Medical material management system and material management method

Abstract

The invention relates to the technical field of computers, provides a medical automation management scheme, and particularly relates to a medical material management system and a material management method. According to the embodiment provided by the invention, the medical material management system from front to back is established based on the SPD system, and system-level linkage of scene application and material management is realized. Through a material management method configured in the system, the input text information can be updated and enhanced to improve the information expression degree by adopting a natural language processing technology, and a corresponding query statement is determined according to semantic features of the text information and a configured vector database; the query statement is updated and supplemented through the dictionary item set in the system, so that the generated SQL query statement is more complete and accurate, the medical material management level is improved, and a user can quickly and conveniently use different businesses.

Description

Technical Field

[0001] This application relates to the field of computer technology and provides a medical automation management solution, specifically a medical material management system and a material management method. Background Art

[0002] Medical consumables are commonly used products in the field of clinical hospitals, and their importance to hospitals and patients is self-evident. Hospitals generally classify medical consumables into high-value consumables and low-value consumables, and some also classify them into daily-use medical consumables and implantable medical consumables. However, there are a huge number of medical consumables, up to tens of thousands, which are very difficult to manage, and it is also difficult to arrange them neatly and orderly for easy use. Under the traditional hospital management mode, in addition to the warehouse management staff, medical staff also spend a lot of time managing medical consumables, which not only increases the work burden of medical staff, but also easily leads to problems such as loss, expiration, and inventory shortage of consumables, making it difficult to manage medical materials efficiently. In addition, the lack of hospital informatization construction and the lack of authoritative management cases further restrict the improvement of medical material management. Summary of the Invention

[0003] To address the above technical problems, this application provides a medical material management system and a material management method, which can build a management system for medical materials based on the SPD system and combine natural language processing means to achieve automatic understanding and execution of tasks, improve the management level of medical materials, and enable users to quickly and conveniently use different services. To achieve the above objectives, the technical solutions adopted in the embodiments of the present invention are as follows:

[0004] In a first aspect, a medical material management system is provided. The system includes a hospital information system, an SPD system, and a supplier ERP system. The hospital information system is linked to the SPD system through an order integration interface system, and at least one user domain is configured in the hospital information system, and a business domain and a data domain are configured in the order integration interface system. The user domain is used to receive text information initiated by a user and transmit the text information to the business domain. The business domain and the data domain are used to parse the text information and generate corresponding SQL query statements, and generate query results based on the query statements and return them to the user domain or / and the target subsystem in the SPD system. The target subsystem issues corresponding action instructions based on the query results.

[0005] In some specific implementation manners, the data domain includes a vector database and a business database. The vector database deploys a query sample set and a dictionary item set, and the business database deploys a medical data characteristic form and a business data form.

[0006] Second aspect, a medical supply management method is provided. The method is applied to the medical supply management system described in any one of the above, and the method includes: receiving text information sent from the user domain and enhancing and updating the text information to obtain target text information; obtaining semantic information of the target text information, determining the maximum similarity vector between the semantic information and the vector database, and generating an SQL query statement based on the maximum similarity vector; generating a query result based on the corresponding relationship between the SQL query statement and the business database.

[0007] In some specific implementation manners, enhancing and updating the text information includes: decomposing the text information into vectors to obtain a vector representation of the text information; determining an intent classification result corresponding to the text information based on the vector representation and performing intent classification, determining a text template and a process rule based on the intent classification result, and rewriting and updating the text information based on the text template to obtain target text information.

[0008] In some specific implementation manners, rewriting and updating the text information based on the text template includes: determining entity type tags in the text template, and filling the segmentations corresponding to the vector representations with the same entity type tags in the text information into the text template.

[0009] In some specific implementation manners, the method further includes: determining the difference between the entity type tags in the current text information and the entity type tags in the previous round of text information, retrieving the historical SQL query statement generated in the previous round based on the difference, and updating the obtained semantic information based on the historical SQL query statement.

