Intelligent customer service information retrieval method and system based on large model

Abstract

The application belongs to the technical field of semantic retrieval, and particularly relates to an intelligent customer service information retrieval method and system based on a large model. The method retrieves and judges a standard semantic question and answer information library of a difference hierarchical index tree of each subject node in a distributed isolated mapping security chain by obtaining a user retrieval semantic association vector, combining a preset standard key entity mapping table and a three-level index mapping table, and returning the retrieved standard question and answer information in key entity frequency order. When the retrieval semantic contains a reservation demand, a distributed reservation decision tree and standard question and answer information are used to generate a cross-system reservation parameter set, a bidirectional mapping dictionary and a matching recommendation algorithm are used to output recommended reservation information, and the bidirectional mapping dictionary and the retrieval index information are dynamically updated through a real-time collection of a consistency frequency ratio of the recommended and real reservation, so as to effectively improve the semantic retrieval precision and the cross-system reservation accuracy.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of semantic retrieval, and particularly relates to an intelligent customer service information retrieval method and system based on a large model. BACKGROUND

[0002] In the field of medical intelligent customer service, with the development of smart medical care, users have an increasing demand for personalized and accurate services, but traditional systems have technical bottlenecks. On the one hand, medical knowledge has strong hospital individualization characteristics, and there are obvious differences in department names and diagnosis and treatment processes among different hospitals. However, the traditional system lacks a dynamic adaptive knowledge base management mechanism, and it is difficult to flexibly maintain the individualized data of different hospitals. On the other hand, when the intelligent customer service is connected with the appointment registration system, the data mapping accuracy is insufficient, resulting in a cumbersome jump process from the user's query to the registration, and poor accuracy of department association. At the same time, the traditional retrieval algorithm cannot effectively handle the semantic ambiguity problems such as synonyms, polysemes and different expressions of different departments in the medical field, resulting in low semantic retrieval accuracy and insufficient answer accuracy. These problems collectively reflect the technical defects of traditional systems in individualized knowledge base management, accurate mapping across systems and medical semantic understanding, which affects the application effect of the medical intelligent customer service system. SUMMARY

[0003] In view of the deficiencies of the prior art, the present application provides an intelligent customer service information retrieval method and system based on a large model. The method retrieves and judges the difference classification index tree standard semantic question and answer information database of each subject node in the distributed isolated mapping security chain by obtaining the user retrieval semantic association vector, combining the preset standard key entity mapping table and the three-level index mapping table, and returns the retrieved standard question and answer information in the order of key entity frequency. When no information is retrieved, the answer is generated by using the pre-trained reasoning generation model in combination with the information database. When the retrieval semantics contains an appointment requirement, the distributed appointment decision tree and the standard question and answer information are used to generate a cross-system appointment parameter set, and the recommended appointment information is output by using a bidirectional mapping dictionary and a matching recommendation algorithm. The consistency frequency ratio of real-time collection of recommendations and real appointments is used to dynamically update the bidirectional mapping dictionary and the retrieval index information, effectively improving the semantic retrieval accuracy and the cross-system appointment accuracy.

[0004] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0005] The intelligent customer service information retrieval method based on a large model comprises the following steps:

[0006] In response to the user retrieval information, the user retrieval semantic association vector and the context association vector are obtained.

[0007] based on the search semantic association vector and the context association vector, combining a preset standard key entity mapping table and a three-level index mapping table built in a distributed isolation mapping security chain, performing standard question and answer search information retrieval judgment on a hierarchical index tree standard semantic question and answer information library configured for each subject node of the distributed isolation mapping security chain;

[0008] If the search is successful, the standard question and answer search information retrieved is returned according to the frequency priority of the search key entity in the search semantic association vector;

[0009] If the search is unsuccessful, according to the user search semantic association vector, through a pre-trained inference generation model combining a hierarchical index tree standard semantic question and answer information library, a question and answer search information sequence and a corresponding evaluation score are generated, and the information with the maximum evaluation score among all generated question and answer search information is fed back to the corresponding user.

[0010] Specifically, the intelligent customer service information retrieval method based on a large model further comprises:

[0011] When the search semantic association vector contains a reservation requirement, according to the user reservation requirement, through a distributed reservation decision tree corresponding to each subject node in the distributed isolation mapping security chain, cross-system reservation matching is performed on the standard question and answer search information, and a cross-system reservation parameter set is obtained;

[0012] Based on the cross-system reservation parameter set, through a preset cross-system bidirectional mapping dictionary combining a matching recommendation algorithm, recommended reservation information is obtained;

[0013] The frequency of reservation and the frequency of real reservation of the corresponding user according to the recommended reservation information are collected in real time, and a reservation consistency frequency ratio is obtained. If the consistency frequency ratio is less than a preset reservation consistency threshold, then according to the real-time reservation information parameters, the recommended mapping information in the bidirectional mapping dictionary and the retrieval index information in the three-level index mapping table are constructed and updated until the reservation consistency threshold is met.

[0014] Specifically, the construction process of the standard key entity mapping table further comprises:

[0015] Obtain the historical text record information and the field standardized text information corresponding to each type of subject containing all sub-subjects, and perform word segmentation preprocessing through a pre-trained professional word segmentation model to obtain the text information space and the field standard text information space corresponding to all sub-subjects under each subject;

[0016] Based on the text information space and the field standard text information space corresponding to all sub-subjects under each subject, through an entity relationship extraction algorithm, obtain the exclusive label key entity vector and the general label key entity vector corresponding to each sub-subject;

[0017] With each general label key entity vector as the cluster center, the clustering distance between each cluster center and all exclusive label key entity vectors is obtained through the cosine formula;

[0018] Based on all the clustering distances corresponding to each cluster center, the truncated distance corresponding to each cluster center is determined, and all the truncated distances corresponding to each cluster center and the clustering distance are input into the DBSCAN algorithm to obtain the exclusive label clustering mapping table corresponding to each general label; the exclusive label clustering mapping table includes the general label and the exclusive label sequence under the corresponding different sub-subjects.

[0019] Specifically, the construction process of the standard key entity mapping table further includes:

[0020] Based on the exclusive label clustering mapping table corresponding to all general labels and the domain standard text information space, the causal correlation degree between different exclusive labels under different general labels is obtained through a causal correlation analysis model;

[0021] Based on the causal correlation degree between different exclusive labels under different general labels, a bidirectional mapping connection between the general label key entity and the corresponding exclusive label key entity is constructed, and based on the bidirectional mapping connection and the exclusive label clustering mapping table corresponding to each general label, a standard key entity mapping table is obtained;

[0022] Real-time collection of historical text record information corresponding to all sub-subjects corresponding to each type of subject and revised domain standardized text information, repeating the construction process of the exclusive label clustering mapping table corresponding to each general label and the bidirectional mapping connection, and updating the standard key entity mapping table through an incremental update model combined with the real-time collected information.

[0023] Specifically, the construction process of the distributed isolated mapping security chain includes:

[0024] Based on the domain information in the domain standardized text information, a root node is constructed, and based on the domain standardized text information, a knowledge graph and a graph embedding algorithm are combined to obtain a domain classification tree and embed the domain classification tree into the root node;

[0025] Based on the subject, a first-level node is constructed, and based on the sub-subject, a second-level node is constructed, and the text information space, historical question and answer information and configured standard reply information corresponding to each sub-subject are combined with a tree database to construct a third-level difference database node;

[0026] Based on the domain type corresponding to each subject, a clustering algorithm is used to obtain a similar subject cluster, and based on the domain type corresponding to the similar subject cluster, a first-level index connection between each root node and the first-level node in the similar subject cluster is constructed.

[0027] Specifically, the construction process of the distributed isolated mapping security chain also includes:

[0028] According to the clustering similarity between the primary nodes in the similar subject clustering cluster, cross-subject connections are constructed, and the information security protection level, subject label code and historical cross-subject search access permission information between subjects are combined, and based on the hash algorithm and the encryption permission control algorithm, a hierarchical encryption permission hash mapping sequence is obtained, and the hierarchical private key permission hash mapping sequence in the hierarchical encryption permission hash mapping sequence is mapped to the cross-subject connection between the corresponding subjects, and a cross-subject security mapping connection sequence is obtained;

[0029] Based on the information of all secondary nodes corresponding to each primary node and the subfield type information of the function information corresponding to each secondary node, a secondary index connection is constructed, and through the function information corresponding to all secondary nodes, a similar sub-subject clustering cluster corresponding to similar function sub-subjects and a causal correlation degree between sub-subjects with causal relationship under each subject are obtained through clustering algorithm and causal analysis algorithm;

[0030] Using the clustering similarity between each sub-subject in the similar sub-subject clustering cluster, cross-subject connections between each sub-subject are constructed, and the obtained causal correlation degree is mapped into the cross-subject connection corresponding to the causal relationship, and the hierarchical public key permission hash mapping sequence in the hierarchical encryption permission hash mapping sequence is mapped into the cross-subject connection corresponding to the different subjects, and a cross-subject causal permission connection is obtained.

[0031] Specifically, the construction process of the distributed isolated mapping security chain also includes:

[0032] With the historical search information frequency of each type of key entity stored in the nodes in the third-level difference database corresponding to each secondary node, the evaluation score of each key entity corresponding to the search feedback question and answer information, and the auxiliary pre-appointment consistency of the search feedback question and answer information, a third-level index connection is constructed through a hash algorithm;

[0033] Based on the root node, the primary node, the secondary node, the third-level difference database node, the first-level index connection, the second-level index connection, and the third-level index connection, and combined with the graph neural network algorithm, a hierarchical index tree standard semantic question and answer information library corresponding to each subject is obtained;

[0034] Based on the hierarchical index tree standard semantic question and answer information library corresponding to each subject combined with the cross-subject security mapping connection and the cross-subject causal permission connection, a distributed isolated mapping security chain is constructed through a blockchain algorithm and a distributed framework;

[0035] Based on the distributed isolated mapping security chain, the general label key entity in each sub-field type in the standard key entity mapping table is mapped to the cross-subject security mapping connection of the corresponding sub-field type, the bidirectional mapping connection is mapped to the cross-sub-subject causal authority connection with the exclusive label clustering mapping table, and the exclusive label standardized distributed isolated mapping security chain is obtained.

