Business knowledge pushing method and device, equipment and medium

Abstract

The invention provides a business knowledge pushing method and device, equipment and a medium, and relates to application of a large model in the field of financial science and technology. The business knowledge pushing method comprises the following steps: obtaining dialogue contents of a first object and a second object, and object information of the first object; determining a to-be-replied question of the first object based on the dialogue content; based on the to-be-replied question, determining at least one knowledge point associated with the to-be-replied question in a pre-constructed knowledge graph; based on the at least one knowledge point and the object information, generating reply content corresponding to the to-be-replied question; and pushing the reply content to the second object.

Description

Technical Field

[0001] This application relates to the field of big data technology and can be applied to the field of financial technology. More specifically, it relates to a method, device, equipment, and medium for pushing business knowledge. Background Technology

[0002] In the fintech field, financial institution staff need to provide responses to customer inquiries when providing customer service. This requires staff to possess certain business knowledge so that they can quickly respond to complex customer questions.

[0003] However, in real-world service scenarios, customer questions are often complex and diverse, involving multiple aspects such as products, processes, and policies. When encountering difficult questions that cannot be answered immediately, staff typically need to interrupt service and obtain answers by manually consulting materials or internal experts. This approach cannot provide real-time responses during the conversation, resulting in excessively long customer wait times and negatively impacting the customer experience.

[0004] While some related technologies offer real-time knowledge base retrieval, the knowledge acquisition process remains at the passive query level, which is inefficient and may miss key information, making it difficult to guarantee the accuracy of the response. Summary of the Invention

[0005] In view of the above problems, this application provides a method, apparatus, device and medium for pushing business knowledge.

[0006] The first aspect of this application provides a method for pushing business knowledge, the method comprising: obtaining dialogue content between a first object and a second object, and object information of the first object; determining a question to be answered for the first object based on the dialogue content; determining at least one knowledge point associated with the question to be answered in a pre-constructed knowledge graph based on the question to be answered; generating reply content corresponding to the question to be answered based on at least one knowledge point and object information; and pushing the reply content to the second object.

[0007] According to an embodiment of this application, a response to a question to be answered is generated based on at least one knowledge point and object information, including: determining a first tag type for a first object based on the object information; and determining the level of detail for each knowledge point when displayed in the response content based on the first tag type.

[0008] According to an embodiment of this application, generating response content corresponding to a question to be answered based on at least one target knowledge point and object information further includes: determining a second tag type of a first object based on the object information, wherein the second tag type is different from the first tag type; determining a target knowledge point associated with the second tag type from at least one knowledge point based on the second tag type; and generating response content corresponding to the question to be answered based on the target knowledge point.

[0009] According to an embodiment of this application, pushing reply content to a second object includes: determining the push priority of each knowledge point when pushing reply content to the second object based on the level of detail of each knowledge point when it is displayed in the reply content.

[0010] According to an embodiment of this application, obtaining the dialogue content of a first object and a second object includes: obtaining the dialogue text of the first object and the second object; and obtaining the audio features of the first object when they are having a dialogue.

[0011] According to embodiments of this application, determining the question to be answered for a first object based on the dialogue content includes: determining a first dialogue text generated by the first object and a second dialogue text generated by the second object from the dialogue text; determining question words in the dialogue text based on the first dialogue text and audio features; determining at least one business keyword based on the first dialogue text and the second dialogue text; and determining the question to be answered based on the at least one business keyword and the question words.

[0012] According to an embodiment of this application, pushing reply content to a second object includes: generating summary information of the reply content based on the reply content; directly pushing the summary information to the second object; and displaying the reply content in response to a target operation of the second object.

[0013] A second aspect of this application provides a business knowledge push device, the method comprising: a data acquisition module for acquiring dialogue content between a first object and a second object, and object information of the first object; a first data processing module for determining a question to be answered by the first object based on the dialogue content; determining at least one knowledge point associated with the question to be answered in a pre-constructed knowledge graph based on the question to be answered; a second data processing module for generating response content corresponding to the question to be answered based on at least one knowledge point and object information; and a data push module for pushing the response content to the second object.

