemplary and is not intended to impose any limitation on the embodiments of the present disclosure.

[0058] As described above, process 300B may be performed by information processing device 101 after process 300A. For example, the knowledge recall process in process 300B may be performed based on the results of the scenario processing and recall range determination process of process 300A. As shown in the figure, Figure 3B Recall 303 and Figure 3A The recall 303 in is the same.

[0059] like Figure 3B As shown in , in 303, the information processing device 101 can enter "recall" to perform the result processing process. Through recall, the information processing device 101 can obtain business information (also referred to as "business knowledge" or "knowledge"). In box 356, the information processing device 101 can recommend answers to the user. If there is no answer at present, in box 358, the information processing device 101 determines whether there is an answer according to the scope of the determined knowledge recall (also referred to as a "knowledge group"). Alternatively, if the information processing device 101 has already obtained the recommended answer, in box 357, the information processing device 101 can recall the recommended question, and the recommended question is also associated with the determined knowledge group. In addition, in box 370, the information processing device 101 can generate a recommended question message.

[0060] Next, in box 360, the information processing device 101 can generate an answer based on the business knowledge obtained in the knowledge recall process using the model. Specifically, the information processing device 101 can describe the recalled business knowledge in natural language through the language model to reply to the user's input. In addition, in box 368, the information processing device 101 can generate an answer message based on the reply to the user's input.

[0061] Alternatively, in box 362, in the case of a specified document, the information processing device 101 may perform knowledge recall in the document specified by the user. In some embodiments, the information processing device 101 may generate a reply to the user's input by performing knowledge recall in the document specified by the user. In this case, the information processing device 101 may generate an answer based on the business knowledge obtained in the knowledge recall process using a model, thereby generating an answer message. Alternatively or additionally, the information processing device 101 may not be able to generate a reply to the user's input by performing knowledge recall in the document specified by the user. In addition, if the answer to the user's input cannot be obtained in the document, in box 366, the information processing device 101 may reply to the user with a predetermined fallback message. Additionally, in box 364, the information processing device 101 may question the user. For example, the information processing device 101 may present a follow-up question to the user to confirm whether the document is correct or whether the question in the user's input is correct.

[0062] In this way, the information processing device 101 can effectively reduce the amount of information to be processed, thereby improving the efficiency of information processing. In addition, the information processing device 101 can avoid processing similar business information in different business fields during the information processing process, thereby improving the accuracy of the information processing results.

[0063] Reference below Figure 4 A schematic diagram describing a general question-answer information processing process 400 according to some embodiments of the present disclosure. It should be understood that the process 400 may be executed by the information processing device 101 or by other appropriate devices, and the embodiments of the present disclosure are not limited thereto.

[0064] In the "Query Rewrite" of box 402, the information processing device 101 may rewrite the user's input. For example, the user's input may include a question. The information processing device 101 may use the information processing model to combine the context in the user's input to determine whether the question needs to be rewritten. If the question needs to be rewritten, the information processing device 101 may optimize the question using the information processing model to obtain an optimized question.

[0065] In the "sub-intention query" of box 404, the information processing device 101 can use the information processing model to determine the intent information corresponding to the optimized question. Specifically, in the "conditional branch" of box 406, the information processing device 101 can determine whether the user's intention is to chat. In some embodiments, the information processing device 101 determines that the intention is a chat intention. For example, the optimized questions include "Hello", "How are you feeling", and other content. In this case, the information processing device 101 can present a predetermined reply to the user. In some implementations, the information processing device 101 only generates answers for questions related to business areas or business information. Additionally, the information processing device 101 uses a unified answer to reply to chat questions. Specifically, in box 408, the information processing device 101 can push messages for the chat intention.

[0066] In box 410, if the information processing device 101 determines that the intention corresponding to the user's input is general knowledge recall, the information processing device 101 can perform knowledge recall based on the optimized question. In box 412, the information processing device 101 can determine whether the business knowledge related to the optimized question is recalled at the conditional branch. If the information processing device 101 does not recall the business knowledge related to the user's input (i.e., "no knowledge recall"), in the "world knowledge logic execution" of box 414, the information processing device 101 can use the information processing model to reply to the optimized question based on the world knowledge.