[0036] Specifically, the process of recommending appointment information includes:

[0037] Based on the exclusive label standardized distributed isolated mapping security chain, a distributed security appointment chain with the same structure is constructed, and each hierarchical index tree standard semantic question and answer information library corresponding to the three-level difference database node under the distributed isolated mapping security chain is replaced by a three-level appointment information library node constructed by the work staff function type, skill proficiency, occupation level, and work scheduling information and the corresponding work staff current load information under the same sub-subject, to obtain a distributed appointment decision tree corresponding to each subject under the distributed security appointment chain;

[0038] According to the search key entity semantics and type information, subject code, sub-subject name, sub-subject code, and work staff function type, skill proficiency, occupation level, and each work staff historical appointment recommendation consistency frequency contained in the secondary nodes between the distributed appointment decision tree corresponding to each subject and the hierarchical index tree standard semantic question and answer information library, a bidirectional mapping dictionary is constructed by a hash algorithm, and a bidirectional balanced mapping dictionary is obtained by using work scheduling information and corresponding work staff current load information, through reinforcement learning and load balancing algorithm.

[0039] Based on the bidirectional balanced mapping dictionary, a cross-system appointment auxiliary connection between the distributed appointment decision tree and the hierarchical index tree standard semantic question and answer information library corresponding to each subject is constructed, and all secondary nodes corresponding to the hierarchical index tree standard semantic question and answer information library corresponding to each subject under the distributed isolated mapping security chain and the distributed appointment decision tree corresponding to the same subject under the distributed security appointment chain are connected by the cross-system appointment auxiliary connection, to obtain a dual search-appointment security chain.

[0040] Specifically, the process of recommending appointment information includes:

[0041] Obtain the user search information, obtain the user search semantic association vector and context association vector through the intent analysis model, and determine whether there is appointment demand information;

[0042] If not, the user retrieval semantic association vector and the context association vector are input to the standard key entity mapping table in the double retrieval-reservation security chain for retrieval key entity standardization, combined with the distributed isolation mapping security chain according to the standardized retrieval semantic association vector and the context association vector, information retrieval is performed, and the retrieved information is fed back;

[0043] If there is a reservation requirement, the standardized retrieval semantic association vector and the context association vector are synchronously input to the distributed isolation mapping security chain and the distributed security reservation chain for retrieval and reservation, and the retrieved information is fed back to the corresponding user at the same time, the retrieved information is fed back to the distributed security reservation chain through the cross-system reservation auxiliary connection to adjust the reservation result, when the information needs to be reserved different sub-subjects, cross-subject association reservation is performed through the cross-subject causal authority connection in the distributed security reservation chain, and the association reservation result is fed back to the corresponding user through the recommendation algorithm;

[0044] Based on the information retrieval and reservation or association reservation process of the corresponding double retrieval-reservation security chain, retrieval and reservation cross-system synchronous simulation training is performed through simulation algorithm, until the evaluation score and reservation consistency frequency ratio of the question and answer retrieval information meet the corresponding threshold value at the same time, the trained double retrieval-reservation security chain is obtained.

[0045] The intelligent customer service information retrieval system based on a large model comprises a response module, a retrieval discrimination module, a discrimination result module, a reservation parameter module, a recommendation module, and a discrimination updating module.

[0046] The response module is used to respond to user retrieval information and obtain user retrieval semantic association vectors and context association vectors.

[0047] The retrieval discrimination module is based on the retrieval semantic association vector and the context association vector combined with the pre-set standard key entity mapping table and the built-in three-level index mapping table in the pre-set distributed isolation mapping security chain, and performs standard question and answer retrieval information retrieval judgment on the hierarchical index tree standard semantic question and answer information library configured on each main node of the distributed isolation mapping security chain.

[0048] The discrimination result module is based on the retrieval discrimination result, returns the standard question and answer retrieval information according to the frequency priority of the retrieval key entity in the retrieval semantic association vector, and when no retrieval is performed, generates a question and answer retrieval information sequence and a corresponding evaluation score through a pre-trained inference generation model combined with the hierarchical index tree standard semantic question and answer information library according to the user retrieval semantic association vector, and feeds back the information with the maximum evaluation score in all generated question and answer retrieval information to the corresponding user.

[0049] The reservation parameter module is used for, when the semantic association vector contains reservation requirements, obtaining a cross-system reservation parameter set by combining standard question and answer retrieval information through a distributed reservation decision tree corresponding to each subject node in a distributed isolated mapping security chain according to user reservation requirements;

[0050] The recommendation module obtains recommended reservation information by combining a matching recommendation algorithm through a preset cross-system bidirectional mapping dictionary based on the cross-system reservation parameter set;

[0051] The discrimination updating module is used for collecting the frequency of reservation according to the recommended reservation information and the frequency of real reservation corresponding to the user in real time, and obtaining a reservation consistency frequency ratio, and if the consistency frequency ratio is less than a preset reservation consistency threshold, then the recommended mapping information in the bidirectional mapping dictionary and the retrieval index information in the three-level index mapping table are constructed and updated according to real-time reservation information parameters until the reservation consistency threshold is met.

[0052] Compared with the prior art, the beneficial effects of the present application are:

[0053] The present application realizes multi-dimensional technical breakthrough by constructing a double-database three-core architecture and a distributed isolated mapping security chain. The semantic vector retrieval and large model inference are used to solve the problem of low semantic retrieval accuracy of traditional systems. The four-level tree information database and three-level index mechanism are used to improve the cross-subject retrieval efficiency. The distributed reservation decision tree and bidirectional mapping dictionary are used to optimize the cross-system reservation process. The causal association analysis and graph neural network are introduced to strengthen the semantic ambiguity resolution and dynamic adaptation capability. The blockchain and encryption permission control are relied on to protect the multi-subject data security and permission management. The scheme forms a closed loop from semantic understanding, intelligent retrieval to accurate reservation, effectively improves the personalized service, cross-system collaboration and semantic understanding ability of medical intelligent customer service, and breaks through the technical bottleneck of traditional systems. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 The present application provides an embodiment: a large model-based intelligent customer service information retrieval method, which is applied to medical information question and answer, and the steps include:

[0055] Figure 2 The present application provides an embodiment: a large model-based intelligent customer service information retrieval system module diagram. DETAILED DESCRIPTION

[0056] Embodiment 1

[0057] Please refer to Figure 1 The present application provides an embodiment: a large model-based intelligent customer service information retrieval method, which is applied to medical information question and answer, and the steps include:

[0058] S1, in response to user retrieval information, obtaining user retrieval semantic association vector and context association vector;

[0059] It should be noted that the user retrieval information in the embodiment is medical related question and answer information; it needs to be further explained that the user retrieval semantic association vector in the embodiment is the key entity related to retrieval extracted from the user input text, such as the key text description of disease name, symptom manifestation, etc. After vectorization processing, a high-dimensional vector is formed. Its function is to convert the user natural language question into a machine computable semantic representation, match with the standard label vector in the knowledge base, realize accurate information retrieval and semantic understanding, for example, when the user inputs that diabetes causes vision loss, extract the key entities such as diabetes and vision loss into semantic vectors, which are used to match the knowledge base content of related departments such as endocrinology department and ophthalmology department, and then recommend appropriate diagnosis and treatment information or registration department, improve the retrieval efficiency and answer accuracy of intelligent customer service system;

[0060] It needs to be further explained that the user retrieval semantic association vector and the context association vector in the embodiment are preferably pre-trained medical word segmentation model and Med-BERT pre-trained language model. These models are pre-trained by collecting historical medical question and answer text information before use, so that the corresponding model can better extract the corresponding retrieval semantic entity and the corresponding context vector from the user input text information; it needs to be further explained that the context association vector in the embodiment is a high-dimensional feature vector generated by combining user conversation history and personalized context of target hospital, which is obtained by extracting conversation history, encoding context features, fusing hospital dimension prior knowledge and dynamically adjusting weight; Its function is to capture the context semantic relationship of user question and the hospital exclusive context features, such as the use habit of department alias, and then eliminate the semantic ambiguity across departments and hospitals, so that the system can accurately understand the user's intention according to the personalized terminology and inquiry mode of different hospitals, such as distinguishing the difference of corresponding department of "stroke" in different hospitals, improving the accuracy of complex disease retrieval and cross system reservation; The context semantic relationship includes but is not limited to symptom evolution path and corresponding symptom professional entity information;

[0061] S2, based on the retrieval semantic association vector and the context association vector, combining the pre-set standard key entity mapping table and the three-level index mapping table built in the pre-set distributed isolation mapping security chain, judging the standard question and answer retrieval information retrieval of the hierarchical index tree standard semantic question and answer information database configured in each main node of the distributed isolation mapping security chain;

[0062] S3, if the retrieval is found, the standard question and answer retrieval information is returned according to the frequency priority of the retrieval key entity in the retrieval semantic association vector;

[0063] In this embodiment, the key entities such as disease names and symptoms in the retrieved semantic association vector are extracted, the frequency of each key entity in the retrieved text is counted, such as "diabetes" appearing twice and "visual decline" appearing once, and the standard question and answer information retrieved is frequency matched and prioritized based on the association between the key entities and the question and answer information in the three-level index mapping table. The specific technical means are as follows: first, the frequency of each key entity in the retrieved semantic association vector is calculated using the TF algorithm (term frequency algorithm) to generate a frequency priority list; second, the question and answer items containing the corresponding key entities in the hierarchical index tree library are quickly located through the hash index, and the question and answer items are sorted in descending order according to the matching frequency of the key entities (such as a question and answer containing "diabetes" and "visual decline" and appearing more frequently), and finally the results are returned according to the priority; the role is to ensure that when the user searches, the system can prioritize the question and answer information with higher matching degree based on the frequency weight of the key entities, for example, when the user asks "the reason why diabetes causes visual decline", the standardized answer that simultaneously mentions the key entities such as "diabetes" and "retinal disease" with high frequency is returned first, improving the accuracy of information feedback and the degree of user demand.

[0064] S4, if no information is retrieved, the question and answer retrieval information sequence and the corresponding evaluation score are generated based on the user retrieval semantic association vector through the pre-trained inference generation model combined with the hierarchical index tree standard semantic question and answer information library, and the information with the maximum evaluation score among all the generated question and answer retrieval information is fed back to the corresponding user; it needs to be further explained that the pre-trained inference generation model in this embodiment is trained by combining the pre-trained Chinese Bert model with the index information constructed by the historical medical question and answer information and the historical retrieval in this embodiment, which will not be described here;

[0065] S5, when the retrieval semantic association vector contains reservation requirements, cross-system reservation matching is performed based on the user reservation requirements through the distributed reservation decision tree corresponding to each subject node in the distributed isolation mapping security chain combined with the standard question and answer retrieval information, and the cross-system reservation parameter set is obtained;

[0066] S6, based on the cross-system reservation parameter set, the recommended reservation information is obtained through the pre-set cross-system bidirectional mapping dictionary combined with the matching recommendation algorithm;

[0067] S7, the frequency of the corresponding user making a reservation according to the recommended reservation information and the frequency of the real reservation are collected in real time, and the reservation consistency frequency ratio is obtained, if the consistency frequency ratio is less than the pre-set reservation consistency threshold, the recommended mapping information in the bidirectional mapping dictionary and the retrieval index information in the three-level index mapping table are constructed and updated according to the real-time reservation information parameters until the reservation consistency threshold is met.

