Oled material information retrieval method, system and device

Abstract

The application discloses an OLED material information retrieval method, system and device, and the method comprises the following steps: obtaining current retrieval conditions submitted by a user, wherein the current retrieval conditions comprise one or more preset retrieval sub-conditions, and the preset retrieval sub-conditions are preconfigured in an interactive interface based on different characteristic dimensions; generating a target query statement according to the current retrieval conditions; performing retrieval in a standard material database according to the target query statement to obtain a retrieval result, wherein the standard material database stores a plurality of material data items, and each material data item comprises field information corresponding to different characteristic dimensions; and determining a target material data item according to the retrieval result and displaying the target material data item in the interactive interface. Since the application can dynamically generate a query statement according to multi-dimensional retrieval conditions submitted by a user, the user can flexibly combine different retrieval sub-conditions, thereby accurately locating an OLED material data item meeting specific requirements, and the accuracy and efficiency of material retrieval are effectively improved.

Description

Technical Field

[0001] This application relates to the field of information management technology, and in particular to a method, system and device for retrieval of OLED material information. Background Technology

[0002] Organic light-emitting diodes (OLEDs) are light-emitting devices based on organic materials, widely used in high-end displays, smart wearables, lighting modules, and other fields. OLED devices consist of different functional layers, and their performance is highly dependent on the material selection and energy level coordination of these layers. Therefore, when developing OLED devices, precise selection and interlayer matching of OLED materials are necessary to meet device performance requirements.

[0003] However, while existing OLED material database systems offer some storage and retrieval capabilities for material information, they mostly rely on static attribute displays and typically only support simple queries based on single parameters. This makes it difficult to meet the multi-dimensional and complex material selection needs commonly encountered in OLED device design. Consequently, developers still need to rely on manual methods for repeated trials and comparisons, a cumbersome process that negatively impacts the overall efficiency of OLED device development. Summary of the Invention

[0004] The main purpose of this application is to provide an OLED material information retrieval method, system and device, which aims to solve the technical problem that existing OLED material databases are unable to meet users' multi-dimensional material retrieval needs.

[0005] To achieve the above objectives, this application proposes an OLED material information retrieval method, the method comprising:

[0006] Obtain the current search criteria submitted by the user. The current search criteria include one or more preset search sub-criteria, which are pre-configured in the interactive interface based on different feature dimensions.

[0007] Generate a target query statement based on the current search conditions;

[0008] Data retrieval is performed in the standard material database according to the target query statement to obtain retrieval results. The standard material database stores several material data items, and each material data item includes field information corresponding to the different feature dimensions.

[0009] The target material data item is determined based on the search results, and the target material data item is displayed on the interactive interface.

[0010] In one embodiment, the step of generating a target query statement based on the current search conditions includes:

[0011] When the current search criteria include one or more preset search sub-criteria, obtain the user input field at the preset search sub-criteria;

[0012] The field type of the user input field is determined, and the target retrieval logic corresponding to the field type is selected from the preset field logic mapping relationship. The preset field logic mapping relationship is a pre-set correspondence between preset field types and preset retrieval logic.

[0013] Based on the target retrieval logic and the user input fields, query statement units are generated, and target query statements are formed according to the query statement units. The query statement units include: range query statement units, text query statement units, and structure query statement units.

[0014] In one embodiment, the step of generating query statement units based on the target retrieval logic and the user input fields includes:

[0015] When the target retrieval logic is a range retrieval logic for a corresponding numerical range field, the user input field is converted into a range query statement unit in the database query language;

[0016] When the target retrieval logic is a text matching logic for a corresponding text string field, the user input field is converted into a text query statement unit in the database query language;

[0017] When the target retrieval logic is the similarity matching logic of the corresponding molecular structure field, the script calling instruction is initialized according to the user input field and determined as a structure query statement unit. The script calling instruction is used to call the preset molecular structure similarity calculation script.

