Digital human interaction management system based on big data analysis

Abstract

The invention belongs to the field of digital human interaction management, relates to a data analysis technology, is used for solving the problem that the multi-round interaction state of a digital human cannot be monitored and analyzed in the prior art, and particularly relates to a digital human interaction management system based on big data analysis. Comprising a voice interaction support module, a multi-round dialogue supervision module and an effectiveness optimization analysis module which are connected in sequence, the voice interaction support module is used for identifying voice information received by the digital human, converting the voice information into text information, inputting the text information into the general large model, calling a corresponding output instruction and sending the output instruction to the execution module; according to the method, reasonable logic extension and supplementary answering can be performed according to the questions of the user, the interaction history and intention information of the user in multiple rounds of dialogues can be effectively memorized, the dialogue context association model is established, and it is ensured that the platform can accurately understand the evolution and progression of the intention of the user in the multiple rounds of dialogues.

Description

Technical Field

[0001] The present invention belongs to the field of digital human interaction management, relates to data analysis technology, and specifically is a digital human interaction management system based on big data analysis. Background Art

[0002] A digital human is a digital human image created by using digital technology and similar to a human image. Generally speaking, a digital human refers to the penetration of digital technology at all levels and stages of human anatomy, physics, physiology, and intelligence; Narrowly speaking, a digital human is the product of the integration of information science and life science, and uses the methods of information science to perform virtual simulation on the morphology and function of the human body at different levels.

[0003] The invention patent with the publication number CN118708702A discloses a digital human interaction management system based on artificial intelligence. This management system converts the obtained dialogue information into digital information and transmits the digital information to the interactive information pre-storage module; It avoids bypassing the privacy word shielding by replacing keywords, thereby obtaining the privacy data of different users; However, this management system cannot monitor and analyze the multi-round interaction status of digital humans, resulting in the inability to automatically identify and optimize repetitive conversations in multi-round interactions, affecting the user experience.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the Invention

[0005] The purpose of the present invention is to provide a digital human interaction management system based on big data analysis, which is used to solve the problem that the prior art cannot monitor and analyze the multi-round interaction status of digital humans;

[0006] The technical problem that the present invention needs to solve is: how to provide a digital human interaction management system based on big data analysis that can monitor and analyze the multi-round interaction status of digital humans.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A digital human interaction management system based on big data analysis includes a voice interaction support module, a multi-round dialogue supervision module, and an effectiveness optimization analysis module that are connected in sequence;

[0009] The voice interaction support module is used to identify the voice information received by the digital human and convert it into text information, input the text information into a general large model and retrieve the corresponding output instruction, and send the output instruction to the execution module;

[0010] The multi-round dialogue supervision module is used to conduct validity supervision and analysis on the multi-round dialogue between the digital human and the user: generate a supervision cycle, mark the multi-round dialogue process between the digital human and the user within the supervision cycle as the supervision process, extract all the voice information extracted by the user during the supervision process, extract the basic parameters of the voice information, and the basic parameters include information type, information field, and keyword set; mark the voice information with exactly the same information type, information field, and keyword set during the supervision process as associated information, and mark the supervision process as a repeated process or a related process through the associated information; mark the ratio of the number of repeated processes within the supervision cycle to the number of supervision processes as the repetition coefficient of the supervision cycle, and determine whether the validity of the multi-round dialogue of the digital human within the supervision cycle meets the requirements through the repetition coefficient;

[0011] The validity optimization analysis module is used to conduct validity optimization analysis on the multi-round dialogue between the digital human and the user.

[0012] Furthermore, the output instructions include an execution signal and a question-and-answer signal; the execution signal includes a limb execution electrical signal corresponding to the text information, and the question-and-answer signal includes a voice broadcast electrical signal corresponding to the text information; after receiving the execution signal, the execution module performs limb control according to the execution signal, and after receiving the question-and-answer signal, the execution module performs voice broadcast control according to the question-and-answer signal.

[0013] Furthermore, the specific process of marking the supervision process as a repeated process or a related process includes: determining whether the output instructions retrieved from the general large model through the associated information are the same. If so, mark the supervision process as a repeated process; if not, mark the supervision process as a related process.