[0068] It needs to be further explained that the construction process of the standard key entity mapping table in the embodiment includes:

[0069] The historical text record information and the field standardized text information corresponding to all sub-agents of each type of agent are obtained, and the pre-trained professional word segmentation model is used for word segmentation preprocessing to obtain the text information space and the field standard text information space corresponding to all sub-agents under each agent;

[0070] It needs to be further explained that the agent in the embodiment refers to a hospital, and the sub-agent refers to the corresponding departments in the hospital;

[0071] It needs to be further explained that the process of obtaining the text information space and the field standard text information space corresponding to all sub-agents under each agent in the embodiment includes:

[0072] The historical question and answer text record information of each type of agent and its sub-agent is collected, including but not limited to the department diagnosis and treatment process of the hospital, disease question and answer data, various disease symptoms and diagnosis information, etc., and the standardized text information in the industry field is obtained, including but not limited to the standard department classification and professional department name in the medical industry, disease diagnosis specification and standard disease professional name, etc.;

[0073] Based on the collected information, the pre-trained medical word segmentation model is used for word segmentation preprocessing of these texts to remove stop words, special symbols and other irrelevant contents, and extract key terms; the pre-trained medical word segmentation model is constructed by the pre-trained model disclosed in the art, which will not be described here;

[0074] Taking the hospital agent in the medical field as an example, assuming that the agent A is a hospital, and its sub-agents include the department of cerebral disease and the department of cardiovascular disease; for the historical question and answer text record of the department of cerebral disease in the hospital A, such as the main diagnosis and treatment of diseases such as stroke and headache in the department of cerebral disease, the word segmentation obtains the words such as department of cerebral disease, diagnosis and treatment, stroke and headache, forming the text information space of the sub-agent; and the description of the department of neurology in the industry standard text information is that the department of neurology mainly diagnoses and treats cerebrovascular diseases and headache, etc., and the word segmentation obtains the department of neurology, diagnosis and treatment, cerebrovascular disease, headache, etc., to constitute the field standard text information space.

[0075] Based on the text information space and the field standard text information space corresponding to all sub-agents under each agent, the exclusive label key entity vector and the general label key entity vector corresponding to each sub-agent are obtained through the entity relationship extraction algorithm; it needs to be further explained that the entity relationship extraction algorithm in the embodiment is constructed by combining the Chinese pre-trained Bert model with BILSTM and CRF (conditional random field) algorithm;

[0076] It needs to be further explained that the acquisition process of the exclusive label key entity vector and the general label key entity vector corresponding to each sub-subject in the embodiment includes:

[0077] First, input the text in the text information space and the text in the domain standard text information space into the Chinese pre-trained Bert model, extract the semantic feature representation of the text, then input these features into the BILSTM network, use its ability to process sequence data in both directions to capture long-distance dependencies in the text, then perform sequence labeling on the results output by BILSTM through the CRF layer, identify the entities and the relationship between entities in the text, and then obtain the exclusive label key entity vector and the general label key entity vector corresponding to each sub-subject. Illustratively, for the stroke disease in the diagnosis and treatment of the brain disease department in the brain disease department text information space of the A hospital brain disease department, after processing by the algorithm, the exclusive label key entity vector of the brain disease department and the general label key entity vector of the neurology department can be extracted, and the entity relationship of "diagnosis and treatment" can be identified.

[0078] Taking each general label key entity vector as the clustering center, the clustering distance between each clustering center and all exclusive label key entity vectors is obtained through the cosine formula.

[0079] Based on all clustering distances corresponding to each clustering center, determine the truncated distance corresponding to each clustering center, input all truncated distances corresponding to each clustering center and clustering distance into the DBSCAN algorithm, and obtain the exclusive label clustering mapping table corresponding to each general label; the exclusive label clustering mapping table includes the general label and the exclusive label sequence under the corresponding different sub-subjects.

[0080] It needs to be further explained that the acquisition process of the exclusive label clustering mapping table corresponding to each general label in the embodiment includes:

[0081] With each general label key entity vector as a clustering center, the clustering distance between each clustering center and all exclusive label key entity vectors is calculated by a cosine formula; based on all clustering distances corresponding to each clustering center, a k-distance graph is generated by calculating the Euclidean distance from each exclusive label key entity vector to the k-th nearest neighbor vector and observing the elbow point position of the curve slope mutation in the graph, and the distance value corresponding to the position is determined as the cutoff distance; then the cutoff distance and the clustering distance corresponding to each clustering center are input into the DBSCAN algorithm, and the core points and boundary points are identified by density peak clustering to obtain the exclusive label clustering mapping table corresponding to each general label. For example, taking the "neurology" general label key entity vector as the clustering center, the clustering distances of the "neurology" general label key entity vector with the "encephalopathy department" of A hospital and the "brain department" of B hospital are calculated, and after the cutoff distance is determined by the k-distance graph, the DBSCAN algorithm is input to generate the clustering mapping table corresponding to the "neurology" general label, which contains exclusive labels such as "encephalopathy department" and "brain department". It needs to be further explained that in this embodiment, the role of the cutoff distance is to serve as a threshold for density calculation. When the clustering distance between the exclusive label and the general label is less than or equal to the cutoff distance, it is considered that the semantics of the two are similar and they are included in the same cluster, otherwise they are considered to be different clusters, so as to ensure that the DBSCAN algorithm can accurately identify the core clustering area and generate a clustering mapping table containing the corresponding relationship between the general label and different sub-subject exclusive labels, thereby realizing the consistency mapping of cross-subject semantics.

[0082] Based on the exclusive label clustering mapping table corresponding to all general labels and the field standard text information space, the causal correlation degree between different exclusive labels under different general labels is obtained by combining an expert experience-based causal correlation analysis model;

[0083] It needs to be further explained that the specific process of obtaining the causal correlation degree between different key entities under different general labels in the medical field includes:

[0084] By marking the causal relationship of the exclusive label entity by experts, a labeled dataset containing the trigger-triggered relationship between diseases is constructed. For example, the label "high blood pressure" can trigger "arteriosclerosis"; secondly, the labeled data and the domain standard text are input into the causal correlation analysis model constructed by the BERT pre-training model combined with the graph attention network. The semantic vector of the key entity is extracted by BERT, the node features are propagated in the causal relationship graph through the graph attention network, and the causal weight between entities is learned. At the same time, the expert pre-set causal rule library is introduced as prior knowledge to regularize and constrain the correlation degree output by the model, and finally the causal correlation degree between key entities under different general labels is obtained. For example, based on the exclusive label clustering mapping table of the "diabetes" general label, including but not limited to "diabetes" and "abnormal glucose metabolism", combined with the description of "diabetes can cause retinopathy" in the domain standard text, the expert marks the causal relationship and inputs the model to obtain the causal correlation degree of "diabetes" and "retinopathy". When the user only describes "visual decline and suffering from diabetes", the system can associate the key entities of "diabetic retinopathy" through causal reasoning; through this causal reasoning process, even if the user cannot describe the real disease name that he wants to express, but through the description of the associated disease name and the external symptoms of the associated disease, the corresponding professional disease information can be accurately matched, and more accurate question and answer information and recommendation results can be given.

[0085] The causal rule library is constructed by those skilled in the art according to the mutual influence relationship between different diseases combined with the correlation algorithm; for example, the strong correlation rule that diabetes causes retinopathy;

[0086] Based on the causal correlation degree between different exclusive labels under different general labels, a bidirectional mapping connection between the key entities of different general labels and the corresponding exclusive label key entities is constructed, and based on the bidirectional mapping connection combined with the exclusive label clustering mapping table corresponding to each general label, a standard key entity mapping table is obtained; it needs to be further explained that the bidirectional mapping connection in the embodiment plays a role in establishing a semantic intercommunication bridge between general labels and exclusive labels, realizing semantic consistency mapping and causal reasoning across subjects and sub-fields; specifically, it realizes bidirectional association between industry standardized terms (such as "neurology") and self-defined terms of each subject (such as "encephalopathy department" and "brain department") by fusing the causal correlation degree of exclusive labels under different general labels, which not only supports mapping exclusive labels (such as "diabetes") searched by the user to general labels (such as "diabetes") to match standardized knowledge, but also can reversely map the associated knowledge of general labels (such as "diabetes causes retinopathy") to exclusive label scenarios based on causal relationship, so that the standard key entity mapping table can not only eliminate semantic ambiguity, but also support complex retrieval based on causal logic, and improve the accuracy of cross-subject knowledge linkage and intelligent reasoning.

[0087] The history text record information corresponding to all sub-main bodies and the revised field standardized text information corresponding to each type of main body added in real time are collected, and the above-mentioned process of constructing the exclusive label clustering mapping table corresponding to each general label and the bidirectional mapping connection is repeated, and the standard key entity mapping table is updated by combining the incremental update model with the information collected in real time.

[0088] It should be further explained that the specific process corresponding to the incremental update model implemented in the embodiment includes:

[0089] After the newly added main body text record and the revised industry standard text are collected in real time, the incremental update model is based on the dynamic vector interpolation algorithm and the hierarchical clustering optimization mechanism. First, the exclusive label and the general label key entity vector are generated by preprocessing the newly added data, then the distance between the newly added vector and the existing clustering center is calculated, if the distance is less than the cutoff distance, the clustering boundary is updated by vector interpolation; exemplary, the weighted average of the newly added vector and the adjacent vector is taken as the new clustering center, otherwise a new cluster is created. At the same time, the bidirectional mapping connection is updated by using the incremental graph neural network, the newly added entity relationship is integrated into the knowledge graph, and the causal association degree is recalculated, finally the dynamic update of the standard key entity mapping table is realized; exemplary, when a system imports "Tangluo disease" as a custom label of "diabetes" through Excel, the system generates its semantic vector after parsing, and calculates the distance with the existing "diabetes" clustering center, if it meets the threshold, the clustering is updated by interpolation algorithm, so that "Tangluo disease" is added to the clustering mapping table, and the causal association weight with entities such as "retinopathy" is updated.