[0018] In one embodiment, before the step of retrieving data from a standard materials database according to the target query statement and obtaining the retrieval results, the following steps are included:

[0019] Raw material data is collected from different data sources, and the raw material data is divided into material data sets corresponding to different material names based on the material names;

[0020] According to the structured data template, extract field information of different feature dimensions under the same material name from each of the aforementioned material data sets;

[0021] Based on the feature extraction results, material data items corresponding to different material names are determined, and a standard material database is constructed based on each material data item.

[0022] In one embodiment, after the step of constructing a standard material database based on each of the material data items, the method further includes:

[0023] Receive a structured material data document and parse the structured material data document to obtain new material data items;

[0024] Determine whether a material data item with the same name as the newly added material data item exists in the standard material database;

[0025] If so, determine the target material name and update the newly added material data item to the material data item corresponding to the target material name;

[0026] If not, then determine the name of the new material and add the name of the new material and the corresponding new material data item to the standard material database.

[0027] In one embodiment, the step of retrieving data from a standard materials database according to the target query statement and obtaining the retrieval results includes:

[0028] The range query statement unit and the text query statement unit are executed in the standard material database to obtain initial search results, which include several candidate material data items.

[0029] Determine whether a structured query statement unit exists in the target query statement;

[0030] If so, the target molecular structure code in the user input field and the candidate molecular structure code in the initial search result are input as input parameters to the preset molecular structure similarity calculation script to obtain the similarity calculation result;

[0031] The target material data item is determined from each candidate material data item as the retrieval result based on the preset similarity threshold and the similarity calculation result.

[0032] In one embodiment, the step of determining the target material data item based on the search results and displaying the target material data item on the interactive interface includes:

[0033] The target material data items are preprocessed according to preset display rules to obtain view data;

[0034] Based on the view data, a visualization component is rendered and generated on the interactive interface to display summary information of the target material data item to the user;

[0035] In response to the user's triggering operation on the visualization component, the target material data item is displayed to the user.

[0036] In one embodiment, the feature dimensions include: structural attribute dimension, performance parameter dimension, functional layer purpose dimension, and literature source dimension.

[0037] Furthermore, to achieve the above objectives, this application also proposes an OLED material information retrieval system, the system comprising:

[0038] The multi-dimensional filtering module is used to obtain the current search conditions submitted by the user. The current search conditions include one or more preset search sub-conditions, which are pre-configured in the interactive interface based on different feature dimensions.

[0039] The data retrieval module is used to generate a target query statement based on the current search conditions; perform data retrieval in the standard material database according to the target query statement, and obtain search results. The standard material database stores a number of material data items, and each material data item includes field information corresponding to the different feature dimensions.

[0040] The user interaction module is used to determine the target material data item based on the search results and display the target material data item on the interactive interface.

[0041] In addition, to achieve the above objectives, this application also proposes an OLED material information retrieval device, the device comprising: a memory, a processor, and an OLED material information retrieval program stored in the memory and executable on the processor, the OLED material information retrieval program being configured to implement the steps of the OLED material information retrieval method as described above.

[0042] This application proposes an OLED material information retrieval method, comprising: obtaining current search conditions submitted by a user, the current search conditions including one or more preset search sub-conditions, the preset search sub-conditions being pre-configured in an interactive interface based on different feature dimensions; generating a target query statement based on the current search conditions; performing data retrieval in a standard material database according to the target query statement to obtain search results, the standard material database storing several material data items, each material data item including field information corresponding to different feature dimensions; determining the target material data item based on the search results, and displaying the target material data item in the interactive interface.