[0014] A third aspect of this application provides an electronic device comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method described above.

[0015] A fourth aspect of this application also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0016] The fifth aspect of this application also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method. Attached Figure Description

[0017] The above-mentioned contents, other objects, features and advantages of this application will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0018] Figure 1 The illustration shows an application scenario diagram of a method, apparatus, device, and medium for pushing business knowledge according to embodiments of this application;

[0019] Figure 2 This illustration shows one of the flowcharts for a method of pushing business knowledge according to an embodiment of this application;

[0020] Figure 3 This illustration shows a second flowchart of a method for pushing business knowledge according to an embodiment of this application;

[0021] Figure 4 This schematic diagram illustrates a structural block diagram of a business knowledge push device according to an embodiment of this application;

[0022] Figure 5 A block diagram of an electronic device suitable for implementing a business knowledge push method according to an embodiment of this application is shown schematically. Detailed Implementation

[0023] The embodiments of this application will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this application. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of this application for ease of explanation. However, it will be apparent that one or more embodiments may be implemented without these specific details. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0024] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The terms “comprising,” “including,” etc., as used herein indicate the presence of features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0025] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0026] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0027] In the technical solution of this application, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, and displayed data) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, application, and application of related data all comply with relevant laws, regulations, and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse.

[0028] In scenarios involving automated decision-making using personal information, the methods, devices, and systems provided in this application all offer users corresponding entry points for choosing to agree to or reject the automated decision-making results. If the user chooses to reject, the process proceeds to the expert decision-making stage. Here, "automated decision-making" refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests, or economic, health, and credit status through computer programs, and then making a decision. Here, "expert decision-making" refers to the activity of making decisions by personnel who specialize in a particular field, possess specialized experience, knowledge, and skills, and have reached a certain level of professional expertise.

[0029] Figure 1 The illustration schematically depicts an application scenario of a business knowledge push method, apparatus, device, medium, and program product according to an embodiment of this application.

[0030] like Figure 1As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0031] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0032] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0033] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0034] It should be noted that the business knowledge push method provided in this application embodiment can generally be executed by server 105. Correspondingly, the business knowledge push device provided in this application embodiment can generally be located in server 105. The business knowledge push method provided in this application embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the business knowledge push device provided in this application embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0035] It should be understood that Figure 1The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0036] It should be noted that the business knowledge recommendation method in this application can be applied to the fintech field, as well as to cross-business scenarios between fintech and other related fields. For example, in supply chain finance, which integrates finance and technology, it can not only recommend financial business knowledge but also combine knowledge from areas such as supply chain management and IoT technology to provide clients with comprehensive consulting services.

[0037] The following will be based on Figure 1 The described scene, through Figures 2-3 The method for pushing business knowledge according to the embodiments of this application will be described in detail.

[0038] Figure 2 One of the flowcharts illustrating a method for pushing business knowledge according to an embodiment of this application is shown.

[0039] like Figure 2 As shown, the method for pushing business knowledge according to the embodiments of this application includes: operations S201 to S203.

[0040] Operation S201 retrieves the dialogue content between the first object and the second object, as well as the object information of the first object.

[0041] In step S202, based on the dialogue content, determine the question to be answered for the first object; based on the question to be answered, determine at least one knowledge point associated with the question to be answered in the pre-constructed knowledge graph.

[0042] Operation S203 generates the response content corresponding to the question to be answered, based on at least one knowledge point and object information.

[0043] Operation S204 pushes the reply content to the second object.

[0044] In the embodiments of this application, the first object can be a customer consulting on a business issue, who is the initiator of the business knowledge request; the second object can be a staff member of a financial institution, who is the party receiving and processing the business knowledge response and responsible for conveying the response to the customer. The dialogue content refers to the information exchanged between the first and second objects, including but not limited to text, voice, and other forms.