[0010] In some specific implementation manners, updating the obtained semantic information based on the historical SQL query statement includes: encoding the target text information and the historical SQL query statement respectively to obtain corresponding semantic feature information and SQL character vectors.

[0011] In some specific implementation manners, determining the maximum similarity vector between the semantic information and the vector database includes: performing attention calculations on the semantic feature information and the SQL character vectors respectively, concatenating the calculation results after the hidden vector output by the long short-term memory network to obtain a fused query vector, and matching the fused query vector with the vector database.

[0012] In some specific implementation manners, generating the SQL query statement based on the maximum similarity vector includes: determining a query example based on the result corresponding to the maximum similarity vector, and determining the matching item of each field value in the target text information with the dictionary item set, and updating the query example based on the matching item to obtain the SQL query statement.

[0013] In some specific implementation manners, generating the query result based on the corresponding relationship between the SQL query statement and the business database includes: performing rule configuration on the query result based on the process rule.

[0014] In the technical solution provided by the embodiments of the present application, a medical material management system from front to back is built based on the SPD system, realizing the system-level linkage between scenario application and material management. And through the material management method configured in the system, the natural language processing technology can be used to update and enhance the input text information to improve the information expression degree, and determine the corresponding query statement according to the semantic features of the text information and the configured vector database, and update and supplement the query statement through the dictionary item set in the system, so that the generated SQL query statement is more complete and accurate, thereby improving the medical material management level and enabling users to quickly and conveniently use different services. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0016] The methods, systems, and / or programs in the drawings will be further described according to exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, where the example numbers represent similar mechanisms in the various views of the drawings.

[0017] Figure 1 It is a schematic structural diagram of the medical material management system provided by the embodiments of the present application.

[0018] Figure 2 It is a user domain interface view provided by the embodiments of the present application.

[0019] Figure 3 It is a schematic data domain structure diagram provided by the embodiments of the present application.

[0020] Figure 4 It is a schematic flowchart of the medical material management method provided by the embodiments of the present application.

[0021] Figure 5 It is a schematic structural diagram of a management device provided by an embodiment of the present application.

[0022] Figure 6 It is a schematic structural diagram of a terminal device provided by an embodiment of the present application. Detailed implementation manners

[0023] To better understand the above technical solutions, the technical solutions of the present application will be described in detail below through the accompanying drawings and specific embodiments. It should be understood that the specific features in the embodiments of the present application and the embodiments are detailed descriptions of the technical solutions of the present application, rather than limitations on the technical solutions of the present application. Without conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0024] In the following detailed description, many specific details are set forth by way of example in order to provide a thorough understanding of the relevant teachings. However, it will be apparent to those skilled in the art that the present application may be practiced without these details. In other instances, well-known methods, procedures, systems, components, and / or circuits have been described at a relatively high level without detail in order to avoid unnecessarily obscuring aspects of the present application.

[0025] In the present application, flowcharts are used to illustrate the execution processes performed by the systems according to the embodiments of the present application. It should be clearly understood that the execution processes of the flowcharts may not be executed in sequence. On the contrary, these execution processes may be executed in reverse order or simultaneously. Additionally, at least one other execution process may be added to the flowchart. One or more execution processes may be deleted from the flowchart.

[0026] Before further elaborating on the embodiments of the present invention, the nouns and terms involved in the embodiments of the present invention are described. The nouns and terms involved in the embodiments of the present invention are applicable to the following explanations.

[0027] (1) In response to, which is used to represent the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more of the executed operations may be real-time or may have a set delay; without special instructions, there is no limitation on the execution sequence of the multiple executed operations.

[0028] (2) Based on, which is used to represent the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more of the executed operations may be real-time or may have a set delay; without special instructions, there is no limitation on the execution sequence of the multiple executed operations.