[0043] Because this application can dynamically generate query statements based on the multi-dimensional search conditions submitted by the user, users can flexibly combine different search sub-conditions to accurately locate OLED material data items that meet specific needs, effectively improving the accuracy and efficiency of material retrieval, thereby helping to improve the overall efficiency of OLED device development. Attached Figure Description

[0044] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0045] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating the first embodiment of the OLED material information retrieval method of this application;

[0047] Figure 2 This is a flowchart illustrating the second embodiment of the OLED material information retrieval method of this application;

[0048] Figure 3 This is a flowchart illustrating the third embodiment of the OLED material information retrieval method of this application;

[0049] Figure 4 This is a schematic diagram of the module structure of the OLED material information retrieval system of this application;

[0050] Figure 5 This is a schematic diagram of the OLED material information retrieval device of this application.

[0051] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0052] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0053] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0054] This application provides an OLED material information retrieval method, referencing... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the OLED material information retrieval method of this application. In this embodiment, the method includes: steps S10~S40:

[0055] Step S10: Obtain the current search conditions submitted by the user. The current search conditions include one or more preset search sub-conditions, which are pre-configured in the interactive interface based on different feature dimensions.

[0056] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, system server, etc. It can also be other terminal devices that can access the OLED material information retrieval system. This embodiment does not limit this. The following uses a terminal device (referred to as "system") that accesses the OLED material information retrieval system as an example to describe the various embodiments of this application.

[0057] It should be understood that users can log in to the system via links or account registration and initiate search requests through the system's interactive interface. This interface can be a browser webpage or an application interface, and it can be divided into a navigation bar, a search bar, a multi-dimensional filtering area, and a data display area. Here, a browser webpage is used as an example for explanation.

[0058] This multi-dimensional filtering area can be displayed as a drop-down menu, which can include several pre-set search sub-conditions with different feature dimensions based on historical search experience or domain search needs. These feature dimensions can be: structural attribute dimension, performance parameter dimension, functional layer purpose dimension, and literature source dimension.

[0059] It should be understood that the preset search sub-conditions corresponding to the structural attribute dimension may include: structure codes (SMILES), molecular constituent elements, material name, etc.; the preset search sub-conditions corresponding to the performance parameter dimension may include: energy level information (HOMO energy level, LUMO energy level), band gap, photoluminescence quantum efficiency (PLQY), emission wavelength ( EL, PL), spectral width (FWHM), lifetime parameters (delayed / prompt lifetime, single-to-triple level difference ΔE) ST The preset search sub-conditions corresponding to the functional layer application dimension can be functional layer tags, such as: substrate, hole injection layer material (HIM), hole transport layer material (HTM), excitation blocking layer material (EBM), light emitting layer material (EML), electron transport layer material (ETM), electron injection layer material (EIM), and upper and lower electrodes, etc.; the preset search sub-conditions corresponding to the literature source dimension can include: digital object identifier (DOI), journal, author, institution, calculation method, etc.

[0060] In practice, after logging into the system, users can select one or more preset search sub-conditions from the drop-down menu on the interactive interface and fill in the corresponding fields, i.e., user input fields, to form the current search conditions. This enables access to the search from different feature dimensions and multi-dimensional joint search, which meets the user's need for precise screening of material performance in the OLED device design stage.

[0061] For example, the current search criteria can be: filtering materials with "HOMO energy level between -6.0 and -5.5 eV, PLQY > 80%, and functional layer = EML".

[0062] Step S20: Generate a target query statement based on the current search conditions.

[0063] It should be understood that when the system receives the current search criteria submitted by the user, it can parse the user input fields corresponding to each sub-criteria and determine the field type of the user input fields (e.g., numeric range type, text string type, molecular structure type).

[0064] Next, query statements corresponding to different sub-conditions can be dynamically constructed based on the SQL statement templates corresponding to each field type. For example, numeric range fields (such as HOMO -6.0~-5.5 eV) can be converted into BETWEEN statements in SQL; text string fields (functional layer = EML) can be converted into "=" conditions in SQL; and molecular structural fields can be converted into script call instructions in SQL to call Python scripts for molecular similarity matching.

[0065] Finally, the SQL query statements generated by the above sub-conditions can be concatenated using AND logic to obtain the target query statement that can query all the above sub-conditions simultaneously.