[0067] Alternatively or additionally, if the information processing device 101 determines that the business information related to the user's input is recalled (i.e., "there is knowledge recall"), then in the conditional branch of box 416, the information processing device 101 can perform business domain identification. For example, the information processing device 101 can count all the recalled business information and at least one business domain associated with the business information. If more than half of all the recalled business information is associated with the same business domain, the business domain is determined to be the business domain corresponding to the optimized question, and subsequent dialogues and knowledge recall will be limited to the business domain.

[0068] For example, if the information processing device 101 determines that the A business domain corresponds to the question, then the A business domain Q&A is entered in box 424. In this case, the information processing device 101 can perform further knowledge recall in the business information corresponding to the A business domain to answer the question. Similarly, if the information processing device 101 determines that the B business domain corresponds to the question, the information processing device 101 can enter the B business domain Q&A in box 422. If the information processing device 101 determines that the C business domain corresponds to the question, the information processing device 101 can enter the C business domain Q&A in box 420.

[0069] Alternatively, if the information processing device 101 cannot determine the business domain corresponding to the optimized question, then in block 418 , the information processing device 101 may ask a counter-question to the user and determine the business domain based on the user's answer to the counter-question.

[0070] In this way, the information processing device 101 can determine the business field corresponding to the user's input, narrow the scope of information processing, and thus improve the efficiency of information processing. In addition, the information processing device 101 can avoid performing knowledge recall in multiple different business fields to obtain similar erroneous business information associated with multiple business fields, thereby improving the accuracy of the information processing results.

[0071] Reference below Figure 5 A schematic diagram of an information processing process 500 for a specified business domain according to some embodiments of the present disclosure is described. It should be understood that the process 500 may be executed by the information processing device 101 or by other appropriate devices, and the embodiments of the present disclosure are not limited thereto.

[0072] In block 502, the information processing device 101 may determine whether the business domain specified by the user is manually input or selected by the user from the provided candidate business domains. For example, the information processing device 101 may provide the user with at least one recommended question based on the user's input, and the recommended question is associated with the business domain. In this case, if the user selects the recommended question, the information processing device 101 may determine that the business domain associated with the recommended question is selected by the user from the provided candidate business domains.

[0073] Specifically, the information processing device 101 can make a judgment in the "conditional branch" of box 504. If the user specifies the business field by manual input, for example, the user inputs a question, the information processing device 101 can perform knowledge recall in box 508. In addition, the scope of knowledge recall is the business information associated with the business field input by the user.

[0074] In this case, in block 510, the information processing device 101 may summarize the answer based on the knowledge recalled in “knowledge recall” in block 508. In some implementations, the information processing device 101 may describe the knowledge in natural language using an information processing model, thereby presenting an answer to the user's input to the user.

[0075] Alternatively or additionally, if the user selects a business field by clicking on a recommended question, the information processing device 101 may recall answers from the recommended question set in block 506. For example, the recommended question set includes multiple recommended questions, and additionally, these recommended questions and related answers may be stored in association. In this case, the information processing device 101 may recall answers related to the recommended question based on the recommended question selected by the user.

[0076] Next, in block 512, the information processing device 101 may recall the recommended questions corresponding to the user's input. For example, after the user gets the answer to the user's input, he or she may want to learn more about related business information or similar business information in other fields. In some embodiments, the information processing device 101 may access a set of recommended questions and may recall recommended questions from the set of recommended questions to present to the user.

[0077] In box 514, the information processing device 101 may push the results of the above process, for example, providing or presenting the recommended questions obtained in box 512 and the answers to the user's input obtained in box 510 or box 506 to the user. In some implementations, the information processing device 101 may provide or present these contents to the user by sending a message to the user.

[0078] In this way, the information processing device 101 can effectively perform knowledge recall and present knowledge and recommended questions for the user's input to the user when the user specifies the business field, thereby improving the efficiency and accuracy of information processing.

[0079] Reference below Figure 6 A schematic diagram of an information processing process 600 for a specified business domain according to some embodiments of the present disclosure is described. It should be understood that the process 600 may be executed by the information processing device 101 or by other appropriate devices, and the embodiments of the present disclosure are not limited thereto.