[0029] Compared with ordinary commodities, medical consumables have the characteristics of a wide variety, high quality requirements, and large usage, which make their management quite challenging. The management of medical consumables has the following characteristics: (1) A wide variety and lack of standards. Due to the development of medical technology and the progress of medical standards, more and more categories of medical consumables have been developed to treat the diverse diseases of modern people. However, there is currently no clear classification standard for medical devices. Most hospitals classify according to the value of the consumables, which can easily bring many problems to consumable management. (2) Low level of informatization. To improve management efficiency and make management data more visual and accurate, hospitals have gradually adopted information systems to manage medical data, enabling hospitals to more conveniently manage processes such as the procurement, acceptance, warehousing, and outbound of consumables, and reducing the possibility of errors. However, generally large and useful information systems are not taken seriously by many small hospitals due to their high prices and operating costs. The traditional management mode is not only inefficient but also prone to errors and can no longer meet the growing demand for consumable management. (3) Strong timeliness of demand. Medical consumables are different from regular commodities in that they directly affect whether rescue operations can be carried out quickly. Therefore, it is particularly crucial to ensure that demand is met in a timely manner. This means that medical consumables need to maintain a stable inventory to avoid delays in treatment due to out-of-stock situations. Even if there is an out-of-stock situation, replenishment must be carried out quickly to prevent further serious impacts. (4) High quality and safety. The medical industry must ensure the safety of medical consumables, otherwise medical accidents may occur. Therefore, there are extremely high requirements for consumables in terms of quality, temperature, shelf life, etc., and they need to meet specified standards to meet the needs of quality and safety.

[0030] Due to the wide variety of medical consumables, the low level of informatization in some hospitals, and the complex and difficult-to-control structure of the medical supply chain itself, many problems of inaccurate inventory in medical consumable management have occurred. One of the key links in the medical supply chain is the management of medical consumables. With the emergence of the refined management model, hospitals are paying more and more attention to using innovative methods to achieve cost reduction and efficiency improvement. The SPD model is divided into three major business links, namely Supply (supply), Processing (processing), and Distribution (distribution). Under this model, it connects external suppliers or third-party logistics agencies outside the hospital, the hospital's central warehouse, and in-hospital departments, achieving the common coordination and demand inside and outside the medical supply chain. A third-party logistics agency can help the hospital with refined inventory management, and at the same time strengthen the hospital's full-process supervision, reducing the hospital's management costs. The implementation of these three major businesses uses the SPD system of a third-party logistics agency and the HIS system of the hospital to complete the management work simultaneously.

[0031] In view of the current management needs, in the embodiments of this application, a medical material management system based on the SPD model is provided. Refer to Figure 1, Regarding this system 100, it includes a hospital information system 110, an SPD system 120, and a supplier ERP system 130. Among them, the hospital information system 110 establishes a link with the SPD system 120 through an order integration interface system 140, and the SPD system 120 and the supplier ERP system 130 establish a link through an off-campus order integration interface system 150. Among them, the center point of this system is the SPD system, and the central warehouse in the SPD system is responsible for the distribution and replenishment management of drugs and consumables to secondary warehouses or departments. The SPD system will monitor the inventory in real time and replenish the inventory in the hospital in a timely manner when the inventory is insufficient. That is to say, the distribution method has changed from the past pull-type distribution based on demand replenishment to the push-type distribution based on system prediction and calculation. During the distribution process, the SPD central warehouse will actively replenish the secondary warehouse or department. In case of emergency stock shortage, emergency replenishment can also be carried out to meet the demand and ensure the timeliness of material supply and the safety of patients' lives.

[0032] And in order to improve the management fineness of the secondary and tertiary warehouses, intelligent medicine cabinets are set up in each department and ward area of this system, and distribution is carried out with distribution boxes. The intelligent medicine cabinets are set up in the ward area, which can not only store consumables more properly and safely, but also trace the consumption of consumables. Most importantly, it enables medical staff to obtain the required consumables in the shortest time, greatly shortening the response time and improving the service level and efficiency of the hospital. And because the SPD system can accurately predict and record the usage of consumables, it can also provide data support and ordering suggestions for the purchasing department.