[0014] Furthermore, the specific process of determining whether the validity of the multi-round dialogue of the digital human within the supervision cycle meets the requirements includes comparing the repetition coefficient with a preset repetition threshold: if the repetition coefficient is greater than or equal to the repetition threshold, it is determined that the validity of the multi-round dialogue of the digital human within the supervision cycle does not meet the requirements, generate a validity optimization analysis signal and send the validity optimization analysis signal to the validity optimization analysis module; if the repetition coefficient is less than the repetition threshold, it is determined that the validity of the multi-round dialogue of the digital human within the supervision cycle meets the requirements, and conduct a comprehensive analysis of the supervision cycle.

[0015] Further, the specific process of comprehensively analyzing the supervision cycle includes: marking the number of dialogue turns in the relevant process as a continuous value, marking the relevant process with a continuous value not less than the preset continuous threshold as a comprehensive optimization process, marking the number of comprehensive optimization processes as a comprehensive optimization value, and comparing the comprehensive optimization value with the preset comprehensive optimization threshold: if the comprehensive optimization value is less than the comprehensive optimization threshold, it is determined that the multi-round dialogue of the digital human within the supervision cycle does not have the comprehensive optimization feature; if the comprehensive optimization value is greater than or equal to the comprehensive optimization threshold, it is determined that the multi-round dialogue of the digital human within the supervision cycle has the comprehensive optimization feature. The type set, field set, and key set are respectively composed of the information types, information fields, and all keywords within the keyword set of all comprehensive optimization processes. The comprehensive optimization data set is composed of the information type, information field, and the information type, information field, and keyword with the most corresponding elements within the keyword set. A comprehensive optimization signal is generated and the comprehensive optimization signal and the comprehensive optimization data set are sent to the mobile terminal of the management personnel.

[0016] Further, the effectiveness optimization analysis module is used to perform effectiveness optimization analysis on the multi-round dialogue between the digital human and the user: marking the repeated process corresponding to the output instruction within the supervision cycle as the concentration value of the output instruction, calculating the variance of the concentration values of all output instructions to obtain the concentration coefficient, and marking the effectiveness optimization measures for the supervision cycle through the concentration coefficient.

[0017] Further, the specific process of marking the effectiveness optimization measures for the supervision cycle includes: comparing the concentration coefficient with the preset concentration threshold: if the concentration coefficient is less than the concentration threshold, marking the effectiveness optimization measures for the supervision cycle as speech recognition optimization, generating a speech recognition optimization signal and sending the speech recognition optimization signal to the mobile terminal of the management personnel; if the concentration coefficient is greater than or equal to the concentration threshold, marking the effectiveness optimization measures for the supervision cycle as information integration optimization, marking the text information corresponding to the K1 repeated processes with the largest concentration value as the integration optimization object, generating an information integration optimization signal and sending the information integration optimization signal and the integration optimization object to the mobile terminal of the management personnel.

[0018] Further, the voice interaction support module is communicatively connected to the general large model, and the general large model is generated by the large model integration module. The large model integration module is used to generate the general large model, the FAQ based on the knowledge base document, design the multi-round dialogue management logic, and construct the dialogue instruction intention recognition model.

[0019] The present invention has the following beneficial effects:

[0020] 1. Integrate a general large model through a large model integration module, make reasonable logical extensions and supplementary answers according to the user's follow-up questions, effectively remember the interaction history and intention information of the user in multi-round conversations, establish a dialogue context association model, and ensure that during multi-round conversations, the platform can accurately understand the evolution and progression of the user's intentions;

[0021] 2. Through the voice interaction support module, the voice information received by the digital human can be recognized and converted into text information, and the corresponding output instructions can be directly retrieved in combination with the general large model to control the digital human. The output instructions include various types and support multi-modal control of the digital human;

[0022] 3. Through the multi-round conversation supervision module, the effectiveness supervision and analysis of the multi-round conversations between the digital human and the user can be carried out. Differentiated markings are made on the supervision process according to the basic parameters of the voice information, and the effectiveness of the multi-round conversations of the digital human within the supervision period is evaluated based on the proportion of the marked quantity in the repeated process;

