Large model interaction method and system

Abstract

The invention provides a large model interaction method and system. The method comprises the following steps: acquiring user session input; based on the user session input and the current user intention, searching and summarizing to obtain an answer search result, and searching and summarizing marketing delivery information in a marketing database based on the user session input and the current user intention to obtain a marketing delivery search result; the quotation source of the answer retrieval result and the quotation source of the marketing release retrieval result are subjected to comprehensive sorting and then serve as a quotation source result to be returned to the user; summarizing and integrating the reference source result and the marketing release retrieval result to obtain an answer result and returning the answer result to the user; and integrating the user request, the answer result and the marketing retrieval result to obtain a recommended associated question, and returning the question to the user to guide the user to further perform multiple rounds of conversations. On the basis of retrieval enhancement and active retrieval, marketing information retrieval enhancement is provided, better experience is provided for users, and enterprise-side marketing requirements can be met.

Description

Technical Field

[0001] The present invention relates to the technical field of large models, and in particular to a large model interaction and system. Background Art

[0002] With the development of big model technology, users can quickly get answers through interaction with big models. On the user side, chatbots or dialogue platforms developed with application prompt word engineering and search enhancement can only get straightforward request results in limited chat memory windows and context information dialogues; on the enterprise side, when seeing the rapid growth of the number of applications and the sharp increase in traffic on the dialogue platform, it is impossible to effectively distribute marketing content to big model users.

[0003] Currently, most of the large model interaction systems are of the retrieval enhancement type, such as Figure 1 As shown, it mainly realizes interactive dialogue of proprietary content and real-time content through local proprietary database or third-party API retrieval. However, it has the following disadvantages: the answer result is a plain text directly associated with the conversation request; and the user needs to describe the needs as accurately and in detail as possible without getting a more accurate answer.

[0004] Taking the perplexity platform as an example, as one of the dialogue platforms with better experience, the perplexity platform supplements the reference source information and related question feedback on the basis of traditional search enhancement direct answer, so that users can further understand the answer details and simplify the user question interaction. Its page screenshots and logical analysis structure are shown below: Figure 2 and Figure 3 As shown in the figure, the disadvantages are that the current platform returns results directly related to the session request, and does not further infer the user's demand intention to provide service recommendations. The lack of marketing capabilities also limits the platform's business model to user subscription payment. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a large model interaction method and system, which proposes marketing information retrieval enhancement based on retrieval enhancement and active retrieval, provides users with a better experience and can meet the marketing needs of enterprises.

[0006] In a first aspect, the present invention provides a large model interaction method, comprising the following steps:

[0007] S1. Obtain user session input and parse the user session input to obtain a user request;

[0008] S2. Search and summarize the user request to obtain answer search results, which include reference source links and search content;

[0009] At the same time, the user's personal setting information, third-party user portrait information, historical conversation information and intention, and current conversation context are comprehensively analyzed to summarize and infer the current user intention; based on the user conversation input and the current user intention, the marketing delivery information is retrieved and summarized in the marketing database to obtain the marketing delivery retrieval result, which includes delivery links, delivery content, delivery type, and delivery strategy;

[0010] S3, comprehensively sorting the reference sources of the answer search result and the marketing delivery search result based on the link weights of the answer search result and the marketing delivery search result, and returning the results to the user as reference source results;

[0011] S4, after summarizing and integrating the reference source results and the marketing placement search results, an answer result is obtained and returned to the user;

[0012] S5. Integrate the user request, the answer result, and the marketing search result, obtain recommended related questions, and return them to the user to guide the user to further conduct multiple rounds of dialogue.