[0045] In the embodiments of this application, the communication between the first object and the second object can be conducted online via text, voice or video, or offline in person.

[0046] In the embodiments of this application, the object information includes relevant information about the first object, including the first object's historical transaction records and business preferences, etc., for personalized generation of response content.

[0047] In the embodiments of this application, a knowledge graph is a structured semantic knowledge base that graphically displays the relationships between different knowledge points and is used to store connections between business knowledge. Each knowledge point is specific knowledge content in the knowledge graph associated with the question to be answered, serving as the basic material for generating the response.

[0048] In the embodiments of this application, the reply content is pushed to the display device carried by the second object.

[0049] Specifically, the system acquires the dialogue content between a first entity (customer) and a second entity (staff) in real time. This involves collecting the dialogue text through a communication interface, capturing audio features from the conversation via microphone, and integrating and recording this multimodal dialogue data. Simultaneously, after obtaining authorization from the first entity, the system retrieves its information from the customer database. Natural language processing (NLP) is then used to analyze the dialogue content. First, the dialogue text is segmented and part-of-speech tagging is performed, and question words are determined based on audio features. Then, named entity recognition (NAME) and semantic role labeling (SLA) are used to further obtain the questions to be answered. Next, based on the questions to be answered, at least one related knowledge point is identified from a pre-constructed knowledge graph using knowledge extraction and fusion techniques, through algorithms such as semantic matching and association analysis. These knowledge points are then combined with the first entity's information, and a response is generated according to pre-defined content generation rules. Finally, the response is pushed to the second entity via a message push module, completing the recommendation of business knowledge.

[0050] By acquiring the conversation content between customers and staff, as well as relevant customer information, the system identifies customer questions from the conversation, uses knowledge graphs to find relevant knowledge points, and combines customer information to generate personalized responses, which are then pushed to staff. This allows staff to answer customers' business questions based on the responses, thus overcoming the shortcomings of traditional methods that cannot quickly and accurately answer customers' difficult questions and improving the customer's business consultation experience.

[0051] According to an embodiment of this application, operation S202 generates response content corresponding to the question to be answered based on at least one knowledge point and object information, including: determining the first tag type of the first object based on the object information; and determining the level of detail of each knowledge point when displayed in the response content based on the first tag type.

[0052] In the embodiments of this application, the first tag type is an identifier that classifies the first object based on object information, used to determine the level of detail in which knowledge points are displayed in the response content. For example, it could be tag types such as "high level of financial knowledge" and "rich investment experience".

[0053] For example, by analyzing the object information of the first object, its first tag type is determined to be "Financial Knowledge Level: Beginner". Once the knowledge point related to the question to be answered is identified, the level of detail presented for this knowledge point in the response content will be adjusted to a more basic and simple description. The response content may simply introduce the basic concepts of risk diversification without going into depth about complex risk diversification models and theories. Conversely, if the first tag type is "Financial Knowledge Level: Advanced", the response content will elaborate on various risk diversification models, applicable scenarios, and case analyses.

[0054] In the embodiments of this application, the business domain of the first object is determined based on the first tag type of the first object. For example, if the first object's understanding of the financial field is quantified as a low level, then the level of detail in the presentation of knowledge points in the response content should also be low, and the content presented can be relatively simple; if the first object's understanding of the financial field is quantified as a high level, then the level of detail in the presentation of knowledge points in the response content should also be high, and the content presented can be more professional and complex.

[0055] By adopting the above method, the first tag type is determined using the object information of the first object. Based on this tag type, the level of detail for each knowledge point in the response content is determined, so that the response content can present knowledge points in a way that is appropriate in detail according to the different characteristics of customers, meet the needs of different customers for knowledge depth, and further improve the personalization and targeting of the response content.