[0033] Among them, the hospital information system (HIS) can include the outpatient (emergency) charging system, outpatient and emergency doctor workstations, inpatient billing system, hospital department system, inpatient doctor workstation, nurse workstation, mobile nurse station, and other systems and interfaces; the SPD system includes the outpatient (emergency) pharmacy management system, central pharmacy management subsystem, large warehouse storage management system, configuration center management subsystem, and equipment control system. Among them, the equipment control system is used to control automatic dispensers, automatic medical supply sub-packaging machines, intelligent storage machines, and transmission equipment.

[0034] Specifically, the target subsystem can be understood as the intelligent medicine cabinets set up in each department and ward area. That is, the medical material management system in this embodiment can query the corresponding medical material management situation through the instructions issued by medical staff, and send the target medical materials to the intelligent medicine cabinets in the corresponding departments or ward areas through the target subsystem, so as to realize the overall medical material query and distribution within the hospital area.

[0035] Among them, in this embodiment, the instruction issued by medical staff is different from the prior art in that it can be text information. That is, when issuing tasks, medical staff can input natural text language, and the natural text language is parsed through the order integration interface system to generate corresponding SQL query statements, and the final query and instruction issuance are realized based on the SQL query statements.

[0036] Therefore, in an implementable manner, at least one user domain is configured in the hospital information system, and each user domain corresponds to a business initiator or a department unit for initiating medical services. Among them, the medical services in this embodiment refer to services related to medical supplies and do not include actual medical treatment services. The user domain is connected to the SPD system through the order integration interface system to implement the processing of services, and the processing process of services relies on the business domain and data domain configured in the order integration interface system.

[0037] Specifically, the business domain and data domain receive the natural text language transmitted by the user domain, parse this text information to generate corresponding SQL query statements, and generate query results based on this query statement and return them to the target subsystem in the user domain or / and the SPD system.

[0038] Among them, refer to Figure 2 This is the user domain interface view in this embodiment. The user domain can be understood as the client corresponding to medical staff or unit departments. This client can be built on a small program or an independently deployed application software. A chat interface is configured in this client, and this chat interface includes a session management function. The query records and interaction contents during the user's use are saved, which is convenient for the user to review historical queries during subsequent accesses or continue the previous operations after interruption. Considering that the user may have a need for the visual representation of data, this system has the ability to automatically convert the data in list form in the query results into charts, effectively improving the readability of the data and making data analysis more intuitive and understandable.

[0039] The business domain and data domain are configured in the order integration interface system for parsing the text information input by the user domain and obtaining query results. Among them, the data processing process of the business domain mainly includes enhancing, updating, and parsing the text information, and generating SQL query statements through vector matching and retrieval.

[0040] Refer to Figure 3Regarding the schematic diagram of the data domain structure, in this embodiment, a vector database 310 and a business database 320 are deployed in the data domain 300, which are used to process vector matching and retrieval tasks and effectively manage and query a large amount of medical business data. In the vector database, a query sample set 311 for storing and managing the processing process and a plurality of dictionary item sets 312 for storing various professional terms and classification data are deployed. The business database 320 is constructed based on PostgreSQL, and a plurality of business data tables 321 are deployed, and each business data table contains a plurality of fields. The design of the data tables and fields fully considers the specific requirements and data characteristics of the medical field, reducing the spatio-temporal complexity of the system when processing medical-related queries.

[0041] For the medical material management system provided in this embodiment, a medical material management method is configured in the order integration interface system to implement the processing and result generation of tasks initiated by the user domain. For this method, please refer to Figure 4 , including the following steps:

[0042] Step S41. Receive the text information sent by the user domain and enhance and update the text information to obtain the target text information.