[0090] The process converts the hospital department personalized text and the industry standard text into key entity vectors through the pre-trained word segmentation model and the entity relation extraction algorithm, effectively eliminates the semantic gap between different hospital self-defined terms and industry standards, enables exclusive labels such as "brain disease department" and "brain department" to accurately correspond to general labels such as "neurology department", and ensures the consistency of cross-hospital retrieval. Secondly, based on the clustering algorithm and the cut-off distance, the exclusive label clustering mapping table is determined, the semantic similarity area is accurately divided by density calculation threshold, the core clustering is identified by DBSCAN algorithm, the accuracy and reliability of label classification are enhanced, and the foundation for consistent mapping of cross-subject semantics is laid. In addition, the process combines expert experience and causal relationship analysis model to mine the causal relationship of key entities, integrates the expert rule base through BERT and graph attention network, realizes the reverse reasoning from symptom to cause, supports users to obtain accurate disease question and answer results under fuzzy description, for example, when the user only mentions "visual decline and suffering from diabetes", the system can be associated to "diabetic retinopathy" through causal reasoning. Finally, the incremental update model uses dynamic vector interpolation and incremental graph neural network to respond to the addition of new data in hospitals and the revision of industry standards in real time, automatically adjusts the clustering boundary and causal weight, ensures that the mapping table continuously adapts to the dynamic evolution of medical knowledge, so that the system can automatically optimize the mapping relationship when facing new terms or knowledge updates, and maintain the accuracy of semantic understanding and retrieval.

[0091] It should be further explained that the construction process of the distributed isolation mapping security chain in the embodiment includes:

[0092] The root node is constructed based on the domain information in the domain standardized text information, and the domain classification tree is obtained based on the domain standardized text information, the knowledge graph and the graph embedding algorithm, and the domain classification tree is embedded into the root node;

[0093] The domain classification tree is obtained by expert experience algorithm decomposition according to industry domain information, each sub-domain is constructed according to the level size marked by expert experience and combined with the knowledge graph and the graph embedding algorithm, including the corresponding sub-node of each sub-domain and the corresponding domain annotation information;

[0094] It should be further explained that the process of constructing the domain classification tree in the embodiment includes:

[0095] Based on the expert experience algorithm combined with industry field standardized text, the field information is decomposed into sub-fields. For example, the medical field is decomposed into internal medicine, surgery, etc., and each sub-field is labeled with a level size. For example, internal medicine is a first-level sub-field, and cardiovascular internal medicine is a second-level sub-field. Secondly, based on the decomposed sub-fields and labeled information, a knowledge graph containing parent-child node relationships is constructed. For example, the "medical field" root node points to the internal medicine and surgery sub-nodes. Thirdly, the graph embedding algorithm is used to map the nodes and relationships in the knowledge graph to a low-dimensional vector space, retaining the field hierarchical structure and semantic association. Finally, the embedded field classification tree is integrated into the root node to form a field classification tree containing sub-field nodes and field labeling information. For example, in the medical field, the expert decomposes the first-level sub-fields of internal medicine, surgery, etc., and the second-level sub-fields of cardiovascular internal medicine, neurology, etc. After constructing the knowledge graph, the TransR (knowledge graph embedding) algorithm is used to embed the vector space to obtain the field classification tree embedded in the root node, where the "neurology" node contains its level label as a second-level sub-field and the semantic association vector with concepts such as "neurological diseases".

[0096] Based on the subject, a first-level node is constructed, and a second-level node is constructed by a sub-subject. The corresponding text information space, historical question and answer information, and configured standard reply information under each sub-subject combine a tree-shaped database to construct a third-level difference database node.

[0097] It should be further explained that the construction process of each level node in the present embodiment includes:

[0098] The first node is constructed based on the basic information of the subject, including but not limited to subject code, name, etc., and is stored in a distributed database; the second node is constructed according to the classification information of the sub-subject, and the parent-child association is established with the first node, for example, the hospital and the department; secondly, for each sub-subject, the text information space, historical question and answer information (including but not limited to user question-standard answer pair) and configured standard reply information (i.e. pre-stored predefined reply template) are structured, and the third node is constructed in the tree-shaped database through B+ tree index algorithm; it needs to be further explained that the third node in the embodiment contains data partition index of the corresponding subject, disease text hash value and multi-dimensional label corresponding to each sub-subject under the current subject, for example, the multi-dimensional label is the three-level association label of department-disease-symptom; for example, when constructing the third node of a certain hospital, the first node is the hospital subject, the second node is the neurology department sub-subject, and the third node stores the text information (including but not limited to stroke diagnosis and treatment process word segmentation result) of the department, historical question and answer (including but not limited to standard answer of symptoms of stroke) and standard reply template, and the B+ tree index is used to realize fast retrieval and hierarchical management, ensuring data isolation and efficient access of different departments; the data partition index refers to that the system uses the storage architecture of hospital ID combined with data partition to create an independent knowledge base space for each hospital; for example, when arranged in a certain hospital, the system automatically generates a dedicated namespace to store the department classification and user question and answer information data of different disease symptoms under each department, so that it is completely isolated from other hospital data; the background management interface supports parallel login of multiple hospital accounts, and the administrator can switch the hospital dimension to maintain the knowledge base, for example, a hospital can update its neurology department diagnosis and treatment process separately without affecting other hospital data.

[0099] Based on the field type corresponding to each subject, the similar subject clustering cluster is obtained through the clustering algorithm, and the first index connection between each node and the first node in the corresponding similar subject clustering cluster is constructed according to the field type corresponding to the similar subject clustering cluster;

[0100] Meanwhile, according to the clustering similarity between the first nodes in the similar subject clustering cluster, a cross-subject connection is constructed, and combined with the information security protection level, subject label code and historical cross-subject retrieval access permission information between subjects, a hierarchical encryption permission hash mapping sequence is obtained based on the hash algorithm and encryption permission control algorithm, and a hierarchical private key permission hash mapping sequence in the hierarchical encryption permission hash mapping sequence is mapped to the cross-subject connection between the corresponding subjects to obtain a cross-subject security mapping connection sequence;

[0101] It needs to be further explained that the embodiment aggregates the subjects into similar subject clusters according to the field type by the field clustering algorithm, constructs a one-level index connection from the root node to the one-level node, realizes the fast positioning and hierarchical retrieval of field knowledge, and at the same time, constructs a cross-subject connection based on the clustering similarity, and fuses the security protection level, label coding and other information, generates a hierarchical permission hash sequence through the hash and encryption algorithm, maps to the connection edge to form a cross-subject security mapping connection, which not only ensures the semantic rationality of the connection through the field correlation, but also realizes the security isolation and on-demand sharing of data between subjects by using hierarchical permission control, finally constructs a cross-subject association system with retrieval efficiency and security protection, which is suitable for medical and other scenes with high requirements for field aggregation and data security.

[0102] It needs to be further explained that the specific implementation process of the hash algorithm and the encryption permission control algorithm in the embodiment includes:

[0103] The DBSCAN clustering algorithm is used to cluster the subject field type vector to obtain similar subject clusters; secondly, based on the field vector similarity of the subjects in the cluster, the cosine distance calculation is used to construct a one-level index connection from the root node to the one-level node; in the construction of the cross-subject connection, the clustering similarity between the one-level nodes in the similar subject cluster is calculated first to generate the cross-subject connection edge; then, combined with the information security protection level of each subject, the subject label code and the historical access permission record, the SHA-256 hash algorithm is used to hash the permission parameters, and then the AES encryption permission control algorithm is used to encrypt the hash value at different levels to generate an encrypted hash sequence containing different permission levels; finally, the hash sequence encrypted by the hierarchical private key is mapped to the cross-subject connection edge to form a cross-subject security mapping connection; for example, in the hospital clustering cluster, the field vector similarity of A and B hospitals is a, when constructing the cross-subject connection, according to the protection level of A hospital: three levels, B hospital: two levels, the subject label codes are H123 and H456 respectively, the permission parameter hash value is calculated through SHA-256, and then a low-permission hash sequence is generated by AES-128 encryption, which is mapped to the connection edge to realize the read-only secure access of A hospital to the data of B hospital. The historical access permission level is set by the person skilled in the art according to the sensitivity of the corresponding data;

[0104] Based on the information of all secondary nodes corresponding to each primary node and the information of the subfield type to which the function information of each secondary node belongs, a secondary index connection is constructed, and through the function information of all secondary nodes, a similar sub-subject clustering cluster corresponding to similar function sub-subjects and a causal correlation degree between sub-subjects existing in a causal relationship under each subject are obtained through a clustering algorithm and a causal analysis algorithm. It needs to be further explained that the information of the subfield type to which the function information of each secondary node belongs is specifically the relationship between the function type corresponding to the department under each hospital and each subfield, for example, the relationship between the function type corresponding to the ophthalmology department and the ophthalmology subfield.

[0105] It needs to be further explained that the process of constructing a secondary index connection and obtaining a causal correlation degree based on the information of all secondary nodes corresponding to each primary node and the subfield type to which the function information of the secondary node belongs in the embodiment is as follows: first, the function information of all secondary nodes under the primary node is extracted, for example, the diagnosis and treatment range of the eye, ear, mouth, nose, and brain surgery, the subfield type to which it belongs is mapped through the field classification tree, and the secondary index connection of the subfield-department is constructed using the inverted index algorithm to realize fast retrieval of related departments according to the subfield; secondly, for all secondary node function information, first generate a similar function sub-subject clustering cluster based on the function vector similarity using the DBSCAN clustering algorithm; then, the causal analysis algorithm constructed by the BERT pre-training model combined with the causal convolution network is used to input the function text into BERT to extract semantic features, capture long-distance causal dependence through the causal convolution layer, calculate the causal correlation degree between sub-subjects, for example, analyze the causal correlation between the endocrinology department and the ophthalmology department due to diabetic retinopathy; for example, under a certain hospital primary node, the function information of the secondary node ophthalmology department is mapped to the ophthalmology subfield to construct an index, and at the same time, it is found through clustering that it belongs to the metabolic eye disease diagnosis and treatment cluster with the endocrinology department, and the causal correlation degree between the two departments due to diabetes-induced visual impairment is calculated through the causal analysis algorithm, which is used for cross-department correlation retrieval and collaborative diagnosis and treatment.

[0106] The clustering similarity between each sub-subject in the similar sub-subject clustering cluster is used to construct a cross-sub-subject connection between each sub-subject, and the causal correlation degree obtained is mapped into the cross-sub-subject connection corresponding to the causal relationship, and the hierarchical public key permission hash mapping sequence in the hierarchical encrypted permission hash mapping sequence is mapped into the corresponding cross-sub-subject connection between different subjects, to obtain a cross-sub-subject causal permission connection.