[0056] According to an embodiment of this application, operation S202, based on at least one target knowledge point and object information, generates response content corresponding to the question to be answered, and further includes: determining a second tag type of the first object based on the object information, wherein the second tag type is different from the first tag type; determining a target knowledge point associated with the second tag type from at least one knowledge point based on the second tag type; and generating response content corresponding to the question to be answered based on the target knowledge point.

[0057] Specifically, firstly, based on the object information of the first object, data mining and analysis techniques are used to evaluate and classify it from multiple dimensions, thereby determining the second label type of the first object. The second label type differs from the previously determined first label type; there can be multiple second labels, each representing an attribute of the first object. Next, for at least one identified knowledge point, association rules and semantic matching algorithms built in a knowledge graph are used to mine the intrinsic connections between each knowledge point and the second label type, accurately selecting target knowledge points closely related to the second label type. Finally, based on the information contained in the target knowledge points and a pre-defined response content generation strategy, natural language generation technology is used to organize, sort, and transform the target knowledge points, generating response content that accurately addresses the question to be answered by the first object, ensuring that the response content highly matches the specific needs and actual situation reflected by the first object based on the second label type.

[0058] By adopting the above method, in addition to adjusting the level of detail of knowledge points displayed according to the first tag type, the second tag type is also used to select target knowledge points related to the specific characteristics of the customer from a large number of knowledge points, thereby further refining the generation of response content, making the response more in line with the customer's actual situation and needs, and improving the quality and practicality of the response content.

[0059] According to an embodiment of this application, operation S204, pushing reply content to the second object, includes: determining the push priority of each knowledge point when pushing reply content to the second object based on the level of detail of each knowledge point when displayed in the reply content.

[0060] In the embodiments of this application, the push priority is determined based on the level of detail of each knowledge point displayed in the response content. When pushing the response content to the second object, the order or importance of each knowledge point is ranked. Knowledge points with higher level of detail or more critical to solving the customer's problem may have a higher push priority.

[0061] Specifically, the priority of push notifications is determined based on the level of detail of the knowledge points in the response content. This allows the knowledge points to be presented in order of importance and detail in solving customer problems when the response content is pushed to the staff. This helps the staff to quickly understand the key content, improves the efficiency of information transmission and processing, and thus provides more efficient services to customers.

[0062] According to an embodiment of this application, operation S201, obtaining the dialogue content of the first object and the second object, includes: obtaining the dialogue text of the first object and the second object; obtaining the audio features of the first object when they are having a dialogue.

[0063] Specifically, dialogue text is the text record of the communication between the first and second parties directly collected from communication channels (such as online chat windows, speech-to-text systems, etc.), forming the original dialogue text.

[0064] Furthermore, during the voice acquisition process, audio of the dialogue content is also captured by acquiring the raw audio stream of the conversation between the two parties in real time. This audio stream is then fed into a speech recognition engine for real-time speech-to-text processing. The output is a text stream with time-stamped tags, and each segment of text is labeled with the speaker (first party or second party). Audio features are also used to extract audio-physical parameters representing the dialogue intent from the raw audio signal of the first party.

[0065] For example, while performing speech recognition, signal processing analysis is performed on the original audio segment of the first object. Features are extracted using digital signal processing algorithms or pre-trained acoustic models. For example, audio features may include any of the following: the fundamental frequency of the first object's audio stream, reflecting pitch, where a rising pitch often occurs at the end of interrogative sentences; the energy of the first object's audio stream, reflecting volume, where a louder volume may indicate emphasis; the speech rate of the first object's audio stream, the number of pronunciations per unit time; and pauses in the first object's audio stream, representing the duration of silence between words.

[0066] In the embodiments of this disclosure, various types of audio features can further help users determine the question words in the dialogue text, as detailed in subsequent embodiments.