[0043] In this embodiment, the user inputs text information on the terminal. The text information can be understood as natural language. Its expression method and text input content take into account both user habits and expression convenience, and are usually colloquial content. For different users, there are different language expression habits, and the description ability and results of information are also different. And because of the expression method of daily spoken language, the sentences are relatively simple, and there are situations such as abbreviations and aliases, resulting in a large amount of noise in the obtained data information, which needs to be processed and eliminated. And for the problems and query information, its clear description is a relatively strict requirement, because users' cognitions of a certain problem are different, and there may be a problem that a certain detail or knowledge point is naturally defaulted to be known and then ignored. If it is necessary to check whether the input information omits details or conditions, it will be more troublesome in the processing process and affect the use. Moreover, the applicant finds that users often input more words unrelated to the business in the text information, such as modal particles like "ma", "ne", "ya", etc.

[0044] Therefore, based on the problems that occur in the above actual use, in order to make the text information processing faster and more accurate. In this embodiment, a text enhancement and update method is provided to enhance and update the text information sent by the user, so that the input text information is updated to the target text information with lower subsequent processing costs while ensuring that its meaning remains unchanged.

[0045] Among them, the processing logic for text enhancement and update is to determine the intent corresponding to the text information input by the current user, and determine the corresponding text template and process rules according to the intent.

[0046] Specifically, the text template in this embodiment is the logical connection relationship between multiple entities. Through this text template, the important entities extracted from the text information can be recombined to obtain the final target text information. The process rules refer to the processing rules of the business domain. Different intents have different processing logics for the business domain. For example, when the user's intent is to query, the business domain needs to synchronize the information to be queried to the user domain for the user to obtain the information, and its process rule is only to obtain the corresponding query information and synchronize it. When the user's intent is to apply for an item, the corresponding process rule of the business domain is to query the corresponding item information, send the item information to the user domain for secondary confirmation, and based on the feedback result of the secondary confirmation, query the target subsystem related to the item, and issue a requisition work order to the target subsystem in the SPD system.

[0047] Specifically, for the text information enhancement and update in this embodiment, the text information needs to be vectorized first to obtain the vector representation of the text information. The vector representation can be obtained through the Word2Vec word vector model, which is used to convert the text into a high-dimensional vector representation. The Word2Vec word vector model can be implemented using the model structure in the prior art, and will not be elaborated in this embodiment.

[0048] In this embodiment, the corresponding intent of the obtained vector representation is determined through an identification model. The identification model is a converged intent identification model specifically constructed based on the Text-CNN model, including a convolutional layer, a pooling layer, a fully connected layer, and a loss function layer. Among them, for the convolutional layer, one-dimensional convolution is used to receive the input vector representation, and the vector representation is processed by convolutional kernels with sizes of 3, 4, and 5 respectively to obtain text features. And in this embodiment, an activation layer is also set at the output end of the convolutional layer, and an activation function is set to improve the non-linear expression of the network. In this embodiment, the Relu activation function is used as the activation function. After the text features are extracted by the convolutional layer, they are pooled by the pooling layer to retain the important features in the text, effectively reducing the size of the input data, thereby reducing the computational complexity. Among them, the max pooling strategy is selected for the pooling operation in this embodiment. A fully connected layer is set at the last stage of the model, which is used to input the feature vector after pooling into the loss function layer to calculate the probability distribution of each category. Among them, the classification task in this embodiment is a multi-classification task, so the sigmoid is selected as the loss function in this embodiment.

[0049] In this embodiment, through the above processing, the intent classification corresponding to the text information provided by the user can be determined. The text information is updated and reorganized according to its intent classification, and subsequent feedback is determined according to the intent classification.

[0050] In an implementable manner, for the update and reorganization of text information, the corresponding text template is determined through intent classification, and then the text information is rewritten and updated according to the text template to obtain the target text information. Among them, the Prompt template is used for the text template. In this template, entity logical relationships and template bottoms are configured according to different intent classification situations. In this embodiment, the entity type tags in this text template are obtained, and the word segmentation corresponding to the vector representation with the same entity type tag in the text information is filled into the above text template, so as to realize the rewrite and update of the text information. It can be understood that in this embodiment, only the key entities in the text information are retained, and the key entities are used to rewrite the text information based on the entity logical relationships of the text template.