[0107] It needs to be further explained that the embodiment takes the medical scene as an example, when the patient has diabetes, the endocrinology department is responsible for the basic blood sugar regulation, and the ophthalmology department may need to deal with the retinopathy caused by diabetes. By calculating the clustering similarity of the endocrinology department and the ophthalmology department, a cross-subject connection is constructed to clarify the association between the two in the diagnosis and treatment of complications of diabetes; The causal correlation degree of "diabetes leading to retinopathy" is mapped to the connection, so that the system can quickly identify the causal relationship between the two departments when handling patient-related consultations, realize cross-department knowledge linkage, and provide more comprehensive diagnosis and treatment recommendations; Then map the hierarchical public key permission hash mapping sequence into the connection, ensure that the endocrinology department doctor can safely access the ophthalmology department's diagnosis and treatment data on diabetic retinopathy after being authorized, and the ophthalmology doctor can also view the endocrinology department's blood sugar control plan for the patient, which not only ensures the safe isolation of data in different departments, but also enables cross-department data collaboration and permission sharing when necessary, optimizing the patient's diagnosis and treatment process and information interaction efficiency, thereby obtaining a cross-subject causal permission connection with causal association and secure permission control.

[0108] The historical search frequency of each type of key entity stored in the nodes of the third-level difference database corresponding to each secondary node, the evaluation score of the search feedback question and answer information corresponding to each key entity, and the auxiliary reservation consistency of the search feedback question and answer information are constructed into a third-level index connection through a hash algorithm; The auxiliary reservation consistency of the search feedback question and answer information is the consistency between the reservation recommendation information corrected by the search information and the user's true reservation information, for example, the system recommends to reserve the C doctor in the ophthalmology department, but the user actually reserves the D doctor in the ophthalmology department;

[0109] Based on the root node, the first-level node, the second-level node, the third-level difference database node, combined with the first-level index connection, the second-level index connection, and the third-level index connection, and combined with the graph neural network algorithm, a hierarchical index tree standard semantic question and answer information library corresponding to each subject is obtained;

[0110] It needs to be further explained that the embodiment extracts the key entity search frequency, feedback evaluation score, and auxiliary reservation consistency data in the third-level database node corresponding to the secondary node, and then constructs a third-level index connection through a hash algorithm after normalization and weighted summation, to quickly locate the key entity with high frequency, high evaluation, and high reservation consistency; Then integrate the root node to the third-level node and the index connection at each level, learn the semantic association and hierarchical relationship between nodes using a graph neural network algorithm, and generate a hierarchical index tree standard semantic question and answer information library by fusing domain knowledge, subject information, etc.; Its role is to improve the search accuracy by constructing indexes from multiple dimensions, and to realize semantic fusion and hierarchical management by combining graph neural networks, so that the final information library can support quick access to high-frequency high-quality question and answer data when users consult, and at the same time, the semantic association between knowledge is strengthened through index connection and graph structure, improving the information retrieval efficiency and answer adaptability in complex scenarios.​​​​​​

[0111] It needs to be further explained that the acquisition process of the hierarchical index tree standard semantic question and answer information library in the embodiment includes:

[0112] First, for each three-level difference database node corresponding to a secondary node, the historical key entity retrieval information frequency is extracted, that is, the number of times each key entity is retrieved is counted; through the sentiment analysis algorithm in natural language processing, the sentiment polarity and score of the retrieval feedback information are calculated to obtain the evaluation score of each key entity corresponding to the retrieval feedback question and answer information; when calculating the auxiliary reservation consistency of the retrieval feedback question and answer information, the sequence matching algorithm is used to compare the reservation recommendation information corrected by the retrieval information with the actual reservation information of the user to judge the matching degree of the two; after normalizing the data in the above three dimensions, the comprehensive weight is generated by weighted summation algorithm, and then the SHA-256 hash algorithm is used to hash the comprehensive weight and key entity information, to construct a three-level index connection, and to realize fast positioning of high-frequency, high-evaluation and high-reservation-consistency key entity information.

[0113] Secondly, the root node, the first-level node, the second-level node, the third-level difference database node, the first-level index connection, the second-level index connection and the third-level index connection are integrated, and the graph neural network algorithm is used to learn the semantic association and hierarchical relationship between nodes through node feature aggregation and message passing mechanism, to fuse the domain knowledge, the subject information, the sub-subject function and the key entity question and answer data, and to generate an initial hierarchical index tree standard semantic question and answer information library corresponding to each subject.

[0114] For example, under a certain hospital subject, ophthalmology is a secondary node, and its three-level difference database node stores the retrieval records of key entities such as cataract surgery; through statistics, it is found that the cataract surgery retrieval frequency is high, the sentiment analysis shows that the user feedback is positive, and the reservation recommendation and the actual reservation are highly consistent, and the three-level index connection is constructed by weighted summation and hash operation; then the ophthalmology node and the hospital first-level node, the medical field root node, and the index connection at each level are input into the graph neural network algorithm, and finally a hierarchical index tree standard semantic question and answer information library containing ophthalmology specialty knowledge and industry general knowledge is formed, which supports users to consult cataract diagnosis and treatment problems, and the system quickly calls high-frequency, high-quality and adaptive question and answer information.

[0115] Based on the hierarchical index tree standard semantic question and answer information library corresponding to each subject, combined with cross-subject secure mapping connection and cross-sub-subject causal authority connection, a distributed isolated mapping secure chain is constructed through blockchain algorithm and distributed framework;

[0116] The general label key entity in the standard key entity mapping table is mapped to the cross-subject security mapping connection of the corresponding sub-field type based on the distributed isolated mapping security chain, the bidirectional mapping connection and the exclusive label clustering mapping table are mapped to the cross-subject causal authority connection for cross-subject exclusive label association mapping, and a distributed isolated mapping security chain with exclusive label standardization is obtained.

[0117] It should be further explained that, in the embodiment, the hierarchical index tree standard semantic question and answer information library, the cross-subject security mapping connection and the cross-subject causal authority connection are integrated into the distributed isolated mapping security chain based on the blockchain algorithm and the distributed framework, so that the distributed storage and the safe isolation of data are realized; the general label key entity in the standard key entity mapping table is mapped to the cross-subject security mapping connection, so that the consistency of standardized retrieval between different subjects is ensured; the bidirectional mapping connection and the exclusive label clustering mapping table are mapped to the cross-subject causal authority connection for cross-subject exclusive label association mapping, so that the semantic and causal association between exclusive labels is strengthened; and finally, the distributed isolated mapping security chain with exclusive label standardization is formed, which not only ensures the safe isolation of data between different hospitals and departments, but also realizes the efficient association and retrieval at the semantic level, and supports the knowledge linkage and safe sharing across subjects and sub-fields.

[0118] It should be further explained that the distributed isolated mapping security chain in the embodiment is used to realize the safe isolation and semantic association of data between different subjects and sub-fields, and is based on the blockchain and the distributed algorithm, integrates the hierarchical index tree standard semantic question and answer information library, the cross-subject security mapping connection and the cross-subject causal authority connection into a distributed storage structure, realizes the node security link through the hash pointer, and guarantees the data integrity and the non-tamperability by using the RSA algorithm. The specific working process includes: first, the general label key entity in the standard key entity mapping table is mapped to the cross-subject security mapping connection through the hash value matching, so as to realize the standardized retrieval between different subjects; then, the causal relationship and the semantic association between the bidirectional mapping connection and the exclusive label clustering mapping table are converted into the edge attribute and the node attribute of the cross-subject causal authority connection by using the property graph model of the graph database, the connection structure is embedded by using the graph traversal algorithm, the edge weight is updated in combination with the causal correlation degree, and the exclusive label association is strengthened. For example, the general label “diabetes” is realized to be shared between hospitals through the hash matching, and the exclusive labels such as “consumptive disease” are associated to the cross-department causal edge through the graph traversal, so that a distributed chain structure with safe isolation and semantic association is finally formed, and efficient retrieval and knowledge linkage across subjects and sub-fields are supported.

[0119] It should be further explained that the specific process of mapping the bidirectional mapping connection and the exclusive label clustering mapping table to the cross-subject causal authority connection for cross-subject exclusive label association mapping in the embodiment includes:

[0120] Firstly, the hierarchical index tree standard semantic question and answer information library of each subject is stored in a distributed manner by using a blockchain algorithm and a distributed hash table (DHT) algorithm, and each node stores part of the data shards; meanwhile, the cross-subject secure mapping connection and the cross-subject causal authority connection are taken as the on-chain data structure, the secure link between nodes is realized through a hash pointer, and a distributed isolated mapping secure chain is formed. In this process, the RSA algorithm is used to sign and verify the on-chain data, so as to ensure the integrity and non-tamperability of the data.

[0121] It needs to be further explained that, in the process of constructing the distributed isolated mapping secure chain, the hash pointer realizes the secure link between nodes through the following process: firstly, each data node (such as a three-level node in a four-level tree library) generates a unique hash value (such as a SHA-256 hash) when stored in a distributed manner, which contains node data content, a timestamp, and an authority identifier; secondly, the cross-subject secure mapping connection and the cross-subject causal authority connection are taken as the edge structure on the chain, and the hash pointer points to the hash value of the target node, forming a chain structure of the source node hash, the edge hash, and the target node hash; when the data is updated, only the hash value of the corresponding node needs to be updated, and the hash value is synchronized to other nodes through the PBFT algorithm, and the chain association of the hash pointer automatically verifies the legality of the data change; for example, when the node data of the neurology department of hospital A is changed, a new hash value H1 is generated, the pointer of the cross-subject connection is updated from the original hash H0 to H1, and other nodes verify the association relationship between H1 and H0 and the RSA signature to confirm that the data has not been tampered with, thereby realizing the secure link and dynamic verification between nodes based on the hash pointer.

[0122] Secondly, for the general label key entity in the standard key entity mapping table, the corresponding cross-subject secure mapping connection is located through a searching algorithm; specifically, the hash value of the general label key entity is matched with the node identifier in the cross-subject secure mapping connection, and the automatic mapping is realized by using a smart contract, so as to ensure the standardized retrieval of the general label between different subjects.

[0123] Thirdly, the bidirectional mapping connection and the exclusive label clustering mapping table are mapped into the cross-subject causal authority connection for cross-subject exclusive label association mapping; firstly, the causal relationship in the bidirectional mapping connection and the semantic association in the exclusive label clustering mapping table are converted into the edge attribute and node attribute of the cross-subject causal authority connection by using the property graph model of the graph database. Through a graph traversal algorithm, nodes and edges with a similarity greater than a similarity threshold in the cross-subject causal authority connection are searched, and the corresponding bidirectional mapping relationship and clustering information are embedded into the connection structure; meanwhile, the weight of the connection edge is updated by using a weighted average algorithm in combination with the causal correlation degree between the subject and the subject under each subject, so as to strengthen the association between the exclusive labels with strong causal relationship.