[0013] In a second aspect, the present invention provides a large model interaction system, comprising:

[0014] The session parsing module is used to obtain user session input and parse the user session input to obtain user requests;

[0015] A retrieval module, used to search and summarize the user request to obtain an answer search result, wherein the answer search result includes a reference source link and a search content;

[0016] The marketing delivery module is used to comprehensively analyze the user's personal setting information, third-party user portrait information, historical conversation information and intention, and current conversation context while the search module is searching, and summarize and infer the current user intention; based on the user conversation input and the current user intention, search and summarize the marketing delivery information in the marketing database to obtain the marketing delivery search result, which includes the delivery link, delivery content, delivery type, and delivery strategy;

[0017] A reference source generation module is used to comprehensively sort the reference sources of the answer search result and the marketing delivery search result based on the link weights of the answer search result and the marketing delivery search result, as well as the bidding price of the marketing delivery search result, and return the results as reference source results to the user;

[0018] An answer result generating module is used to summarize and integrate the reference source results and the marketing delivery search results, obtain the answer result and return it to the user;

[0019] The recommended related question generation module is used to integrate the user request, the answer result, and the marketing search result, and return the recommended related questions to the user to guide the user to further conduct multiple rounds of dialogue.

[0020] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages: the present invention integrates large-model reasoning and retrieval capabilities and personalized content generation to improve user experience; at the same time, it meets the marketing needs of enterprise users, integrates marketing information flow strategies, and integrates marketing content into questions and answers to achieve more extensive and efficient marketing content distribution, expand the application methods of large models, provide users with a better experience, and can undertake enterprise-side marketing needs.

[0021] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The present invention will be further described below in conjunction with embodiments with reference to the accompanying drawings.

[0023] Figure 1 A flowchart of the existing large model interaction method;

[0024] Figure 2 This is a schematic diagram of the interface when the perplexity platform returns results;

[0025] Figure 3 A logical diagram of the process flow that returns the results for the perplexity platform;

[0026] Figure 4 is a flow chart of the method of the present invention;

[0027] Figure 5 It is a schematic diagram of the framework of the system of the present invention. DETAILED DESCRIPTION

[0028] The embodiments of the present application provide a large model interaction method and system, and propose marketing information retrieval enhancement based on retrieval enhancement and active retrieval, so as to provide users with a better experience and meet the marketing needs of enterprises.

[0029] The technical solution in the embodiments of the present application has the following overall idea: the present invention integrates large-model reasoning and retrieval capabilities and personalized content generation to enhance user experience; at the same time, it meets the marketing needs of enterprise users, integrates marketing information flow strategies, integrates marketing content into questions and answers, achieves wider and more efficient marketing content distribution, expands the application methods of large models, provides users with a better experience and can undertake the marketing needs of the enterprise side.

[0030] Embodiment 1

[0031] like Figure 4 As shown, this embodiment provides a large model interaction method, including the following steps:

[0032] S1. Obtain user session input and parse the user session input to obtain a user request;

[0033] S2. Search and summarize the user request to obtain answer search results, which include reference source links and search content;

[0034] At the same time, the user's personal setting information, third-party user portrait information, historical conversation information and intention, and current conversation context are comprehensively analyzed to summarize and infer the current user intention; based on the user conversation input and the current user intention, the marketing delivery information is retrieved and summarized in the marketing database to obtain the marketing delivery retrieval result, which includes delivery links, delivery content, delivery type, and delivery strategy;

[0035] S3. After comprehensively ranking the reference sources of the answer search result and the marketing delivery search result based on the link weights of the answer search result and the marketing delivery search result, as well as the bidding price of the marketing delivery search result, the reference sources of the answer search result and the marketing delivery search result are returned to the user as reference source results; the comprehensive ranking includes:

[0036] (a1) Applicable to guiding traffic to news sites, that is, when users search for a certain piece of news, it can improve the ranking of links in similar news;

[0037] (a2) Applicable to official link protection and traffic diversion, based on official information protection, the latest marketing plan distribution, and methods, to ensure that users receive the latest official information;

[0038] (a3) Applicable to the competition among objects, lists or channels of the same category, and to recommend similar products or services while answering user questions.

[0039] S4. After summarizing and integrating the reference source results and the marketing delivery search results, an answer result is obtained and returned to the user; the summarizing and integrating is achieved based on the delivery strategy of the marketing delivery search results, and includes:

[0040] (b1) Supplementary additional information based on intention speculation: that is, based on the current user intention speculation and the possible user service request intention, supplementary service function docking is provided;

[0041] (b2) Expansion and supplement of the official latest marketing plan;

[0042] (b3) Expansion and replacement of similar lists, competing products, channel information, and promotional information.