[0023] 4. Through the effectiveness optimization analysis module, the effectiveness optimization analysis of the multi-round conversations between the digital human and the user can be carried out. The concentration coefficient is obtained through comprehensive calculation based on the number of corresponding repeated processes of the output instructions, and then the effectiveness optimization measures for the supervision period are marked through the concentration coefficient to improve the effectiveness optimization efficiency of the digital human's multi-round conversations. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0025] Figure 1 It is the system block diagram of Embodiment 1 of the present invention;

[0026] Figure 2 It is the method flow chart of Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] The following will clearly and completely describe the technical solutions of the present invention in combination with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0028] Embodiment 1: As Figure 1As shown in the figure, a digital human interaction management system based on big data analysis includes a voice interaction support module, a multi-turn dialogue supervision module, and an effectiveness optimization analysis module that are connected in sequence. The voice interaction support module is communicatively connected to a general large model, and the general large model is generated by a large model integration module.

[0029] The large model integration module is used to integrate the general large model to ensure that the platform can intelligently understand and accurately answer a wide range of questions raised by users, covering common fields such as history, science and technology, culture, business, and life, and can make reasonable logical extensions and supplementary answers according to user follow-up questions;

[0030] FAQ generation based on knowledge base documents: It can automatically identify and extract key information, core concepts, and common questions in the knowledge base documents provided by customers, and automatically generate a structured dialogue FAQ list based on this content. The coverage rate of FAQ generation should reach more than 80% of the effective information in the document, and the answer to each FAQ is concise and clear, with an average word count controlled between 100-300 words, making it easy for users to understand and interact;

[0031] Design a perfect multi-turn dialogue management logic that can effectively remember the interaction history and intention information of users in multi-turn dialogues, establish a dialogue context association model, and ensure that during multi-turn dialogues, the platform can accurately understand the evolution and progression of user intentions, avoiding topic deviation or repeated answers;

[0032] Build a high-precision dialogue instruction intention recognition model that can quickly and accurately extract instruction intentions from user dialogue texts, such as opening a specific website (such as an official website), playing a specific video (such as an enterprise introduction video), querying specific data (such as the company's operation data for the previous year), etc., and the intention recognition accuracy rate reaches more than 90%;

[0033] Develop a complete front-end software development kit (SDK), encapsulate the core function interfaces of digital human interaction, speech recognition, large model dialogue, etc., to facilitate customers to quickly integrate the functions of this system into their own applications or websites. At the same time, provide detailed interface description documents, including interface function descriptions, parameter descriptions, return value descriptions, sample codes, etc., to ensure that customer developers can easily understand and use the SDK for integration development work;

[0034] Functions such as the business knowledge Q&A platform and large model capability call in the digital human system need to provide interfaces for the company's OA system or other systems to call. The interface forms include but are not limited to: WEB integration, JS embedding, WeChat official account, API interface, etc. This function call is not restricted by the number of users, and the usage permissions of OA system or other system users should be connected to the permission management module of the digital human system to realize different application scenarios based on different role permissions.

[0035] For the identified instruction intent, the platform can generate and send corresponding instructions or remarks to relevant systems (such as BI system or digital human display system) within 500 milliseconds to ensure the timeliness and accuracy of instruction execution; make reasonable logical extensions and supplementary answers according to the user's follow-up questions, and effectively remember the interaction history and intent information of the user in multi-round conversations, establish a dialogue context association model, and ensure that during multi-round conversations, the platform can accurately understand the evolution and progression of the user's intent.

[0036] The voice interaction support module is used to recognize the voice information received by the digital human and convert it into text information, input the text information into the general large model and retrieve the corresponding output instructions. The output instructions include execution signals and Q&A signals; the execution signals include limb execution electrical signals corresponding to the text information, and the Q&A signals include voice broadcast electrical signals corresponding to the text information; send the output instructions to the execution module. After receiving the execution signal, the execution module performs limb control according to the execution signal. After receiving the Q&A signal, the execution module performs voice broadcast control according to the Q&A signal; directly retrieve the corresponding output instructions from the general large model to control the digital human. The output instructions include various types and support multi-modal control of the digital human.