[0051] For example, for the text input: What are the top 3 consumables used in the past month? Through the method proposed in step S41, the intent of this input text information is a query intent, and its key entities are the past month, usage quantity, top three in ranking, and consumables. The text template corresponding to the query intent is called, and the above key entities are filled into the text template, and the updated text obtained is: Query the top three consumables used in the past month. From this case, it can be seen that the text information processed in this step is clearer and more explicit than the input, and the interference caused by non-standard terms is reduced.

[0052] Step S42. Obtain the semantic information of the target text information, determine the maximum similarity vector between the semantic information and the vector database, and generate an SQL query statement based on the maximum similarity vector.

[0053] Regarding step S41, it is used to update the text information input by the user to obtain a more accurate and complete target text information, so as to enhance the understanding of the input text. For the processed target text information, in this embodiment, its corresponding SQL query statement needs to be obtained. In this embodiment, for this purpose, the semantic information of the target text information is first determined, and then the semantic information is determined with the query examples in the configured vector database. Then, each field value in the target text information is matched with the set of dictionary items in the vector database to determine the matching items. Finally, the query examples are updated according to the matching items to obtain the final SQL statement.

[0054] Among them, in this embodiment, the semantic information of the target text information is obtained by using an encoder-decoder structure. However, it should be noted that for the text information input in each round of the multi-round inquiry scenario, there is a correlation. The traditional encoder-decoder structure can only pay attention to the connection between the contexts of the target text information in the current round of inquiry, and there is a loss of the connection between the contexts in the multi-round inquiry scenario. Therefore, in order to make the semantic extraction more accurate, not only the context connection of the current inquiry round needs to be concerned, but also the context connection between the text information in the previous and next inquiry rounds needs to be concerned.

[0055] Therefore, in this embodiment, in order to ensure the accuracy and integrity of semantic extraction, the input of the encoder-decoder structure should include not only the target text information of the current round of inquiry but also the result output processed in the previous round.

[0056] Therefore, in this embodiment, before semantic extraction, it is necessary to determine whether the current inquiry round and the previous inquiry round belong to associated rounds, and determine the accuracy of subsequent semantic information extraction according to the judgment result.

[0057] Specifically, the judgment of whether it belongs to an associated round is determined based on the difference between the entity type tags in the current text information and the entity type tags in the previous round of information. Specifically, if the proportion of the number of different entity type tags corresponding to the current text exceeds the preset threshold compared with the entity type tags in the previous round of text information, it is determined that there is no association between the current text and the previous round of text; otherwise, it is determined that there is an association between the current text and the previous round of text, and the features corresponding to the historical SQL query statement in the previous round need to be combined in this round of processing to obtain a complete semantic feature expression.

[0058] Specifically, first, the encoder-decoder structure corresponding to the multi-round inquiry is described. The main structures of the encoder and decoder in this embodiment are both long short-term memory networks, and an attention mechanism is configured in the decoder. Among them, the long short-term memory network can use the general network in the prior art, and its network structure will not be elaborated in this embodiment.

[0059] Among them, the encoder is used to obtain the semantic feature information corresponding to the target text information. The decoder is used to splice the semantic feature information and the SQL character vector corresponding to the historical SQL query statement based on the attention mechanism, and then splice the calculation result with the hidden vector output by the long short-term memory network to obtain a fused query vector. Finally, the fused query vector is matched with the vector database.

[0060] As can be seen from step S41, the vector representation corresponding to the entity has been obtained in step S41. Although the target text information and the text information change during this processing, the entity in the target text information remains unchanged, and its corresponding vector representation also remains unchanged. Moreover, for the text in the target text information except for the entity, it is configured based on a template, and it has a fixed vector and does not need to be separately extracted during this process and can be directly retrieved. Therefore, in this embodiment, there is no need to perform the process of extracting vector representation in step S42.

[0061] In this embodiment, through the encoder-decoder structure, the fusion query vector corresponding to the target text information can be determined. This fusion query vector includes the query vector corresponding to the current text information and also takes into account the SQL character vector corresponding to the result of the previous round of query.