[0043] S5. Integrate the user request, the answer result, and the marketing search result, and further integrate the following contents:

[0044] (c1) The system guides service functions based on intention inference;

[0045] (c2) Guidance questions for official marketing plans;

[0046] (c3) Questions about similar lists, competing products, channel information, and promotional information;

[0047] The recommended related questions are then returned to the user, guiding the user to further engage in multiple rounds of dialogue.

[0048] Based on the same inventive concept, the present application also provides a device corresponding to the method in Example 1, see Example 2 for details.

[0049] Embodiment 2

[0050] like Figure 5 As shown, in this embodiment, a large model interaction system is provided, including:

[0051] The session parsing module is used to obtain user session input and parse the user session input to obtain user requests;

[0052] A retrieval module, used to search and summarize the user request to obtain an answer search result, wherein the answer search result includes a reference source link and a search content;

[0053] The marketing delivery module is used to comprehensively analyze the user's personal setting information, third-party user portrait information, historical conversation information and intention, and current conversation context while the search module is searching, and summarize and infer the current user intention; based on the user conversation input and the current user intention, search and summarize the marketing delivery information in the marketing database to obtain the marketing delivery search result, which includes the delivery link, delivery content, delivery type, and delivery strategy;

[0054] The reference source generation module is used to comprehensively sort the reference sources of the answer search result and the marketing delivery search result based on the link weights of the answer search result and the marketing delivery search result, as well as the bidding price of the marketing delivery search result, and return the comprehensive sorting to the user as the reference source result; the comprehensive sorting includes:

[0055] (a1) Applicable to guiding traffic to news sites, that is, when users search for a piece of news, it can improve the ranking of links in similar news;

[0056] (a2) Applicable to official link protection and traffic diversion, based on official information protection, the latest marketing plan distribution, and methods, to ensure that users receive the latest official information;

[0057] (a3) Applicable to the competition among objects, lists or channels of the same category, and recommend similar products or services while answering user questions.

[0058] The answer result generation module is used to summarize and integrate the reference source results and the marketing delivery search results, obtain the answer results and return them to the user; the summary and integration are implemented based on the delivery strategy of the marketing delivery search results, and include:

[0059] (b1) Supplementary additional information based on intention speculation: that is, based on the current user intention speculation and the possible user service request intention, supplementary service function docking is provided;

[0060] (b2) Expansion and supplement of the official latest marketing plan;

[0061] (b3) Expansion and replacement of similar lists, competing products, channel information, and promotional information.

[0062] The recommendation-related question generation module is used to integrate the user request, the answer result, and the marketing search result, and also integrate the following contents:

[0063] (c1) The system guides service functions based on intention inference;

[0064] (c2) Guidance questions for official marketing plans;

[0065] (c3) Questions about similar lists, competing products, channel information, and promotional information;

[0066] The recommended related questions are then returned to the user, guiding the user to further engage in multiple rounds of dialogue.

[0067] Since the system introduced in the second embodiment of the present invention is a system used to implement the method of the first embodiment of the present invention, those skilled in the art can understand the specific structure and deformation of the device based on the method introduced in the first embodiment of the present invention, so it is not described here in detail. All devices used in the method of the first embodiment of the present invention belong to the scope of protection of the present invention.

[0068] The following are examples of application scenarios of the present invention:

[0069] User portraits include:

[0070] User personal information settings: mother of two children;

[0071] User tags: love life, love games;

[0072] The interaction process includes:

[0073] 1. Interaction between drug and test result inquiry

[0074] First round of interaction:

[0075] User session input: "Amoxicillin";

[0076] The large model platform (hereinafter referred to as the platform) parses user requests and retrieves answers; infers interaction intent, has no associated historical records, and defaults to scientific scenarios;

[0077] The platform returns the answer and information source "Amoxicillin is a semi-synthetic broad-spectrum β-lactam antibiotic, mainly used to treat various infections caused by sensitive bacteria. The following is some main information about amoxicillin. Mechanism of action: xxx, Indications: xxx, Adverse reactions: xxx, Precautions and suggestions: xxx";