[0066] Step S30: Perform data retrieval in the standard material database according to the target query statement to obtain the retrieval results. The standard material database stores several material data items, and each material data item includes field information corresponding to the different feature dimensions.

[0067] It should be noted that the standard materials database is a specialized database that has undergone standardization and structured modeling, storing several material data items. The system can pre-collect material-related data from different data sources or receive data uploaded by administrators, and extract data from the material-related data according to different feature dimensions to obtain the corresponding field information; and encapsulate each field information into different material data items with different material names (IDs).

[0068] Each material data item may include the material name (ID), molecular structure code (SMILES), HOMO / LUMO energy level, band gap (Eg), and emission wavelength (…). EL, Photoluminescence quantum efficiency (PLQY), excited-state energy difference (ΔE) ST Information such as half-maximum width (FWHM), lifetime parameters (prompt / delayed lifetime), functional layer labels, and literature sources.

[0069] It should also be noted that the target query statement can be executed with read-only permissions in the aforementioned standard materials database. The system can configure a dedicated database account with read-only permissions for this target query statement. For example, this account can be restricted to executing only SELECT queries in the database, and not INSERT, UPDATE, DELETE, or other database modification statements. This ensures that even if the target query statement is constructed abnormally, the material data items in the standardized materials database will not be tampered with or corrupted, thus achieving storage security for each material data item.

[0070] In its implementation, the system can use a target query statement to search the standard materials database and return all material data items that match the target query statement.

[0071] Step S40: Determine the target material data item based on the search results, and display the target material data item on the interactive interface.

[0072] It should be understood that the system can perform preprocessing operations such as sorting and pagination on all retrieved material data items, i.e., the target material data items, so as to present the target material data items in a unified format on the interactive interface.

[0073] Furthermore, to specifically illustrate how the target material data items are processed for display to the user in the interactive interface, step S40 also includes: steps S401~S403:

[0074] Step S401: Preprocess the target material data item according to the preset display rules to obtain view data.

[0075] It should be understood that the preset display rules may include field selection rules, data formatting rules, and structural organization rules. The preset display rules can be used to filter and extract view data that can be displayed on the front-end interface from the field information of the target material data item.

[0076] Field selection rules can be rules that filter out a key subset of information from all fields of a target material data item to be displayed in the list summary. For example, this rule can be set to display fields such as "material name, SMILES, HOMO, LUMO, luminescent layer" in the summary, while hiding fields such as "detailed lifetime curve, complete literature list".

[0077] Data formatting rules can be used to convert the raw field information of target material data items into a format that is easy for users to understand or view. For example, the value of HOMO energy level "-5.67" can be formatted as "-5.67 eV", or an excessively long SMILES string can be truncated for display.

[0078] Structure organization rules can package field information processed by field selection rules and data formatting rules into structured data objects (such as JavaScript objects), thereby obtaining an array of data objects, i.e., view data.

[0079] Step S402: Based on the view data, render and generate a visualization component on the interactive interface to display a summary information of the target material data item to the user.

[0080] It should be understood that a visualization component can be a front-end component that graphically displays summary information, and it can be built based on a data list or information card interface (UI) template.

[0081] In practice, the system can use front-end technologies (such as Vue.js and React) to fill different data objects from the above view data into the UI templates corresponding to the front-end components, thereby rendering the front-end components, obtaining visual components, and displaying them to the user in the data display area.

[0082] Step S403: In response to the user's trigger operation on the visualization component, display the target material data item to the user.

[0083] It should be understood that the system can continuously monitor user actions such as clicking or hovering over generated visual components (such as a material card or a row in a table) through a front-end event listening mechanism.

[0084] In its implementation, upon detecting a user's triggered action, the system can determine the corresponding target material data item based on the summary information clicked by the user. Then, it displays all field information of that target material data item in the data display area through pop-ups, drawers, or other means, or directly redirects the user to a new browser page displaying all field information of the target material data item. This achieves an efficient information retrieval and interaction process for the user, avoiding page information redundancy caused by piling up all field information in the data display area, allowing the user to focus on the specific material of interest.