[0080] In block 602, the information processing device 101 may obtain a document specified by a user input. In block 604, the information processing device 101 may perform document fragment recall on the document. Specifically, the information processing device 101 may perform document fragment recall based on the user input using an information processing model.

[0081] In box 606, the information processing device 101 can generate an answer to the user's input based on the recalled document fragments. In "Loading all document fragments" in box 608, the information processing device 101 can load all document fragments and generate recommended questions based on these document fragments using the information processing model. In addition, in box 610, the information processing device 101 can generate recommended questions based on the answer and the content of the document. In box 612, the information processing device 101 can present the recommended questions and answers to the user. For example, the information processing device 101 can integrate the recommended questions and answers in a message card and send it to the user.

[0082] In this way, the information processing device 101 can perform knowledge recall in the document specified by the user and generate answers and recommended questions for the user's input, thereby improving information processing efficiency.

[0083] Figure 7 FIG. 7 is a flowchart of a method 700 for information processing according to some embodiments of the present disclosure. It should be understood that the method 700 may be, for example, Figure 1 The information processing device 101 or other appropriate device is used for execution.

[0084] At 710, the information processing device 101 determines first business information related to the user's input. The first business information is associated with at least one candidate business domain. At 720, the information processing device 101 determines a target business domain corresponding to the input based on the first business information and at least one candidate business domain. At 730, the information processing device 101 determines second business information associated with the target business domain based on the input.

[0085] In some exemplary embodiments, the information processing device 101 may determine the target business field corresponding to the input in the following manner, for example, by determining the degree of relevance of each candidate business field in at least one candidate business field to the input based on the first business information, and determining the target business field from the at least one candidate business field based on the degree of relevance.

[0086] In some exemplary embodiments, the information processing device 101 may determine the target business domain corresponding to the input by applying the first business information and at least one candidate business domain to a domain determination model.

[0087] In some exemplary embodiments, the domain determination model may be obtained by training by taking reference business information and a plurality of reference candidate business domains as inputs and taking a reference target business domain as output.

[0088] In some exemplary embodiments, the information processing device 101 may determine in the information database first business information related to the input and associated with at least one candidate business domain. The information database may include candidate business information associated with multiple candidate business domains.

[0089] In some exemplary embodiments, the user input may include business domain information, and method 700 may further include: determining business information associated with the business domain indicated by the business domain information from an information library based on the input, the information library including candidate business information associated with multiple candidate business domains.

[0090] In some exemplary embodiments, the user input may include a first question, and method 700 may further include: obtaining a second question by applying the input to an information processing model, wherein the second question is an optimization of the first question; and determining a response to the second question from the second business information.

[0091] In some exemplary embodiments, the method 700 may further include: determining a response to the input based on the second service information.

[0092] Figure 8 800 is a block diagram of an apparatus 800 for information processing according to some embodiments of the present disclosure. The apparatus 800 may be implemented as or included in Figure 1 The information processing device 101 or other appropriate devices. Each module / component in the apparatus 800 may be implemented by hardware, software, firmware or any combination thereof.

[0093] As shown in the figure, the device 800 includes a first determination module 810, which is configured to determine first business information related to the user's input, and the first business information is associated with at least one candidate business field; a second determination module 820, which is configured to determine a target business field corresponding to the input based on the first business information and at least one candidate business field; and a third determination module 830, which is configured to determine second business information associated with the target business field based on the input.

[0094] In some exemplary embodiments, the second determination module 820 may be further configured to determine the relevance of each of the at least one candidate business field to the input based on the first business information; and determine the target business field from the at least one candidate business field based on the relevance.

[0095] In some exemplary embodiments, the second determination module 820 may be further configured to determine the target business domain by applying the first business information and at least one candidate business domain to a domain determination model.

[0096] In some exemplary embodiments, the domain determination model is trained by taking reference business information and a plurality of reference candidate business domains as inputs and taking a reference target business domain as output.

[0097] In some exemplary embodiments, the first determination module 810 may be further configured to determine first business information related to the input in an information library, where the information library includes candidate business information associated with a plurality of candidate business fields.

[0098] In some exemplary embodiments, the input may include business domain information, and the apparatus 800 may further include an information determination module configured to determine business information associated with the business domain indicated by the business domain information from an information library based on the input, the information library including candidate business information associated with multiple candidate business domains.