[0078] Second round of interaction:

[0079] User session input: "Amoxicillin Clavulanate Potassium";

[0080] The platform parses user requests and retrieves answers; it infers interaction intent and historically queries amoxicillin and scientific scenarios;

[0081] The platform returns the answer and information source "Amoxicillin and clavulanate potassium is a compound preparation composed of two ingredients, amoxicillin and clavulanate potassium. It combines the advantages of the two drugs and expands the antibacterial spectrum xxx. Mechanism of action: xxx, Indications: xxx, Adverse reactions: xxx, Precautions and suggestions: xxx";

[0082] The third round of interaction:

[0083] User session input: "Children's test strip test, rhinovirus positive, prescription is amoxicillin clavulanate potassium"

[0084] The platform parses the user's request and retrieves the answer;

[0085] To infer the user's interaction intention, first obtain the following information:

[0086] “

[0087] Conversation history: Questions mainly revolved around the pharmacological properties of amoxicillin and its combination preparations, and

[0088] The reasons and precautions for using this drug in children with rhinovirus infection are expanded;

[0089] Possible intention: to fully understand the situation of these two antibiotics, as well as the rationality and precautions of using them in children with rhinovirus infection, so as to have a better understanding and grasp of the doctor's medication method;

[0090] Emotional response: reflects the concerns and doubts about drug use as a parent or patient, and the hope to obtain professional answers and guidance;

[0091] Platform strategy:

[0092] Show understanding and concern, express your understanding and attention to the user's concerns, and use a friendly and approachable tone to make the user feel your sincere concern. This helps to establish a good communication atmosphere.

[0093] Provide general information. You can provide some general information about the drug, such as indications, mechanism of action, common adverse reactions, etc.

[0094] Emphasize compliance with doctor's orders, and objectively point out that without confirmation from professionals, it is best to follow the doctor's professional judgment and orders to avoid interrupting or adjusting the medication method on your own.

[0095] Provide links to authoritative medical resources. Search engines can give priority to official websites or articles from authoritative medical institutions in the results, such as the Food and Drug Administration, Centers for Disease Control and Prevention, hospitals, etc. These resources can provide users with accurate and reliable drug information.

[0096] Online answers from professional doctors. Some medical consultation websites have online doctor duty services. Search engines can aggregate the answers from doctors on these websites to questions about the use of the drug and provide users with professional advice.

[0097] Provide the registration entrance of regular hospitals. If the user expresses the need for a follow-up or second consultation, provide the official registration entrance of a local large general hospital;

[0098] For online drug purchase services, if the drug requires a prescription, no online drug purchase channels are recommended because there are certain safety and legal risks. Users are advised to purchase such drugs at local regular offline pharmacies or hospital pharmacies.

[0099] ”

[0100] The platform returns the answer result and the citation source result "For children who test positive for rhinovirus, doctors prescribe amoxicillin and clavulanate potassium, which may be based on the following considerations:

[0101] Prevention of secondary bacterial infection: After rhinovirus infection, the body's defenses are reduced, and bacteria are more likely to cause concurrent infections, such as otitis media, pneumonia, etc. Amoxicillin and clavulanate potassium can effectively prevent and treat these bacterial infections.

[0102] Symptom relief: Although viral colds themselves do not require antibiotics, some bacterial complications (such as sinusitis) may make symptoms worse. Amoxicillin can treat these bacterial infections and provide symptom relief.

[0103] Condition assessment: Sometimes it is difficult for doctors to determine whether it is a pure viral infection or a bacterial infection. They will use preventive medication based on symptoms and make appropriate adjustments after observing the condition.

[0104] Child's condition: If the child has low immunity or other underlying diseases, the doctor will consider the prophylactic use of antibiotics to prevent bacterial complications.