[0037] The multi-round conversation supervision module is used to conduct effectiveness supervision and analysis on the multi-round conversations between the digital human and the user: generate a supervision cycle, mark the multi-round conversation process between the digital human and the user within the supervision cycle as the supervision process, extract all the voice information extracted by the user during the supervision process, and extract the basic parameters of the voice information. The basic parameters include information type, information field, and keyword set;

[0038] Mark the voice information with exactly the same information type, information field, and keyword set during the supervision process as associated information, and determine whether the output instructions retrieved from the general large model through the associated information are the same. If so: mark the supervision process as a repeated process; if not, mark the supervision process as a relevant process; mark the ratio of the number of repeated processes to the number of supervision processes within the supervision cycle as the repetition coefficient of the supervision cycle, and compare the repetition coefficient with the preset repetition threshold:

[0039] If the repetition coefficient is greater than or equal to the repetition threshold, it is determined that the effectiveness of the multi-round conversations of the digital human within the supervision cycle does not meet the requirements, generate an effectiveness optimization analysis signal and send the effectiveness optimization analysis signal to the effectiveness optimization analysis module;

[0040] If the repetition coefficient is less than the repetition threshold, it is determined that the validity of the multi-round conversation of the digital human within the supervision period meets the requirements, and a comprehensive analysis of the supervision period is carried out: the number of conversation rounds in the relevant process is marked as a continuous value, the relevant process with a continuous value not less than the preset continuous threshold is marked as a comprehensive optimization process, the number of comprehensive optimization processes is marked as the comprehensive optimization value, and the comprehensive optimization value is compared with the preset comprehensive optimization threshold:

[0041] If the comprehensive optimization value is less than the comprehensive optimization threshold, it is determined that the multi-round conversation of the digital human within the supervision period does not have the comprehensive optimization feature;

[0042] If the comprehensive optimization value is greater than or equal to the comprehensive optimization threshold, it is determined that the multi-round conversation of the digital human within the supervision period has the comprehensive optimization feature. The type set, domain set, and key set are respectively composed of the information types, information fields, and all keywords within the keyword set of all comprehensive optimization processes. The comprehensive optimization data set is composed of the information type, information field, and the information type, information field, and keyword with the most corresponding elements within the keyword set. A comprehensive optimization signal is generated and the comprehensive optimization signal and the comprehensive optimization data set are sent to the mobile terminal of the management personnel; a validity supervision analysis is carried out on the multi-round conversation between the digital human and the user, the supervision process is differentially marked according to the basic parameters of the voice information, and the validity of the multi-round conversation of the digital human within the supervision period is evaluated through the ratio of the marked quantity of the repetition process.

[0043] The validity optimization analysis module is used to perform validity optimization analysis on the multi-round conversation between the digital human and the user: the repetition process corresponding to the output instruction within the supervision period is marked as the concentrated value of the output instruction, the variance of the concentrated values of all output instructions is calculated to obtain the concentration coefficient, and the concentration coefficient is compared with the preset concentration threshold:

[0044] If the concentration coefficient is less than the concentration threshold, the validity optimization measure for the supervision period is marked as voice recognition optimization, a voice recognition optimization signal is generated and the voice recognition optimization signal is sent to the mobile terminal of the management personnel;

[0045] If the concentration coefficient is greater than or equal to the concentration threshold, the validity optimization measure for the supervision period is marked as information integration optimization, the text information corresponding to the K1 repetition processes with the largest concentrated value is marked as the integration optimization object, an information integration optimization signal is generated and the information integration optimization signal and the integration optimization object are sent to the mobile terminal of the management personnel; a validity optimization analysis is carried out on the multi-round conversation between the digital human and the user, the concentration coefficient is obtained through comprehensive calculation according to the number of repetition processes corresponding to the output instruction, and then the validity optimization measure for the supervision period is marked through the concentration coefficient, improving the validity optimization efficiency of the multi-round conversation of the digital human.