[0099] In some exemplary embodiments, the input may include a first question, and the device 800 may also include an input optimization module configured to obtain a second question by applying the input to an information processing model, wherein the second question is an optimization of the first question; and determine a response to the second question from the second business information.

[0100] In some exemplary embodiments, the apparatus 800 may further include a response determination module configured to determine a response to the input based on the second service information.

[0101] Fig. 9 FIG. 9 is a block diagram of an electronic device 900 capable of implementing an embodiment of the present disclosure. It should be understood that Fig. 9The electronic device 900 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Fig. 9 The electronic device 900 shown may be used to implement the above-described method. Fig. 9 The electronic device 900 shown can be used to implement Figure 1 The information processing device 101 or Figure 8 information processing device 800.

[0102] like Fig. 9 As shown, the electronic device 900 is in the form of a general-purpose computing device. The components of the electronic device 900 may include, but are not limited to, one or more processors or processing units 910, a memory 920, a storage device 930, one or more communication units 940, one or more input devices 950, and one or more output devices 960. The processing unit 910 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 920. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 900.

[0103] The electronic device 900 typically includes a plurality of computer storage media. Such media may be any available media accessible to the electronic device 900, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 920 may be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 930 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data (e.g., training data for training) and may be accessed within the electronic device 900.

[0104] The electronic device 900 may further include additional removable / non-removable, volatile / non-volatile storage media. Fig. 9 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. Memory 920 may include a computer program product 925 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0105] The communication unit 940 implements communication with other computing devices through a communication medium. Additionally, the functions of the components of the electronic device 900 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 900 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0106] The input device 950 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 960 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 900 may also communicate with one or more external devices (not shown) through the communication unit 940 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 900, or communicate with any device that allows the electronic device 900 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0107] According to an exemplary embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary embodiment of the present disclosure, a computer program product is also provided, the computer program product is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary embodiment of the present disclosure, a computer program product is provided, on which a computer program is stored, and when the program is executed by a processor, the method described above is implemented.

[0108] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0109] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0110] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0111] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0112] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the marketplace, or to enable other persons of ordinary skill in the art to understand the various embodiments disclosed herein.

Claims

1. An information processing method, comprising: Determining first business information related to the user's input, wherein the first business information is associated with at least one candidate business field; determining a target business domain corresponding to the input based on the first business information and the at least one candidate business domain; as well as Second business information associated with the target business area is determined based on the input.

2. The method according to claim 1, wherein determining a target business domain corresponding to the input comprises: Determining, based on the first business information, a degree of relevance between each candidate business field in the at least one candidate business field and the input; as well as The target business field is determined from the at least one candidate business field based on the degree of relevance.

3. The method according to claim 1, wherein determining a target business domain corresponding to the input comprises: The target business domain is determined by applying the first business information and the at least one candidate business domain to a domain determination model.

4. The method according to claim 3, wherein the domain determination model is obtained by training by taking reference business information and a plurality of reference candidate business domains as inputs and taking a reference target business domain as output.

5. The method according to claim 1, wherein determining the first business information associated with the at least one candidate business domain comprises: Determine first business information related to the input in an information base, wherein the information base includes candidate business information associated with a plurality of candidate business areas.

6. The method of claim 1, wherein the input includes business domain information, and the method further comprises: Based on the input, business information associated with the business field indicated by the business field information is determined from an information base, wherein the information base includes candidate business information associated with a plurality of candidate business fields.

7. The method of claim 1 , wherein the input comprises a first question, and the method further comprises: A second problem is obtained by applying the input to an information processing model, wherein the second problem is an optimization of the first problem; as well as An answer to the second question is determined from the second service information.

8. The method according to any one of claims 1 to 7, further comprising: A response to the input is determined based on the second service information.

9. An information processing device, comprising: A first determination module is configured to determine first business information related to a user's input, wherein the first business information is associated with at least one candidate business field; a second determination module, configured to determine a target business field corresponding to the input based on the first business information and the at least one candidate business field; as well as The third determination module is configured to determine second business information associated with the target business field based on the input.

10. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the device to perform the method according to any one of claims 1 to 8 when executed by the at least one processing unit.

11. A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1 to 8 when executed by a processor.

Images