[0085] This embodiment can dynamically generate query statements based on multi-dimensional search conditions submitted by the user, allowing users to flexibly combine different search sub-conditions to accurately locate OLED material data items that meet specific needs, thereby improving the accuracy and efficiency of material retrieval. Simultaneously, by displaying the search results on the interactive interface, users can intuitively view the key information of the target material data items, further enhancing the user experience and ease of operation.

[0086] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the OLED material information retrieval method of this application.

[0087] In this embodiment, to specifically illustrate how to generate the target query statement, step S20 specifically includes: steps S201~S203:

[0088] Step S201: When the current search condition includes one or more preset search sub-conditions, obtain the user input field at the preset search sub-condition.

[0089] It should be understood that each preset search sub-condition can maintain an input box or input option, so that users can select the preset search sub-condition to complete the corresponding field input.

[0090] For example, a user can enter "-6.0~-5.5" in the input box for the HOMO level subcondition and select "EML" in the drop-down option for the functional layer. The user input fields can then include the aforementioned "-6.0~-5.5", "EML", and their corresponding field names "HOMO" and "functional_layer".

[0091] Step S202: Determine the field type of the user input field, and select the target retrieval logic corresponding to the field type from the preset field logic mapping relationship. The preset field logic mapping relationship is a pre-set correspondence between preset field types and preset retrieval logic.

[0092] It should be understood that the preset field logical mapping relationship is a mapping table pre-set by the system. This mapping table pre-defines the retrieval logic corresponding to each field type, including: range retrieval logic corresponding to numerical range fields, text string fields corresponding to text matching logic, and molecular structure fields corresponding to similarity matching logic.

[0093] Among them, numerical range fields can include user input fields corresponding to field names such as HOMO, LUMO, and wavelength; text string fields can include user input fields corresponding to field names such as author, journal, and functional layer label; and molecular structure fields can include user input fields corresponding to the field name SMILES.

[0094] In its implementation, the system can classify the user input fields at each preset search sub-condition, and then query the aforementioned mapping table for the search logic that has a mapping relationship with the determined field type as the target search logic.

[0095] Step S203: Generate query statement units based on the target retrieval logic and the user input fields, and compose a target query statement based on the query statement units.

[0096] It should be understood that the system can generate corresponding query statement units in parallel based on the target retrieval logic for each user input field corresponding to each sub-condition. Query statement units are components of the target query statement, and can include different types: range query statement units, text query statement units, and structured query statement units.

[0097] Furthermore, to illustrate in detail how to generate different types of query statement units, step S203 specifically includes: steps S2031~S2033:

[0098] Step S2031: When the target retrieval logic is a range retrieval logic for a corresponding numerical range field, the user input field is converted into a range query statement unit in the database query language.

[0099] It should be understood that when the user input field is a numeric range field, the corresponding target retrieval logic is a range retrieval logic. The system can directly translate the user-input range field (e.g., -6.0 to -5.5) into a range query clause in the database's native query language (SQL) as a unit of the range query statement.

[0100] For example, the range query clause above could be "WHERE HOMO BETWEEN -6.0 AND -5.5".

[0101] Step S2032: When the target retrieval logic is the text matching logic of the corresponding text string type field, the user input field is converted into a text query statement unit in the database query language.

[0102] It should be understood that when the user input field is a text string, the corresponding target retrieval logic is text matching logic. The system can convert the user input field into an exact match clause or a fuzzy match clause in SQL to serve as a unit of text query statement.

[0103] For example, the exact match clause mentioned above can be "WHERE functional_layer = 'ETL'"; the fuzzy match clause can be "WHERE author LIKE '%Smith%'".