[0124] For example, in the medical field, diabetes as a general label key entity is mapped to the cross-subject security mapping connection between hospital A and hospital B through hash matching, realizing the safe sharing of data; while the exclusive label such as diabetes and sugar disease is associated to the causal relationship edge of diabetic retinopathy in the cross-sub-subject causal authority connection between the endocrinology department and the ophthalmology department through the graph traversal algorithm, and the weight of the edge is adjusted according to the causal correlation degree; finally, a distributed isolated mapping security chain with standardized exclusive label is formed, which not only ensures the safe isolation of data between different hospitals and departments, but also realizes efficient association and retrieval at the semantic level.

[0125] This process builds a hierarchical, safe and efficient semantic association and data management system through multi-dimensional technical integration and algorithm application. First, at the level of domain knowledge structuring, the domain classification tree is constructed based on expert experience and graph embedding algorithm and the root node is embedded, which systematically decomposes the industry domain information into a hierarchical sub-domain structure, enabling different subjects and sub-subjects to associate and integrate knowledge under a unified domain framework.

[0126] In terms of data node construction and index connection, through the construction of one to three level nodes and corresponding index connection, the fine management from subject to sub-subject to specific data node is realized; the B+ tree index algorithm is used to construct three-level differential database nodes to ensure efficient storage and fast retrieval of data; the hash algorithm is used to construct three-level index connection, combined with multi-dimensional information such as retrieval frequency, feedback score and reservation consistency, to accurately locate high-quality Q&A data and improve the quality and efficiency of users accessing information. At the same time, the establishment of index connection at different levels forms a close semantic association between data at different levels, supporting multi-dimensional fast retrieval and knowledge linkage; in terms of security and authority management, the cross-subject security mapping connection and cross-sub-subject causal authority connection are generated through hash algorithm and encryption authority control algorithm, which not only ensures the safe isolation of data between different subjects and sub-subjects, but also enables safe sharing and collaborative access of data under authorization; the knowledge linkage between sub-subjects is strengthened based on causal correlation degree, ensuring that in medical scenarios, related departments can achieve knowledge complementation and cross-department collaborative diagnosis and treatment based on causal relationship; finally, a distributed isolated mapping security chain is built through blockchain algorithm and distributed framework, and the standard key entity mapping table and exclusive label information are integrated, realizing distributed storage and safe sharing of data, while ensuring the standardized mapping of exclusive labels between different subjects and sub-subjects; this process not only ensures the integrity and non-tamperability of data, but also significantly improves the semantic understanding and knowledge reasoning ability of the system in complex scenarios, providing more accurate and comprehensive Q&A services and data support for users.

[0127] It should be further explained that the process of recommending reservation information in the embodiment includes:

[0128] The same structure of the distributed security reservation chain is constructed based on the distributed isolated mapping security chain with exclusive label standardization, and each hierarchical index tree standard semantic question and answer information library corresponding to the three-level difference database node under the distributed isolated mapping security chain is replaced by a three-level reservation information library node constructed by the staff function type, skill proficiency, occupation level, and work scheduling information and the current load information of the corresponding staff, to obtain the distributed reservation decision tree corresponding to each subject under the distributed security reservation chain.

[0129] It should be further explained that the distributed security reservation chain in the embodiment aims to realize efficient, intelligent and safe reservation decision, which is based on the distributed isolated mapping security chain with exclusive label standardization, and by constructing the distributed reservation decision tree with the same structure as the hierarchical index tree standard semantic question and answer information library, and constructing the three-level reservation information library node with the staff function type, skill proficiency and other information, the digital management of medical resources is realized. The specific workflow is as follows: first, the multi-dimensional information of the staff under each sub-subject is collected, after data cleaning and feature engineering processing, B+ tree index algorithm is used to construct three-level nodes to realize fast retrieval; then, a bidirectional mapping dictionary is constructed by using a hash algorithm, which associates the reservation decision tree with the semantic question and answer information library data, and generates a bidirectional balanced mapping dictionary through reinforcement learning and load balancing algorithm to optimize personnel load allocation; based on the bidirectional balanced mapping dictionary, a cross-system reservation auxiliary connection between the distributed reservation decision tree under each subject and the corresponding two-level nodes of the hierarchical index tree standard semantic question and answer information library is constructed to obtain a double retrieval-reservation security chain; when the user retrieval information is obtained, the reservation demand is determined through the intent analysis model, and when there is no reservation demand, the information retrieval feedback is performed, and when there is reservation demand, the synchronization retrieval and reservation are performed, and the reservation result is adjusted by means of the cross-system reservation auxiliary connection, the cross-subject associated reservation is realized through the cross-subject causal permission connection, and finally the result is fed back to the user through the recommendation algorithm to ensure the reasonable allocation of resources and accurate reservation. The preferred intent analysis model is a model fine-tuned based on the Chinese pre-trained Bert model combined with the user historical retrieval text information;

[0130] It should be further explained that the construction process of the three-level reservation information library node in the embodiment includes:

[0131] First, the hierarchical index tree standard semantic question and answer information library of each subject in the distributed isolated mapping security chain with exclusive label standardization is taken as a template, and the hierarchical structure of the root node, the first-level node and the second-level node is retained to construct the distributed reservation decision tree.

[0132] In constructing the three-level appointment information library node, first, the job function type (such as attending physician, nurse), skill proficiency (evaluated by historical diagnosis and treatment data combined with machine learning algorithm), professional level (title evaluation information), and work scheduling information (calendar scheduling table structured data) of the staff under each sub-subject are collected, and the current load information of the staff is obtained in real time, such as the number of patients to be treated, the progress of patients in diagnosis, etc. Second, the data cleaning algorithm is used to remove redundant and incorrect data, and the non-structured or semi-structured data is converted into a structured feature vector through the feature engineering algorithm, such as converting the skill proficiency into a quantitative value in the 0-1 interval; third, the B+ tree index algorithm is used, taking the staff ID as the primary key, and taking the job function type, skill proficiency, professional level, work scheduling, and current load information as index fields to construct the three-level appointment information library node. Each node contains data partition index, personnel information hash value, and multi-dimensional labels including department, function, and skill level, realizing fast positioning and efficient retrieval.

[0133] For example, under the surgical sub-subject of a certain hospital, the job function type (such as orthopedic surgery doctor), skill proficiency (based on past orthopedic surgery success rate evaluation), professional level (chief physician), work scheduling (morning outpatient service from Monday to Friday), and current load (3 patients to be seen) of each doctor are collected, and after data cleaning and feature engineering processing, the B+ tree index algorithm is used to construct the three-level appointment information library node, so that the system can quickly filter out doctors who meet the patient's needs and have reasonable load, and finally form a complete distributed secure appointment chain, supporting efficient, intelligent, and secure appointment decisions.

[0134] According to the retrieval key entity semantics and type information, subject code, sub-subject name, sub-subject code, and staff job function type, skill proficiency, professional level, and historical appointment recommendation consistency frequency of each staff contained in the two-level nodes between the distributed appointment decision tree corresponding to each subject and the hierarchical index tree standard semantic question and answer information library, a bidirectional mapping dictionary is constructed through a hash algorithm, and a bidirectional balanced mapping dictionary is obtained through reinforcement learning and load balancing algorithm using work scheduling information and corresponding staff current load information. It needs to be further explained that the bidirectional mapping dictionary defined in this embodiment contains fields such as hospital code, custom department name, and standard department code; when the system interfaces with a new hospital, the semantics of the custom department name is first analyzed by the large model, the standard department code is matched, and then the administrator confirms and writes it into the mapping dictionary.

[0135] It needs to be further explained that the construction process of the bidirectional balanced mapping dictionary in this embodiment includes:

[0136] Firstly, the distributed reservation decision tree corresponding to each subject and the retrieval key entity information of the secondary node in the hierarchical index tree standard semantic question and answer information base are extracted, including subject code (such as hospital number), sub-subject name (such as neurology), sub-subject code (unique identification of department), and staff function type, skill proficiency, occupation level and other data. Combine and splice these information, generate hash value through SHA-256 hash algorithm, construct bidirectional mapping dictionary with hash value as index, associate reservation decision tree and semantic question and answer information base data, and realize fast bidirectional retrieval of information.

[0137] In constructing the bidirectional balanced mapping dictionary, the work scheduling information (such as scheduling period, work period) and current load information (such as remaining number of consultations, average consultation time) of the staff are first obtained from the three-level reservation information base node of the distributed reservation decision tree. A load balancing algorithm based on dynamic weight is used to assign an initial load weight to the staff according to their skill proficiency and occupation level. Staff with high skill proficiency and high occupation level are given higher weight. Combined with the work scheduling information, the scheduling period is subdivided into time slices, and the theoretical number of consultations of each staff in each time slice is calculated. Real-time monitoring of current load information, when the remaining number of consultations of a staff is lower than the threshold, the load weight is reduced; otherwise it is increased. By continuously adjusting the weight, the Hungarian algorithm is used for task allocation optimization, so that the load of the staff in the same period tends to be balanced, and a bidirectional balanced mapping dictionary containing personnel, time and load balance relationship is generated.

[0138] For example, under a certain hospital subject, the neurology department as a secondary node, its disease retrieval information, department code and other data are hashed to construct a bidirectional mapping dictionary with the functions and skills of the department doctors. For the doctors in this department, according to the schedule and real-time consultation situation, the dynamic weight and Hungarian algorithm are used to adjust the consultation tasks of each doctor in different periods, such as distributing 2 of the 5 reservations originally concentrated on C doctor to D doctor with lower load from 10:00 to 11:00 in the morning, and finally forming a bidirectional balanced mapping dictionary that ensures reasonable allocation of resources and improves service efficiency.

[0139] It needs to be further explained that the embodiment constructs a distributed reservation decision tree based on the distributed isolated mapping security chain, replaces the three-level nodes with the functions and skills of the staff, and realizes the rapid retrieval and management of personnel information by combining the B+ tree index algorithm; the bidirectional mapping dictionary constructed by the hash algorithm is associated with the reservation decision tree and the semantic question and answer information library data, which eliminates the semantic ambiguity of the hospital self-defined department name and the standard department code, and supports the semantic conversion of the department across the system; the bidirectional balanced mapping dictionary constructed based on the dynamic weight and the Hungarian algorithm dynamically adjusts the reservation allocation according to the staff scheduling and load condition, and realizes the balanced optimization of personnel load in the same period. The distributed security reservation chain and the bidirectional balanced mapping system formed finally not only realize the full-process digitization from the disease knowledge retrieval to the doctor resource matching, but also improve the utilization rate of medical resources through the load balancing algorithm, ensure that the user obtains accurate and efficient reservation recommendation, and optimize the resource allocation and user experience of medical services.