[0105] However, some doctors believe that there is no need to overuse antibiotics for common viral colds in children. Therefore, parents can ask the doctor for the specific reasons for taking the medicine and take it strictly according to the doctor's orders. At the same time, they should also pay attention to symptomatic supportive treatment, such as regular diet and rest. If the symptoms do not improve or worsen, they should return to the doctor in time. "

[0106] At the same time, related questions are recommended, namely, supplementary return to online medical consultation, local medical registration or local over-the-counter drug purchase service entrance and question guidance.

[0107] 2. Popular game query interaction

[0108] User session input: "Recent popular game "Game Name 1""

[0109] The system searches the knowledge base and summarizes the answer retrieval result R1 as follows:

[0110] Link 1, "A very popular new game recently is "Game Name 1". Brief introduction... Judging from the user reputation and download volume, the response is very good";

[0111] Link 2, "Official website content of "Game Name 1" xxx";

[0112] Link 3, "Game Name 1 Player Community, Reviews and Guide xxx";

[0113] User intent identification: retrieve marketing information based on user portraits and user requests, and summarize marketing search results R2;

[0114] The system sorts the reference sources of the answer search result R1 and the marketing placement search result R2 based on the link weights and bidding prices of R1 and R2, and returns them to the user as the reference source result A1. The original R1 result may be affected by the R2 result, resulting in the following situations:

[0115] If R2 has information site traffic guidance marketing (similar content), link 1-1 replaces link 1, "The new game that is very popular recently is "Game Name 1", . Brief introduction...";

[0116] If there is an official marketing release, link 2 is the official latest release link;

[0117] If there are objects, lists or channels of the same category competing for traffic, the third record of R1 may be affected and ranked lower. When returned to user A1, it may become link 3-1, "《Game Name 1》Similar Product Introduction xxx List xxx";

[0118] After summarizing and integrating the reference source result A1 and the marketing delivery search result R2, the system obtains the answer result A2 and returns it to the user; the summarization and integration are implemented based on the R2 delivery strategy, including the following three types:

[0119] Additional information based on the system's intention inference: The system infers the user's intention and profiles

[0120] "Love games" may mean "understand and experience games". Based on the possible user service request intention, the answer content supplements "You can download or purchase the experience through the following legitimate channels: xxxx";

[0121] An expansion and supplement to the official latest marketing plan, which includes the latest game expansion pack or operation activity introduction in addition to the basic introduction of the original game;

[0122] Similar lists, competing products, channel information, and recommendation information are expanded and replaced, and the experience download link in the returned results is replaced with the "xxbao" application download link;

[0123] The system integrates the user request Q, the answer result A2, and the marketing search result R2. While returning the possible questions directly related to the reasoning, it can also integrate the following content and return it as a recommended related question A3 to guide the user to further multiple rounds of dialogue:

[0124] Service function guidance based on intention inference: Based on the intention inference and the request intent of "understanding and experiencing the game", the system provides additional service function docking interaction guidance questions such as "Download link of "Game Name 1", "Strategy of "Game Name 1", and "What is the player community of "Game Name 1"?";

[0125] Guidance questions for the official marketing plan: "Download the latest expansion pack activity experience of "Game Name 1""

[0126] Questions guiding similar rankings, competing products, channel information, and promotional information: "Game Name 1's type and the same category MMO rankings", "Game Name 1's competitor Game Name 2's reputation and experience".

[0127] Although the specific implementation modes of the present invention are described above, those skilled in the art should understand that the specific implementation modes described are only illustrative and are not intended to limit the scope of the present invention. Equivalent modifications and changes made by those skilled in the art in accordance with the spirit of the present invention should be included in the scope of protection of the claims of the present invention.

Claims

1. A large model interaction method, characterized in that: The steps include: S1. Obtain user session input and parse the user session input to obtain a user request; S2. Search and summarize the user request to obtain answer search results, which include reference source links and search content; At the same time, it comprehensively analyzes the user's personal settings information, third-party user portrait information, historical conversation information and intentions, and the current conversation context, and summarizes and infers the current user's intentions; Based on the user session input and the current user intention, the marketing delivery information is retrieved and summarized in the marketing database to obtain a marketing delivery retrieval result, wherein the marketing delivery retrieval result includes a delivery link, delivery content, delivery type, and delivery strategy; S3, comprehensively sorting the reference sources of the answer search result and the marketing delivery search result based on the link weights of the answer search result and the marketing delivery search result, and returning the results to the user as reference source results; S4, after summarizing and integrating the reference source results and the marketing placement search results, an answer result is obtained and returned to the user; S5. Integrate the user request, the answer result, and the marketing search result, obtain recommended related questions, and return them to the user to guide the user to further conduct multiple rounds of dialogue.