[0046] Embodiment 2: As Figure 2As shown in the figure, a digital human interaction management method based on big data analysis includes the following steps:

[0047] Step 1: Generate a general large model, FAQs based on knowledge base documents, design a perfect multi-round dialogue management logic, and build a high-precision dialogue instruction intention recognition model;

[0048] Step 2: Identify the voice information received by the digital human and convert it into text information, input the text information into the general large model and retrieve the corresponding output instructions, and send the output instructions to the execution module;

[0049] Step 3: Conduct an effectiveness supervision and analysis of the multi-round dialogue between the digital human and the user: Generate a supervision cycle, mark the multi-round dialogue process between the digital human and the user within the supervision cycle as the supervision process, and mark the supervision process as a relevant process or a repeated process;

[0050] Step 4: Mark the ratio of the number of repeated processes within the supervision cycle to the number of supervision processes as the repetition coefficient of the supervision cycle, and determine whether the effectiveness of the multi-round dialogue of the digital human within the supervision cycle meets the requirements through the repetition coefficient;

[0051] Step 5: Conduct an effectiveness optimization analysis of the multi-round dialogue between the digital human and the user: Mark the repeated process corresponding to the output instruction within the supervision cycle as the concentration value of the output instruction, calculate the variance of the concentration values of all output instructions to obtain the concentration coefficient, and mark the effectiveness optimization measures of the supervision cycle through the concentration coefficient.

[0052] A digital human interaction management system based on big data analysis, when working, generates a general large model, FAQs based on knowledge base documents, designs a perfect multi-round dialogue management logic, and builds a high-precision dialogue instruction intention recognition model;

[0053] Step 2: Identify the voice information received by the digital human and convert it into text information, input the text information into the general large model and retrieve the corresponding output instructions, and send the output instructions to the execution module; Generate a supervision cycle, mark the multi-round dialogue process between the digital human and the user within the supervision cycle as the supervision process, and mark the supervision process as a relevant process or a repeated process; Mark the ratio of the number of repeated processes within the supervision cycle to the number of supervision processes as the repetition coefficient of the supervision cycle, and determine whether the effectiveness of the multi-round dialogue of the digital human within the supervision cycle meets the requirements through the repetition coefficient; Mark the repeated process corresponding to the output instruction within the supervision cycle as the concentration value of the output instruction, calculate the variance of the concentration values of all output instructions to obtain the concentration coefficient, and mark the effectiveness optimization measures of the supervision cycle through the concentration coefficient.

[0054] The above content is only an example and explanation of the structure of the present invention. Those skilled in the art of this technology can make various modifications, supplements, or use similar methods to replace the specific embodiments described, as long as they do not deviate from the structure of the invention or exceed the scope defined by this claim book, they shall fall within the protection scope of the present invention.

[0055] In the description of this specification, the description referring to terms such as "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0056] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the present invention to only the specific implementation manners. Obviously, according to the content of this specification, many modifications and variations can be made. This specification selects and specifically describes these embodiments to better explain the principle and practical application of the present invention, so that those skilled in the art of this technology can well understand and utilize the present invention. The present invention is only limited by the claim book and its full scope and equivalents.

Claims

1. A digital human interaction management system based on big data analysis, characterized in that: It includes a voice interaction support module, a multi-round dialogue supervision module, and an effectiveness optimization analysis module connected in sequence; The voice interaction support module recognizes the voice information received by the digital human and converts it into text information, inputs the text information into the universal large model and retrieves the corresponding output instructions, and sends the output instructions to the execution module; The multi-round dialogue supervision module generates a supervision cycle, marks the multi-round dialogue program between the digital human and the user within the supervision cycle as a supervision process, extracts all voice information extracted by the user during the supervision process, and extracts basic parameters of the voice information, including information type, information field, and keyword set; marks voice information with exactly the same information type, information field, and keyword set in the supervision process as associated information, and marks the supervision process as a repeated process or a related process through the associated information; marks the ratio of the number of repeated processes to the number of supervision processes within the supervision cycle as the repetition coefficient of the supervision cycle, and determines whether the effectiveness of the multi-round dialogue of the digital human within the supervision cycle meets the requirements through the repetition coefficient; The effectiveness optimization analysis module performs effectiveness optimization analysis on multiple rounds of dialogues between the digital human and the user.