[0067] By employing the above method, the dialogue text of the first and second parties, as well as the audio features of the first party during the dialogue, are simultaneously acquired, achieving multimodal acquisition of conversational information. This approach not only relies on text content but also incorporates the acoustic characteristics of speech as a supplementary data source, effectively overcoming analytical biases caused by semantic ambiguity or incomplete expression in single textual information, thus enabling a more accurate understanding of customer intent.

[0068] Figure 3 A flowchart illustrating a method for pushing business knowledge according to an embodiment of this application is shown in the illustration.

[0069] According to an embodiment of this application, in operation S202, based on the dialogue content, the question to be answered for the first object is determined, such as... Figure 3 As shown, this includes operations S301 to S304.

[0070] Operation S301: Determine the first dialogue text generated by the first object and the second dialogue text generated by the second object from the dialogue text.

[0071] Operation S302: Based on the first dialogue text and audio features, determine the question words in the dialogue text.

[0072] In an embodiment of the present application, a query word represents a keyword or phrase that clearly indicates an interrogative sentence in the first dialogue text in the dialogue context; at the same time, the query word is used together with a business keyword to determine the question to be replied to for the first object.

[0073] Operation S303: Determine at least one business keyword according to the first dialogue text and the second dialogue text.

[0074] In an embodiment of the present application, a business keyword is a professional vocabulary or entity related to the financial business field that appears in the first dialogue text or the second dialogue text, and is used to determine the subject of the question to be replied to.

[0075] Operation S304: Determine the question to be replied to according to at least one business keyword and the query word.

[0076] Specifically, after obtaining the dialogue text, the dialogue text is separated into the first dialogue text and the second dialogue text. For the content in the first dialogue text, keyword matching is performed to check whether there is a query word in the query word library. Among them, for a query word with ambiguity, for example, the text content such as "right" or "呢" is verified twice in combination with the audio feature of the first dialogue text. For example, if the end of a certain part of the content in the first dialogue text has "吗", and the audio feature shows that the end tone rises significantly, it can be confirmed that this is an interrogative sentence. For another example, if the end of a certain part of the content in the first dialogue text has "吧", but the audio feature shows that the tone is flat or decreasing, it may be a declarative sentence or a suggestion, rather than a strict question, so its priority as a "question to be replied to" can be reduced. At the same time, natural language processing is performed on the first dialogue text, and all business keywords are extracted using a predefined financial business dictionary or a named entity recognition model.

[0077] In an embodiment of the present disclosure, a certain part of the content in the first dialogue text that simultaneously meets the following target conditions can be determined as the question to be replied to:

[0078] Target condition one: This content belongs to the first dialogue text.

[0079] Target condition two: This content contains a query word, and the audio feature of this query word meets the preset query word audio feature after audio feature verification.

[0080] Target condition three: This content contains at least one business keyword to ensure that the question is related to the financial business.

[0081] In an embodiment of the present application, the following target condition may further be included: Target condition four: The question associated with this content has not been solved by the subsequent reply in the second dialogue text (that is, the staff has not given the answer related to the business keyword in this content).

[0082] By employing the above method, which uses question words and business keywords in the dialogue text, combined with audio features, to determine the questions to be answered, the true questions of customers can be identified more accurately. By integrating linguistic cues and acoustic features, it is possible to effectively distinguish between genuine interrogative sentences and declarative or exclamatory sentences in the dialogue, significantly improving the accuracy and robustness of question identification and avoiding misjudgments caused by relying solely on keyword matching.

[0083] According to an embodiment of this application, in operation S204, pushing reply content to the second object includes: generating summary information of the reply content based on the reply content; directly pushing the summary information to the second object; and displaying the reply content in response to the target operation of the second object.