[0104] Step S2033: When the target retrieval logic is the similarity matching logic of the corresponding molecular structure field, the script calling instruction is initialized according to the user input field and determined as a structure query statement unit. The script calling instruction is used to call the preset molecular structure similarity calculation script.

[0105] It should be understood that when the user input field is a molecular structure field, the corresponding target retrieval logic is similarity matching logic. In this case, the system can initialize and call script instructions based on the user input field and determine it as a structural query statement unit.

[0106] It should be noted that this command invokes a pre-defined molecular structure similarity calculation script. This script can be an external Python script pre-configured by the administrator using professional libraries such as RDKit. It calculates the similarity between user-input molecular structure codes (SMILES) and those stored in the database. Furthermore, by setting a similarity threshold, the script can return the material data item that most closely matches the user-input SMILES based on the similarity calculation results.

[0107] For example, the above-mentioned structured query statement unit can be a function call that includes user input SMILES (e.g., CCO) and a similarity threshold (e.g., 0.8), represented as "CALL similarity_search('CCO', 0.8)".

[0108] Furthermore, to specifically illustrate how to perform data retrieval based on the above target query statement, step S30 includes: steps S301~S304:

[0109] Step S301: Execute the range query statement unit and the text query statement unit in the standard material database to obtain initial search results, which include several candidate material data items.

[0110] It should be understood that the system can execute range query statement units and text query statement units within the database to filter out material data items that meet the numerical range conditions and material data items that meet the text matching conditions. Then, material data items that simultaneously meet the numerical range conditions and text matching conditions are identified as candidate material data items, and the initial search results are obtained.

[0111] Step S302: Determine whether there is a structured query statement unit in the target query statement.

[0112] It should be understood that the system can determine whether the search involves a molecular structure similarity matching process. If not, the initial search results can be directly determined as the final search results, that is, the candidate material data items can be determined as the target material data items.

[0113] Step S303: If yes, then the target molecular structure code in the user input field and the candidate molecular structure code in the initial search result are input as input parameters to the preset molecular structure similarity calculation script to obtain the similarity calculation result.

[0114] It should be understood that if this search involves a molecular structure similarity matching process, the target molecular structure code (such as a SMILES string) in the user input field and the candidate molecular structure code corresponding to each candidate material data item can be used as input parameters to call an external preset molecular structure similarity calculation script to perform similarity calculation.

[0115] This external script can calculate the similarity score between the target molecular structure code and each candidate molecular structure code based on molecular fingerprinting or molecular substructure calculation methods, and return a list of similarity calculation results.

[0116] Specifically, when the external script receives the target molecular structure code and a candidate molecular structure code, it can start two different sets of computation logic in parallel: Path A: similarity calculation based on molecular fingerprint; Path B: similarity calculation based on substructure matching.

[0117] In path A, the molecular fingerprints corresponding to the target molecular structure code and the candidate molecular structure code can be calculated separately. A molecular fingerprint is a method of converting a molecular structure into a fixed-length binary vector. Common molecular fingerprints include MACCS bond fingerprints, E-State fingerprints, and Morgan fingerprints.

[0118] Next, the Tanimoto coefficient can be used to calculate the molecular fingerprint similarity between the two molecular fingerprints. The formula for calculating molecular fingerprint similarity using the Tanimoto coefficient is as follows:

[0119]

[0120] Where T(A, B) represents the molecular fingerprint similarity, where A is the molecular fingerprint corresponding to the target molecular structure encoding and B is the molecular fingerprint corresponding to the candidate molecular structure encoding.

[0121] Finally, the above process is repeated to obtain the molecular fingerprint similarity between the target molecular structure code and the molecular structure code of each candidate molecular structure.

[0122] In path B, firstly, the longest common subsequence (LCS) algorithm can be used to obtain the length of the longest common subsequence (LCS_Length) of the target molecular structure code and the candidate molecular structure code, respectively.