2. According to claim 1, a digital human interaction management system based on big data analysis is characterized in that: The output instructions include execution signals and question-and-answer signals; the execution signals include physical execution electrical signals corresponding to the text information, and the question-and-answer signals include voice broadcast electrical signals corresponding to the text information; after receiving the execution signals, the execution module performs physical control according to the execution signals, and after receiving the question-and-answer signals, the execution module performs voice broadcast control according to the question-and-answer signals.

3. A digital human interaction management system based on big data analysis according to claim 2, characterized in that: The specific process of marking the supervision process as a repeated process or a related process includes: determining whether the output instructions retrieved from the general large model through the associated information are the same, if so: marking the supervision process as a repeated process; if not, marking the supervision process as a related process.

4. A digital human interaction management system based on big data analysis according to claim 3, characterized in that: The specific process of determining whether the effectiveness of the multi-round dialogue of the digital person within the supervision cycle meets the requirements includes comparing the repetition coefficient with the preset repetition threshold: if the repetition coefficient is greater than or equal to the repetition threshold, it is determined that the effectiveness of the multi-round dialogue of the digital person within the supervision cycle does not meet the requirements, generating an effectiveness optimization analysis signal and sending the effectiveness optimization analysis signal to the effectiveness optimization analysis module; If the repetition coefficient is less than the repetition threshold, it is determined that the effectiveness of the digital human's multiple rounds of dialogue within the supervision cycle meets the requirements, and a comprehensive analysis of the supervision cycle is conducted.

5. The digital human interaction management system based on big data analysis according to claim 4 is characterized in that: The specific process of conducting a comprehensive analysis of the supervision cycle includes: marking the number of conversation rounds of the relevant process as a continuous value, marking the relevant process whose continuous value is not less than the preset continuous threshold as a comprehensive optimization process, marking the number of comprehensive optimization processes as the comprehensive optimization value, and comparing the comprehensive optimization value with the preset comprehensive optimization threshold: if the comprehensive optimization value is less than the comprehensive optimization threshold, then it is determined that the multiple rounds of conversations of the digital person within the supervision cycle do not have the comprehensive optimization feature; if the comprehensive optimization value is greater than or equal to the comprehensive optimization threshold, then it is determined that the multiple rounds of conversations of the digital person within the supervision cycle have the comprehensive optimization feature, and the information types, information fields and all keywords in the keyword set of all comprehensive optimization processes constitute a type set, a field set and a key set respectively, and the information type, information field and keyword with the most corresponding elements in the information type, information field and keyword set constitute a comprehensive optimization data set, generate a comprehensive optimization signal and send the comprehensive optimization signal and the comprehensive optimization data set to the mobile phone terminal of the manager.

6. The digital human interaction management system based on big data analysis according to claim 5 is characterized in that: The effectiveness optimization analysis module is used to perform effectiveness optimization analysis on multiple rounds of dialogues between digital humans and users: the repeated processes corresponding to the output instructions within the supervision cycle are marked as the concentrated values ​​of the output instructions, the variance of the concentrated values ​​of all output instructions is calculated to obtain the concentration coefficient, and the effectiveness optimization measures of the supervision cycle are marked by the concentration coefficient.

7. The digital human interaction management system based on big data analysis according to claim 6 is characterized in that: The specific process of marking the effectiveness optimization measures of the supervision cycle includes: comparing the concentration coefficient with the preset concentration threshold: if the concentration coefficient is less than the concentration threshold, the effectiveness optimization measures of the supervision cycle are marked as voice recognition optimization, a voice recognition optimization signal is generated and the voice recognition optimization signal is sent to the mobile phone terminal of the manager; if the concentration coefficient is greater than or equal to the concentration threshold, the effectiveness optimization measures of the supervision cycle are marked as information integration optimization, the text information corresponding to the K1 repeated processes with the largest concentration value is marked as an integration optimization object, an information integration optimization signal is generated and the information integration optimization signal and the integration optimization object are sent to the mobile phone terminal of the manager.

8. The digital human interaction management system based on big data analysis according to claim 7 is characterized in that: The voice interaction support module is communicated with the general big model, and the general big model is generated by the big model integration module. The big model integration module is used to generate the general big model, FAQ based on knowledge base documents, design multi-round dialogue management logic, and build a dialogue instruction intention recognition model.

Images