[0140] Based on the bidirectional balanced mapping dictionary, the cross-system reservation auxiliary connection between the distributed reservation decision tree under each subject and the corresponding secondary nodes of the hierarchical index tree standard semantic question and answer information library is constructed, and the cross-system reservation auxiliary connection is used to connect the hierarchical index tree standard semantic question and answer information library corresponding to each subject under the distributed isolated mapping security chain and all secondary nodes corresponding to the distributed reservation decision tree of the same subject under the distributed security reservation chain in a many-to-many manner, to obtain a double retrieval-reservation security chain.

[0141] Obtain the user retrieval information, obtain the user retrieval semantic association vector and context association vector through the intent analysis model, and determine whether there is reservation demand information;

[0142] If not, input the user retrieval semantic association vector and context association vector into the standard key entity mapping table in the double retrieval-reservation security chain for key entity standardization, perform information retrieval according to the standardized retrieval semantic association vector and context association vector in combination with the distributed isolated mapping security chain, and feed back the retrieved information;

[0143] If there is a reservation requirement, the standardized search semantic association vector and the context association vector are synchronously input to the distributed isolated mapping security chain and the distributed security reservation chain for search and reservation, the searched information is fed back to the corresponding user, at the same time, the searched information is fed back to the distributed security reservation chain through the cross-system reservation auxiliary connection to adjust the reservation result, when different sub-subjects need to be reserved in the searched information, cross-subject association reservation is performed through the cross-subject causal authority connection in the distributed security reservation chain, and the association reservation result is fed back to the corresponding user through a recommendation algorithm; it should be noted that, in the embodiment, through the cross-subject association reservation, when a user asks how to treat diabetes and hypertension, the system analyzes the keywords to match the main department, calls the joint diagnosis and treatment scheme or generates a comprehensive answer through a large model, recommends multi-department registration and prompts the user to consult the doctors of the multi-department. It should be further pointed out that, according to the process, when a user inquires about the treatment of cerebral apoplexy in A hospital, the system recommends the department of cerebral disease, carries the hospital code, the standard department code, the problem semantic label and other parameters through the bidirectional mapping dictionary to jump to the registration system; the registration system calls the distributed reservation decision tree of the hospital according to the parameters, converts the local department ID, and displays the corresponding doctors based on the semantic label, and feeds back the corresponding doctor information to the user for reservation decision.

[0144] If the user mentions that the postoperative pain persists after consulting the orthopedic department, the system recognizes the pain semantic label, automatically associates the pain department and pushes the referral prompt, and asks whether it needs to jump to the registration.

[0145] Based on the information search and reservation or association reservation process of the double search-reservation security chain, cross-system synchronous simulation training is performed through simulation algorithm until the evaluation score of the question and answer search information and the reservation consistency frequency ratio simultaneously satisfy the corresponding threshold value, and the trained double search-reservation security chain is obtained.

[0146] The embodiment realizes the deep integration and safe cooperation of semantic search and intelligent reservation by constructing a double search-reservation security chain, and exhibits multi-dimensional technical advantages and application value in the medical field. First, based on the hierarchical index tree standard semantic question and answer information library, a distributed reservation decision tree is constructed, the three-level nodes are replaced by the functions, skills, scheduling and load of the staff, a distributed security reservation chain is formed, and full-process digital management from knowledge search to resource scheduling is realized, thereby providing accurate reservation decision support for users.

[0147] In terms of information association and mapping, a bidirectional mapping dictionary is constructed through a hash algorithm to achieve bidirectional fast retrieval of semantic question and answer information and reservation decision data, ensuring that the user's retrieved disease information can be accurately associated with the staff with corresponding skills. The bidirectional balanced mapping dictionary constructed based on dynamic weight and Hungarian algorithm can intelligently schedule according to the staff's scheduling and real-time load, effectively balance the workload, and improve resource utilization and service efficiency.

[0148] When processing user retrieval information, it is judged by an intention analysis model whether there is a reservation demand, realizing intelligent diversion of retrieval and reservation. For users who only need information retrieval, standardized retrieval is performed using a standard key entity mapping table and a distributed isolated mapping security chain to ensure the accuracy and consistency of the information; for users with reservation needs, retrieval and reservation are performed simultaneously using a distributed isolated mapping security chain and a distributed security reservation chain, and information interaction and reservation result adjustment are realized through cross-system reservation auxiliary connection, supporting cross-subject associated reservation and meeting the multi-department collaborative needs in complex diagnosis and treatment scenarios.

[0149] Finally, the dual retrieval-reservation security chain is simulated and trained across systems to continuously optimize the evaluation score of question and answer retrieval and the consistency of reservation, ensuring that the system can continuously provide high-quality retrieval and reservation services in actual application, improving user satisfaction and the intelligent level of the system. This complete technical system not only guarantees the security and isolation of data, but also realizes efficient collaboration of knowledge retrieval and resource scheduling, providing strong technical support for intelligent services in the medical field and the like.

[0150] Embodiment 2

[0151] Please refer to Figure 2 Another embodiment provided by the present application is an intelligent customer service information retrieval system based on a large model, which comprises a response module, a retrieval discrimination module, a discrimination result module, a reservation parameter module, a recommendation module, and a discrimination updating module.

[0152] The response module is used to respond to user retrieval information and obtain user retrieval semantic association vectors and context association vectors.

[0153] The retrieval discrimination module, based on the retrieval semantic association vectors and the context association vectors, in combination with a pre-set standard key entity mapping table and a three-level index mapping table built in a pre-set distributed isolated mapping security chain, performs standard question and answer information retrieval judgment on a hierarchical index tree standard semantic question and answer information database configured in each main node of the distributed isolated mapping security chain.

[0154] The discrimination result module returns the standard question and answer search information according to the frequency priority of the search key entity in the search semantic association vector based on the search discrimination result, and when the standard question and answer search information is not searched, generates a question and answer search information sequence and a corresponding evaluation score according to the user search semantic association vector through the pre-trained inference generation model combined with the hierarchical index tree standard semantic question and answer information library, and feeds back the information with the largest evaluation score in all generated question and answer search information to the corresponding user.

[0155] The reservation parameter module is configured to, when the search semantic association vector contains reservation requirements, obtain a cross-system reservation parameter set by combining the standard question and answer search information through the distributed reservation decision tree corresponding to each subject node in the distributed isolated mapping security chain according to the user reservation requirements.

[0156] The recommendation module is configured to obtain recommended reservation information by combining a matching recommendation algorithm through a preset cross-system bidirectional mapping dictionary based on the cross-system reservation parameter set.

[0157] The discrimination update module is configured to collect the frequency of reservation according to the recommended reservation information and the frequency of real reservation of the corresponding user in real time, and obtain a reservation consistency frequency ratio, and if the consistency frequency ratio is less than a preset reservation consistency threshold, then construct and update the recommended mapping information in the bidirectional mapping dictionary and the search index information in the three-level index mapping table according to the real-time reservation information parameters until the reservation consistency threshold is met.

[0158] Embodiment 3

[0159] An electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements an intelligent customer service information retrieval method based on a large model when executing the computer program.

[0160] A computer readable storage medium having computer instructions stored thereon, when the computer instructions are executed, an intelligent customer service information retrieval method based on a large model is executed.

[0161] The embodiments of the application are described above in combination with the drawings, but the application is not limited to the above specific embodiments, the above specific embodiments are only illustrative and not limiting, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments without departing from the purpose of the application and the scope protected by the claims under the inspiration of the application, and these are all within the protection of the application.

[0162] If the technical solutions of the present disclosure involve personal information, the product applying the technical solutions of the present disclosure has clearly informed the personal information processing rules before processing the personal information and has obtained the personal independent consent. If the technical solutions of the present disclosure involve sensitive personal information, the product applying the technical solutions of the present disclosure has obtained the personal independent consent before processing the sensitive personal information and at the same time meets the requirement of "explicit consent". For example, at the personal information collection device such as a camera, a clear and prominent sign is set to inform that the personal information collection range has been entered and the personal information will be collected. If the person voluntarily enters the collection range, it is considered to agree to collect the personal information. Or on the device for processing personal information, through the pop-up information or by asking the person to upload his / her personal information, the personal authorization is obtained under the condition that the obvious sign / information informs the personal information processing rules. The personal information processing rules can include the personal information processor, the purpose of processing personal information, the processing method, the type of processed personal information and other information.