[0062] Furthermore, for the acquisition of the SQL query statement, the fusion query vector is calculated for similarity with the query sample set in the vector database to obtain the query sample corresponding to the maximum similarity. In this embodiment, the similarity calculation can be implemented by using the methods in the prior art and will not be elaborated in this embodiment. Also, to ensure the integrity of the matching, it is necessary to perform secondary matching and update on the professional terms in the target text information. By parsing the dictionary item fields of each entity in the target text information and performing text similarity matching with the dictionary item set of professional terms, each field value is cyclically checked to see if a matching item with the dictionary value can be found. If the matching is successful, it is then continued to determine whether these dictionary items belong to the collection category. For the collection category dictionary items, each subclass is parsed out and connected using the "OR" logic; for the non-collection category dictionary items, they are directly replaced with the standardized professional terms in the dictionary item set, and the query sample is updated with the standardized professional terms to form the final SQL query statement, effectively solving the problem of inaccurate expression in the text.

[0063] Step S43. Generate a query result based on the corresponding relationship between the SQL query statement and the business database.

[0064] In this embodiment, because the corresponding processing process is different due to different intents. Therefore, for the obtained query statement, in this embodiment, the execution of the SQL query also needs to be configured according to the process rules obtained in step S41, that is, it is necessary to determine whether to only return or issue a command to other target subsystems for execution for the execution of the SQL query.

[0065] If only a return is made, the data tables related to the SQL query are selected, and the structures of the related data tables are incorporated into the returned context information to weaken the interference of irrelevant content and thus reduce the length of the context. If a command needs to be sent to other target subsystems for execution, the related data tables and command symbols are sent to the corresponding target subsystems for the execution of corresponding actions when returning.

[0066] Regarding steps S41 - S43, the embodiments of the present application provide a medical supply management system and management method, which can enhance and improve the information expression degree by updating the input text information, determine the corresponding query statement according to the semantic features of the text information and the configured vector database, and update and supplement the query statement according to the configured set of dictionary items, so that the generated SQL query statement is more complete and accurate, thereby overall improving the management level of medical supplies and enabling users to quickly and conveniently use different services.

[0067] In another implementable manner, referring to Figure 5 , for the method of steps S41 - S43, a virtual management device can also be separately configured to execute it. Regarding this management device 50, it includes:

[0068] A text processing module 51, configured to receive the text information sent by the user and enhance and update the text information to obtain target text information;

[0069] A query generation module 52, configured to obtain the semantic information of the target text information, determine the maximum similarity vector between the semantic information and the vector database, and generate an SQL query statement based on the maximum similarity vector;

[0070] A result generation module 53, configured to generate a query result based on the corresponding relationship between the SQL query statement and the business database.

[0071] Referring to Figure 6, the methods corresponding to steps S41 - S43 can also be integrated into the provided terminal device 60. Due to relatively large differences that may occur in devices due to configuration or performance, it may include one or more processors 601 and a memory 602. One or more applications or data can be stored in the memory 602. Among them, the memory 602 can be transient storage or persistent storage. The applications stored in the memory 602 can include one or more modules (not shown in the figure), and each module can include a series of computer - executable instructions in the terminal device. Further, the processor 601 can be set to communicate with the memory 602 to execute a series of computer - executable instructions in the memory 602 on the terminal device. The terminal device can also include one or more power supplies 603, one or more wired or wireless network interfaces 604, one or more input / output interfaces 605, one or more keyboards 606, etc.

[0072] In a specific embodiment, the terminal device includes a memory and one or more programs. One or more of the programs are stored in the memory, and one or more of the programs can include one or more modules. Each module can include a series of computer - executable instructions for the terminal device and is configured to be executed by one or more processors. The one or more programs include the following computer - executable instructions for:

[0073] Receiving the text information sent from the user domain and enhancing and updating the text information to obtain target text information;

[0074] Obtaining the semantic information of the target text information, determining the maximum similarity vector between the semantic information and the vector database, and generating an SQL query statement based on the maximum similarity vector;

[0075] Generating a query result based on the corresponding relationship between the SQL query statement and the business database.