2. A large model interaction method according to claim 1, characterized in that: The comprehensive ranking in S3 includes: (a1) Applicable to guiding traffic to news sites, that is, when users search for a certain piece of news, it can improve the ranking of links in similar news; (a2) Applicable to official link protection and traffic diversion, based on official information protection, the latest marketing plan distribution, and methods, to ensure that users receive the latest official information; (a3) Applicable to the competition among objects, lists or channels of the same category, and to recommend similar products or services while answering user questions.

3. A large model interaction method according to claim 1, characterized in that: The summarization and integration of S4 is achieved based on the delivery strategy of the marketing delivery search results, and includes: (b1) Supplementary additional information based on intention speculation: that is, based on the current user intention speculation and the possible user service request intention, supplementary service function docking is provided; (b2) Expansion and supplement of the official latest marketing plan; (b3) Expansion and replacement of similar lists, competing products, channel information, and promotional information.

4. A large model interaction method according to claim 1, characterized in that: In S5, the recommendation association question also integrates the following contents: (c1) The system guides service functions based on intention inference; (c2) Guidance questions for official marketing plans; (c3) Questions regarding similar rankings, competing products, channel information, and promotional information.

5. A large model interactive system, characterized by: include: The session parsing module is used to obtain user session input and parse the user session input to obtain user requests; A retrieval module, used to search and summarize the user request to obtain an answer search result, wherein the answer search result includes a reference source link and a search content; The marketing delivery module is used to comprehensively analyze the user's personal setting information, third-party user portrait information, historical conversation information and intentions, and current conversation context while the search module is searching, and summarize and infer the current user's intentions; Based on the user session input and the current user intention, the marketing delivery information is retrieved and summarized in the marketing database to obtain a marketing delivery retrieval result, wherein the marketing delivery retrieval result includes a delivery link, delivery content, delivery type, and delivery strategy; A reference source generation module is used to comprehensively sort the reference sources of the answer search result and the marketing delivery search result based on the link weights of the answer search result and the marketing delivery search result, as well as the bidding price of the marketing delivery search result, and return the results as reference source results to the user; An answer result generating module is used to summarize and integrate the reference source results and the marketing delivery search results, obtain the answer result and return it to the user; The recommended related question generation module is used to integrate the user request, the answer result, and the marketing search result, and return the recommended related questions to the user to guide the user to further conduct multiple rounds of dialogue.

6. A large model interactive system according to claim 5, characterized in that: The comprehensive ranking in the citation source generation module includes: (a1) Applicable to guiding traffic to news sites, that is, when users search for a certain piece of news, it can improve the ranking of links in similar news; (a2) Applicable to official link protection and traffic diversion, based on official information protection, the latest marketing plan distribution, and methods, to ensure that users receive the latest official information; (a3) Applicable to the competition among objects, lists or channels of the same category, and to recommend similar products or services while answering user questions.

7. A large model interactive system according to claim 5, characterized in that: The summarization and integration of the answer result generation module is implemented based on the delivery strategy of the marketing delivery search results, and includes: (b1) Supplementary additional information based on intention speculation: that is, based on the current user intention speculation and the possible user service request intention, supplementary service function docking is provided; (b2) Expansion and supplement of the official latest marketing plan; (b3) Expansion and replacement of similar lists, competing products, channel information, and promotional information.

8. A large model interactive system according to claim 5, characterized in that: When integrating the user request, the answer result, and the marketing search result, the recommendation-related question generation module also integrates the following contents: (c1) The system guides service functions based on intention inference; (c2) Guidance questions for official marketing plans; (c3) Questions regarding similar rankings, competing products, channel information, and promotional information.

Images