[0084] Specifically, when pushing a response to the second recipient, the generated response is first analyzed to extract key sentences and phrases from the text. Based on word frequency statistics, semantic understanding, and sentence importance assessment, the response is condensed into a concise summary. The summary should retain the core points of the response, covering key conclusions, important suggestions, or key data related to the question. After generating the summary, it is sent directly to the second recipient via a push notification system. The receiving system on the second recipient's end monitors user actions in real time. When it detects that the second recipient has performed a pre-defined target operation (such as clicking on the summary or performing a gesture in a specific area), based on an event-triggered mechanism, it calls the database or cache storing the complete response content and displays the full response to the second recipient, satisfying their need for detailed information.

[0085] By employing the above method, the burden on staff from receiving excessive information is avoided. A summary of the response is first sent to them, allowing them to quickly grasp the core points. When staff require detailed information, the full response is displayed through a targeted action. This approach ensures effective information delivery while improving the flexibility and efficiency of information retrieval.

[0086] The following describes in detail the methods for identifying business keywords and query terms in the embodiments of this application.

[0087] In the embodiments of this application, word segmentation tools in natural language processing are used to segment the original dialogue text into individual words or phrases. Then, part-of-speech tagging tools are used to tag each word with its part of speech, such as noun, verb, adjective, adverb, etc., thereby understanding the grammatical structure of the sentence and the role of words in the sentence. Named entities in the dialogue text are identified, such as financial institution names, product names, customer names, dates, etc. Through a pre-trained named entity recognition model, this entity information can be accurately extracted from the text. Subsequently, dependency relationships between words in the sentence are analyzed to construct a dependency syntax tree. Through dependency relationships, the core verb of the text and the semantic connections between other components and the core verb can be determined, such as subject-verb, verb-object, and attributive-head relationships. For example, for the text "I want to understand the benefits of the product," it can be determined that "understand" is the core verb expressing the customer's intention, "I" is the subject, and "the benefits of the product" is the object, clearly showing the structure of the text. Through the above methods, the types of each word in the dialogue text are cleaned, thereby determining which are business keywords and question words. At the same time, the types of each word in the dialogue text can also be used to generate subsequent questions to be answered.

[0088] In the embodiments of this application, in addition to text recognition through word segmentation tools, the confidence level of the recognition result can be further determined through audio features.

[0089] For example, in the process of identifying business keywords and question words, a portion of the first dialogue text that meets objective conditions one to three may simultaneously include text content A and text content B. In this case, text content A and text content B correspond to question A and question B to be answered, respectively. Audio features can then be used to determine the confidence levels of text content A and text content B; that is, by obtaining the fundamental frequency, energy, speech rate, and pause features of the audio stream of the first object in text content A and text content B, respectively, the confidence levels of text content A and text content B used to generate question A and question B to be answered can be determined.

[0090] In the embodiments of this application, after obtaining the confidence levels of text content A and text content B, when pushing the response content to the second object (i.e., the staff), response content A and response content B can be displayed simultaneously for response content A corresponding to question A to be answered and response content B corresponding to question B to be answered. Among them, the response content with higher confidence level is displayed first.

[0091] In embodiments of this application, the response content with higher confidence level between response content A and response content B may be selected for display.

[0092] In the embodiments of this application, the knowledge graph can be updated and dynamically adjusted in real time. Using machine learning algorithms, the knowledge points and relationships in the knowledge graph are automatically updated based on the latest policies, product information, and customer feedback in the fintech field. For example, when new financial regulatory policies are introduced, the system can quickly integrate the relevant policy points into the knowledge graph, ensuring that the recommended responses are accurate and timely.

[0093] In the embodiments of this application, while displaying the response content, functions for further interaction with the customer are provided. For example, the customer can ask follow-up questions, provide feedback, or suggest modifications to the response content. The response strategy can be adjusted in a timely manner based on customer feedback, forming an interactive consultation service model that enhances communication and trust between the customer and the financial institution.

[0094] This application also provides a business knowledge push device, including:

[0095] Figure 4 The diagram illustrates a structural block diagram of a business knowledge push device according to an embodiment of this application.