[0076] Optionally, the processor can execute various functions by running or executing the software program stored in the memory and calling the data stored in the memory, such as executing the Figure 4 method shown above.

[0077] In a specific implementation, as an embodiment, the processor can include one or more microprocessors.

[0078] The memory is used to store the software program for implementing the solution of this application and is controlled by the processor for execution. The specific implementation method can refer to the above - mentioned method embodiments and will not be elaborated here.

[0079] In this application, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or a similar expression means any combination of these items, including any combination of single item(s) or plural item(s). For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0080] It should be understood that in various embodiments of this application, the sequence numbers of the above - mentioned processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this application.

[0081] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0082] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0083] If the described function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer - readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read - only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0084] As described above, it is only the specific implementation manner of this application. However, the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claimed rights.

Claims

1. A medical supplies management system, characterized in that, The system includes a hospital information system, an SPD system, and a supplier ERP system; the hospital information system is linked to the SPD system through an order integration interface system, and at least one user domain is configured in the hospital information system, and a business domain and a data domain are configured in the order integration interface system; the user domain is used to receive text information initiated by a user and transmit the text information to the business domain, and the business domain and the data domain are used to parse the text information and generate corresponding SQL query statements, and after generating a query result based on the SQL query statements, return it to the user domain or / and a target subsystem in the SPD system, and the target subsystem issues corresponding action instructions based on the query result.

2. The medical supply management system according to claim 1, wherein The data domain includes a vector database and a business database. The vector database deploys a query example set and a dictionary item set, and the business database deploys a medical data characteristic form and a business data form.

3. A medical supplies management method, characterized in that, The method is applied to the medical material management system according to any one of claims 1-2, and the method includes: Receiving the text information sent by the user domain and performing enhanced update on the text information to obtain target text information; Obtaining the semantic information of the target text information, determining the maximum similarity vector between the semantic information and the vector database, and generating an SQL query statement based on the maximum similarity vector; Generating a query result based on the corresponding relationship between the SQL query statement and the business database.

4. The medical supply management method according to claim 3, wherein, Performing enhanced update on the text information, including: decomposing the text information into vectors to obtain a vector representation of the text information; and determining the corresponding intent classification result of the text information based on the vector representation for intent classification, and determining a text template and a process rule based on the intent classification result, and rewriting and updating the text information based on the text template to obtain target text information.

5. The medical supply management method according to claim 4, wherein Rewriting and updating the text information based on the text template, including: determining the entity type tags in the text template, and filling the segmentations corresponding to the vector representations with the same entity type tags in the text information into the text template.

6. The medical supply management method according to claim 5, wherein, The method further includes: determining the difference between the entity type tags in the current text information and the entity type tags in the previous round of text information, retrieving the historical SQL query statement generated in the previous round based on the difference, and updating the obtained semantic information based on the historical SQL query statement.

7. The medical supply management method according to claim 6, wherein Updating the obtained semantic information based on the historical SQL query statement, including: encoding the target text information and the historical SQL query statement respectively to obtain corresponding semantic feature information and SQL character vectors.

8. The medical supply management method according to claim 7, wherein Determining the maximum similarity vector between the semantic information and the vector database, including: performing attention calculations on the semantic feature information and the SQL character vectors respectively, concatenating the calculation results after the hidden vector output by the long short-term memory network to obtain a fusion query vector, and matching the fusion query vector with the vector database.

9. The medical supply management method according to claim 3, wherein Generate an SQL query statement based on the maximum similarity vector, including: determining a query example based on the result corresponding to the maximum similarity vector, and determining the matching item of each field value in the target text information with the dictionary item set, and updating the query example based on the matching item to obtain the SQL query statement.

10. The medical supplies management method according to claim 4, characterized in that, Generate a query result based on the corresponding relationship between the SQL query statement and the business database, including: performing rule configuration on the query result based on the process rule.

Images