[0123] Next, the substructure similarity score can be obtained by calculating the ratio of the length of the longest common subsequence to the lengths of the two molecular structures. The formula for calculating the substructure similarity is as follows:

[0124]

[0125] Where Similarity is the molecular substructure similarity, LCS_Length is the length of the longest common subsequence, Length_molecule1 is the structure length corresponding to the target molecular structure encoding, and Length_molecule2 is the structure length corresponding to the candidate molecular structure encoding.

[0126] Finally, the above process is repeated to obtain the molecular substructure similarity between the target molecular structure code and the code of each candidate molecular structure.

[0127] When obtaining the molecular fingerprint similarity and molecular substructure similarity between the target molecular structure code and each candidate molecular structure code based on paths A and B, respectively, a weighted average fusion method can be used. This involves calculating the weighted average of the molecular fingerprint similarity and molecular substructure similarity according to preset weights (weight w1 for molecular fingerprint similarity and weight w2 for molecular substructure similarity). These preset weights can be pre-defined by the administrator for different types of molecular structure codes, or they can be uniformly set (e.g., w1=50%, w2=50%).

[0128] Furthermore, the target molecular structure encoding can be pre-identified to determine whether it includes pre-defined key functional groups. If so, the molecular substructure similarity can be assigned a higher weight, such as 80% or even 100%. If not, the molecular fingerprint similarity can be assigned a higher weight, such as 60% or 70%. This embodiment does not impose any limitations on this.

[0129] The script will then return a similarity score of T(A, B) * w1 + Similarity * w2, where w1 + w2 = 1.

[0130] Then, the similarity scores can be sorted from high to low, and the material data items corresponding to the candidate molecular structure codes with a similarity score of 0 can be discarded to obtain a list of similarity calculation results.

[0131] Step S304: Determine the target material data item as the retrieval result from each of the candidate material data items based on the preset similarity threshold and the similarity calculation result.

[0132] It should be understood that this preset similarity threshold can be a pre-set value used to determine whether the codes of two molecular structures are sufficiently similar. For example, the threshold can be set to 0.8, in which case two molecular structures are considered similar if the similarity is greater than 0.8.

[0133] In its implementation, the system can filter out the final target material data item from candidate material data items based on the similarity calculation results and a preset similarity threshold. This target material data item can satisfy all of the user's search sub-conditions.

[0134] This embodiment constructs a preset logical mapping relationship for fields, which can convert search conditions of different field types into corresponding query statement units to form the target query statement, thus realizing joint retrieval of multiple feature dimensions. Furthermore, since the target query statement can be constructed based on the query method provided by the database itself and external scripts, the performance bottleneck caused by complex algorithms directly performing a full database scan is solved during retrieval by using a database initial screening and script re-screening mode. This allows the system to quickly respond to complex and compound user queries, further improving the user's material retrieval efficiency.

[0135] Based on the first and second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to that in embodiments one and two above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the OLED material information retrieval method of this application.

[0136] In this embodiment, to specifically illustrate how to construct a standard material database to achieve unified management of material data, before step S30, the following steps are included: S01~S03:

[0137] Step S01: Collect raw material data from different data sources, and divide the raw material data into material data sets corresponding to different material names based on the material names.

[0138] It should be understood that the system can automatically or manually retrieve or import raw material data from multiple heterogeneous data sources, such as scientific journal websites, patent databases, and experimental report files. This raw material data can be in different formats, such as PDF, HTML, and Excel.

[0139] The system can generate unique hash identifiers based on parameters such as material name, wavelength, and energy level, or directly use the material name (ID) as the core identifier to classify the original material data and group related data belonging to the same identifier into the same material data set.

[0140] Step S02: Extract field information of different feature dimensions under the same material name from each of the material data sets according to the structured data template.

[0141] It should be understood that this structured data template is a predefined template used to extract field information of different feature dimensions from the material dataset, including: material name, molecular structure code (SMILES), HOMO / LUMO energy level, emission wavelength, photoluminescence quantum efficiency (PLQY), lifetime parameter, etc.; as well as the data type and unit of each field information (e.g., HOMO energy level, unit eV, numerical type).