[0096] Based on the aforementioned method for pushing business knowledge, this application provides a device for pushing business knowledge, which will be described below in conjunction with... Figure 4 The device is described in detail.

[0097] like Figure 4 As shown, the business knowledge push device 400 of this embodiment includes a data acquisition module 410, a first data processing module 420, a second data processing module 430, and a data push module 440.

[0098] According to an embodiment of this application, a data acquisition module 410 is used to acquire the dialogue content between a first object and a second object, as well as object information of the first object; a first data processing module 420 is used to determine the question to be answered for the first object based on the dialogue content; and to determine at least one knowledge point associated with the question to be answered in a pre-constructed knowledge graph based on the question to be answered; a second data processing module 430 is used to generate the response content corresponding to the question to be answered based on at least one knowledge point and object information; and a data push module 440 is used to push the response content to the second object.

[0099] According to an embodiment of this application, the second data processing module 430 is further configured to determine the first tag type of the first object based on the object information; and determine the level of detail of each knowledge point when displayed in the response content based on the first tag type.

[0100] According to an embodiment of this application, the second data processing module 430 is further configured to determine a second tag type of the first object based on the object information, wherein the second tag type is different from the first tag type; determine a target knowledge point associated with the second tag type from at least one knowledge point based on the second tag type; and generate a response content corresponding to the question to be answered based on the target knowledge point.

[0101] According to an embodiment of this application, the data push module 440 is further configured to determine the push priority of each knowledge point when pushing the reply content to the second object based on the level of detail of each knowledge point when displayed in the reply content.

[0102] According to an embodiment of this application, obtaining the dialogue content of a first object and a second object includes: obtaining the dialogue text of the first object and the second object; and obtaining the audio features of the first object when they are having a dialogue.

[0103] According to an embodiment of this application, the first data processing module 420 is further configured to: determine, from the dialogue text, a first dialogue text generated by a first object and a second dialogue text generated by a second object; determine, based on the first dialogue text and audio features, question words in the dialogue text; determine at least one business keyword based on the first dialogue text and the second dialogue text; and determine the question to be answered based on the at least one business keyword and the question words.

[0104] According to an embodiment of this application, the data push module 440 is further configured to generate summary information of the reply content based on the reply content; directly push the summary information to the second object; and display the reply content in response to the target operation of the second object.

[0105] According to embodiments of this application, any multiple modules among the data acquisition module 410, the first data processing module 420, the second data processing module 430, and the data push module 440 can be combined into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functions of one or more of these modules can be combined with at least some of the functions of other modules and implemented in one module. According to embodiments of this application, at least one of the data acquisition module 410, the first data processing module 420, the second data processing module 430, and the data push module 440 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any appropriate combination of any of these three implementation methods. Alternatively, at least one of the data acquisition module 410, the first data processing module 420, the second data processing module 430, and the data push module 440 may be implemented at least partially as a computer program module, which can perform corresponding functions when the computer program module is run.

[0106] Figure 5 A block diagram of an electronic device suitable for implementing a business knowledge push method according to an embodiment of this application is shown schematically.

[0107] like Figure 5 As shown, an electronic device 500 according to an embodiment of this application includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage portion 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this application.

[0108] RAM 503 stores various programs and data required for the operation of electronic device 500. Processor 501, ROM 502, and RAM 503 are interconnected via bus 504. Processor 501 executes various operations of the method flow according to embodiments of this application by executing programs in ROM 502 and / or RAM 503. It should be noted that programs may also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 may also execute various operations of the method flow according to embodiments of this application by executing programs stored in one or more memories.

[0109] According to embodiments of this application, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to a bus 504. The electronic device 500 may also include one or more of the following components connected to the input / output (I / O) interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 510 as needed so that computer programs read from it can be installed into the storage section 508 as needed.

[0110] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The aforementioned computer-readable storage medium carries one or more programs, which, when executed, implement the business knowledge push method according to the embodiments of this application.