Claims

1. A method for intelligent customer service information retrieval based on a large model, characterized in that, The method comprises the following steps: In response to user retrieval information, a user retrieval semantic association vector and a context association vector are obtained; Based on the retrieval semantic association vector and the context association vector, a pre-set standard key entity mapping table and a three-level index mapping table built in a pre-set distributed isolation mapping security chain are combined to perform standard question and answer retrieval information retrieval judgment on a hierarchical index tree standard semantic question and answer information library configured on each subject node of the distributed isolation mapping security chain; If the retrieval is successful, the standard question and answer retrieval information retrieved is returned according to the frequency priority of the retrieval key entity in the retrieval semantic association vector; If the retrieval is unsuccessful, a pre-trained inference generation model is combined with the hierarchical index tree standard semantic question and answer information library to generate a question and answer retrieval information sequence and a corresponding evaluation score according to the user retrieval semantic association vector, and the information with the maximum evaluation score among all the generated question and answer retrieval information is fed back to the corresponding user. The construction process of the standard key entity mapping table comprises the following steps: Text information and domain standardized text information corresponding to all sub-subjects of each type of subject are obtained, and a pre-trained professional word segmentation model is used for word segmentation preprocessing to obtain a text information space and a domain standardized text information space corresponding to all sub-subjects under each subject; Based on the text information space and the domain standardized text information space corresponding to all sub-subjects under each subject, an entity relationship extraction algorithm is used to obtain a special label key entity vector and a general label key entity vector corresponding to each sub-subject; Cosine formula is used to obtain the clustering distance between each clustering center and all special label key entity vectors, taking each general label key entity vector as a clustering center; Based on all clustering distances corresponding to each clustering center, the truncation distance corresponding to each clustering center is determined, and all truncation distances and clustering distances corresponding to each clustering center are input into a DBSCAN algorithm to obtain a special label clustering mapping table corresponding to each general label; the special label clustering mapping table comprises a general label and a special label sequence under different sub-subjects corresponding to the general label; Based on the special label clustering mapping table corresponding to all general labels and the domain standardized text information space, a causal association analysis model is used to obtain the causal association degree between different special labels under different general labels; Based on the causal association degree between different special labels under different general labels, a bidirectional mapping connection between different general label key entities and corresponding special label key entities is constructed, and a standard key entity mapping table is obtained based on the bidirectional mapping connection and the special label clustering mapping table corresponding to each general label. The construction process of the distributed isolation mapping security chain comprises the following steps: Based on the hierarchical index tree standard semantic question and answer information library corresponding to each subject, a cross-subject security mapping connection and a cross-subject causal authority connection are combined to construct a distributed isolation mapping security chain by using a block chain algorithm and a distributed framework. 2.The large model-based intelligent customer service information retrieval method of claim 1, wherein, The method further comprises the following steps: When the semantic association vector contains a reservation requirement, according to the user reservation requirement, cross-system reservation matching is performed by combining standard question and answer retrieval information through a distributed reservation decision tree corresponding to each subject node in a distributed isolated mapping security chain, and a cross-system reservation parameter set is obtained; Based on the cross-system reservation parameter set, recommended reservation information is obtained by combining a matching recommendation algorithm through a preset cross-system bidirectional mapping dictionary; The frequency of reservation according to the recommended reservation information and the frequency of real reservation of the corresponding user are collected in real time, and a reservation consistency frequency ratio is obtained. If the consistency frequency ratio is less than a preset reservation consistency threshold, then according to the real-time reservation information parameters, the recommended mapping information in the bidirectional mapping dictionary and the retrieval index information in the three-level index mapping table are constructed and updated until the reservation consistency threshold is met. 3.The large model-based intelligent customer service information retrieval method of claim 2, wherein, The construction process of the standard key entity mapping table also includes: Real-time collection of historical text record information and revised domain standardized text information corresponding to all sub-subjects of each type of subject, repeating the above-mentioned construction process of each general label corresponding to the exclusive label clustering mapping table and the bidirectional mapping connection, and updating the standard key entity mapping table through an incremental update model combined with real-time collected information. 4.The large model-based intelligent customer service information retrieval method of claim 3, wherein, The construction process of the distributed isolated mapping security chain also includes: Based on the domain information in the domain standardized text information, a root node is constructed, and a domain classification tree is obtained by combining a knowledge graph and a graph embedding algorithm according to the domain standardized text information, and the domain classification tree is embedded into the root node; Based on the subject, a first-level node is constructed, and a second-level node is constructed by a sub-subject, and a third-level difference database node is constructed by combining a tree database with the text information space, historical question and answer information and configured standard reply information corresponding to each sub-subject under each subject; Based on the domain type corresponding to each subject, a similar subject clustering cluster is obtained through a clustering algorithm, and a first-level index connection between each root node and the first-level nodes in the similar subject clustering cluster is constructed according to the domain type corresponding to the similar subject clustering cluster. 5.The large model-based intelligent customer service information retrieval method of claim 4, wherein, The construction process of the distributed isolated mapping security chain also includes: According to the clustering similarity between the first-level nodes in the similar subject clustering cluster, a cross-subject connection is constructed, and a hierarchical encryption permission hash mapping sequence is obtained based on a hash algorithm and an encryption permission control algorithm by combining the information security protection level, the subject label code and the historical cross-subject retrieval access permission information between the subjects, and the hierarchical private key permission hash mapping sequence in the hierarchical encryption permission hash mapping sequence is mapped to the cross-subject connection between the corresponding subjects to obtain a cross-subject security mapping connection sequence; Based on all second-level node information corresponding to each first-level node and sub-domain type information corresponding to the function information of each second-level node, a second-level index connection is constructed, and similar sub-subject clustering clusters corresponding to similar function sub-subjects and causal correlation degrees between sub-subjects having a causal relationship under each subject are obtained through a clustering algorithm and a causal analysis algorithm through all function information of the second-level nodes. The cross-subject connection between each sub-subject is constructed by using the clustering similarity between each sub-subject in the similar sub-subject clustering cluster, and the causal correlation degree obtained is mapped into the cross-subject connection corresponding to the existing causal relationship, and the hierarchical public key permission hash mapping sequence in the hierarchical encrypted permission hash mapping sequence is mapped into the corresponding cross-subject connection between different subjects, and the cross-subject causal permission connection is obtained. 6.The large model-based intelligent customer service information retrieval method of claim 5, wherein, The construction process of the distributed isolated mapping security chain also includes: The historical search information frequency of each type of key entity stored in the node of the three-level difference database corresponding to each two-level node, the evaluation score of the search feedback question and answer information corresponding to each key entity, and the auxiliary reservation consistency of the search feedback question and answer information are constructed by a hash algorithm to construct a three-level index connection; Based on the root node, the first-level node, the second-level node, the three-level difference database node, the first-level index connection, the second-level index connection, and the third-level index connection, and combining the graph neural network algorithm, the hierarchical index tree standard semantic question and answer information library corresponding to each subject is obtained; Based on the distributed isolated mapping security chain, each sub-field type of the general label key entity in the standard key entity mapping table is mapped into the cross-subject security mapping connection of the corresponding sub-field type, the bidirectional mapping connection is mapped into the cross-subject causal permission connection with the exclusive label clustering mapping table for cross-subject exclusive label association mapping, and the distributed isolated mapping security chain with exclusive label standardization is obtained. 7.The large model-based intelligent customer service information retrieval method of claim 6, wherein, The process of recommending reservation information includes: Based on the distributed isolated mapping security chain with exclusive label standardization, a distributed security reservation chain with the same structure is constructed, and each hierarchical index tree standard semantic question and answer information library corresponding to the three-level difference database node under the distributed isolated mapping security chain is replaced by a three-level reservation information library node constructed by the function type, skill proficiency, occupation level, and work scheduling information of the staff and the current load information of the corresponding staff under the same sub-subject, to obtain a distributed reservation decision tree corresponding to each subject under the distributed security reservation chain. According to the search key entity semantics and type information, the subject code, the sub-subject name, the sub-subject code, and the staff function type, skill proficiency, occupation level, and historical reservation recommendation consistency frequency of each staff contained in the two-level nodes between the distributed reservation decision tree corresponding to each subject and the hierarchical index tree standard semantic question and answer information library, a bidirectional mapping dictionary is constructed by a hash algorithm, and a bidirectional balanced mapping dictionary is obtained by using the work scheduling information and the current load information of the corresponding staff through reinforcement learning and load balancing algorithm. Based on the bidirectional balanced mapping dictionary, a cross-system reservation auxiliary connection between the distributed reservation decision tree and the hierarchical index tree standard semantic question and answer information library corresponding to each two-level node under each subject is constructed, and all two-level nodes corresponding to the hierarchical index tree standard semantic question and answer information library corresponding to each subject under the distributed isolated mapping security chain and the distributed reservation decision tree corresponding to the same subject under the distributed security reservation chain are connected in a many-to-many manner by using the cross-system reservation auxiliary connection, to obtain a double search-reservation security chain. 8.The large model-based intelligent customer service information retrieval method of claim 7, wherein, The process of recommending the appointment information further includes: Obtaining user search information, obtaining user search semantic association vectors and context association vectors through an intent analysis model, and determining whether there is appointment demand information; If there is no appointment demand information, inputting the user search semantic association vectors and the context association vectors into the standard key entity mapping table in the double search-appointment security chain for search key entity standardization, performing information search according to the standardized search semantic association vectors and the context association vectors in combination with the distributed isolation mapping security chain, and feeding back the searched information; If there is appointment demand, synchronously inputting the standardized search semantic association vectors and the context association vectors into the distributed isolation mapping security chain and the distributed security appointment chain for synchronous search and appointment, feeding back the searched information to the corresponding user, feeding back the searched information to the distributed security appointment chain for appointment result adjustment through the cross-system appointment auxiliary connection, when different sub-subjects need to be appointed in the searched information, performing cross-subject association appointment through the cross-subject causal permission connection in the distributed security appointment chain, and feeding back the association appointment result to the corresponding user through a recommendation algorithm; Based on the information search and appointment or association appointment process of the double search-appointment security chain, performing search and appointment cross-system synchronous simulation training through a simulation algorithm until the evaluation score and the appointment consistency frequency ratio of the question and answer search information simultaneously satisfy the corresponding threshold value, and obtaining the trained double search-appointment security chain.

9. The large model-based intelligent customer service information retrieval system for implementing the large model-based intelligent customer service information retrieval method of any one of claims 1-8, characterized in that, It includes: a response module, a search discrimination module, a discrimination result module, an appointment parameter module, a recommendation module, and a discrimination update module; The response module is configured to respond to user search information and obtain user search semantic association vectors and context association vectors. The search discrimination module is configured to, based on the search semantic association vectors and the context association vectors in combination with a pre-set standard key entity mapping table and a built-in three-level index mapping table of a pre-set distributed isolation mapping security chain, perform standard question and answer search information search and judgment on a hierarchical index tree standard semantic question and answer information database configured for each subject node of the distributed isolation mapping security chain. The discrimination result module is configured to, based on the search discrimination result, return the searched standard question and answer search information according to the frequency priority of the search key entity in the search semantic association vectors, when no information is searched, generate a question and answer search information sequence and a corresponding evaluation score according to the user search semantic association vectors through a pre-trained reasoning generation model in combination with the hierarchical index tree standard semantic question and answer information database, and feed back the information with the largest evaluation score in all generated question and answer search information to the corresponding user. The appointment parameter module is configured to, when the search semantic association vectors contain appointment demand, perform cross-system appointment matching on the standard question and answer search information through a distributed appointment decision tree corresponding to each subject node of the distributed isolation mapping security chain according to the user appointment demand, and obtain a cross-system appointment parameter set. The recommendation module obtains the recommended reservation information based on the cross-system reservation parameter set, through a preset cross-system bidirectional mapping dictionary combined with a matching recommendation algorithm; The discrimination updating module is configured to collect the frequency of making reservations according to the recommended reservation information and the frequency of making real reservations in real time, and obtain a reservation consistency frequency ratio. If the consistency frequency ratio is less than a preset reservation consistency threshold, the recommended mapping information in the bidirectional mapping dictionary and the search index information in the three-level index mapping table are constructed and updated according to the real-time reservation information parameters until the reservation consistency threshold is met.

Images