[0111] According to embodiments of this application, the computer-readable storage medium can be a non-volatile computer-readable storage medium, such as including but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this application, the computer-readable storage medium may include ROM 502 and / or RAM 503 and / or one or more memories other than ROM 502 and RAM 503 described above.

[0112] Embodiments of this application also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code enables the computer system to implement the business knowledge push method provided in the embodiments of this application.

[0113] When the computer program is executed by the processor 501, it performs the functions defined in the system / apparatus of this application embodiment. According to the embodiments of this application, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0114] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 509, and / or installed from a removable medium 511. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0115] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by processor 501, it performs the functions defined in the system of this application embodiment. According to embodiments of this application, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0116] According to embodiments of this application, program code for executing the computer programs provided in the embodiments of this application can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device 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 computing device (e.g., via the Internet using an Internet service provider).

[0117] 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 application. 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 a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may 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.

[0118] Those skilled in the art will understand that the features described in the various embodiments of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. In particular, the features described in the various embodiments of this application can be combined and / or combined in various ways without departing from the spirit and teachings of this application. All such combinations and / or combinations fall within the scope of this application.

Claims

1. A method for pushing business knowledge, characterized in that, The method includes: Obtain the dialogue content between the first object and the second object, as well as the object information of the first object; Based on the dialogue content, determine the question to be answered for the first object; based on the question to be answered, determine at least one knowledge point associated with the question to be answered in a pre-constructed knowledge graph; Based on the at least one knowledge point and the object information, generate the response content corresponding to the question to be answered; The reply content is pushed to the second object.

2. The method according to claim 1, characterized in that, Based on the at least one knowledge point and the object information, generate the response content corresponding to the question to be answered, including: Based on the object information, determine the first tag type of the first object; Based on the first tag type, determine the level of detail for each knowledge point when it is displayed in the response content.

3. The method according to claim 2, characterized in that, Based on the at least one target knowledge point and the object information, generating the response content corresponding to the question to be answered further includes: Based on the object information, a second tag type for the first object is determined, wherein the second tag type is different from the first tag type; Based on the second tag type, determine the target knowledge point associated with the second tag type from the at least one knowledge point; Based on the target knowledge points, generate the corresponding response content for the question to be answered.

4. The method according to claim 2, characterized in that, Pushing the reply content to the second object includes: Based on the level of detail of each knowledge point when it is displayed in the response content, the push priority of each knowledge point is determined when pushing the response content to the second object.

5. The method according to claim 1, characterized in that, The process of obtaining the dialogue content between the first object and the second object includes: Obtain the dialogue text between the first object and the second object; Obtain the audio features of the first object during the dialogue.

6. The method according to claim 5, characterized in that, Based on the dialogue content, determine the questions to be answered for the first party, including: From the dialogue text, determine the first dialogue text generated by the first object and the second dialogue text generated by the second object, respectively; Based on the first dialogue text and the audio features, determine the question words in the dialogue text; Based on the first dialogue text and the second dialogue text, at least one business keyword is determined; The question to be answered is determined based on the at least one business keyword and the question word.

7. The method according to claim 1, characterized in that, Pushing the reply content to the second object includes: Based on the response content, a summary of the response content is generated; The summary information is directly pushed to the second object; In response to the target operation of the second object, the reply content is pushed to the second object.

8. A business knowledge push device, characterized in that, The method includes: The data acquisition module is used to acquire the dialogue content between the first object and the second object, as well as the object information of the first object; The first data processing module is used to determine the question to be answered for the first object based on the dialogue content; and to determine at least one knowledge point associated with the question to be answered in a pre-constructed knowledge graph based on the question to be answered. The second data processing module is used to generate the response content corresponding to the question to be answered based on the at least one knowledge point and the object information; The data push module is used to push the reply content to the second object.

9. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 7.

Images