[0142] In practice, with the assistance of administrators, the system can find field names and corresponding values ​​of different feature dimensions from unstructured text or semi-structured tables according to structured data templates.

[0143] For example, the system can identify "HOMO = -5.42 eV" from a paper paragraph related to material A and extract the HOMO energy level information as a performance parameter dimension for material A.

[0144] Step S03: Determine the material data items corresponding to different material names based on the feature extraction results, and construct a standard material database based on each material data item.

[0145] It should be understood that the feature extraction results can be field information of different feature dimensions under different material names. This field information of different feature dimensions can be encapsulated into various material data items, thereby realizing the transformation process from material data set to material data item, ensuring that each material data item can contain standardized information of the material name under different feature dimensions.

[0146] In practice, the system can store all extracted material data items in a standardized database, thereby constructing a standard material database.

[0147] Furthermore, to ensure the scalability of the standard materials database, the administrator can also update the data in the standard materials database through document uploads. Therefore, after step S03, steps S04 to S07 are also included:

[0148] Step S04: Receive the structured material data document and parse the structured material data document to obtain the new material data item.

[0149] It should be understood that the system can also provide an administrator backend interface to receive new material documents uploaded by the administrator in standard formats (such as JSON, XML, and EXCEL).

[0150] In its implementation, the system can similarly parse the aforementioned material documents and extract the material data items to obtain the newly added material data items. These newly added material data items can contain new material information or updates to existing material information.

[0151] Step S05: Determine whether there exists a material data item with the same name as the newly added material data item in the standard material database.

[0152] Step S06: If yes, determine the target material name and update the newly added material data item to the material data item corresponding to the target material name.

[0153] Step S07: If not, determine the name of the new material and add the name of the new material and the corresponding new material data item to the standard material database.

[0154] In its implementation, the system can check whether a material data item with the same name as the newly added material data item exists in the standard material database, thereby determining whether the newly added data is an update of an existing record or a new record.

[0155] If a material data item with the same name already exists in the database, the system can update the information of the new material data item into the existing material data item by updating the field value or adding new field information.

[0156] If a material data item with the same name does not exist in the database, the system can add the new material name and its corresponding material data item to the standard material database. This achieves the data update of the standard material database.

[0157] In addition, administrators can also use the aforementioned administrator backend interface to add, delete, or modify fields in different material data items in the standard material database, or restrict access to specific material data items, in order to further ensure the scalability of the standard material database.

[0158] This embodiment aggregates multi-source data based on material names, extracts feature dimension field information based on structured templates, and implements a dynamic maintenance mechanism for updating or adding data in the database through parsing and same-name judgment. This transforms the scattered and heterogeneous original material data into a structured database with a unified parameter system, and ensures that the database can be continuously and accurately updated and expanded. This provides a reliable data foundation for subsequent multi-dimensional intelligent retrieval and solves the problem of low material retrieval efficiency caused by the dispersion, inconsistency and difficulty in maintenance of material data in traditional methods.

[0159] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the OLED material information retrieval method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0160] In addition, this application also provides an OLED material information retrieval system, such as Figure 4 As shown, Figure 4 This is a schematic diagram of the module structure of the OLED material information retrieval system of this application.

[0161] Depend on Figure 4 It is known that the system includes: a multi-dimensional filtering module 401, a data retrieval module 402, and a user interaction module 403.

[0162] The multidimensional filtering module 401 is used to obtain the current search conditions submitted by the user. The current search conditions include one or more preset search sub-conditions, which are pre-configured in the interactive interface based on different feature dimensions.

[0163] The data retrieval module 402 is used to generate a target query statement based on the current search conditions; perform data retrieval in the standard material database according to the target query statement, and obtain search results. The standard material database stores a number of material data items, and each material data item includes field information corresponding to the different feature dimensions.

[0164] User interaction module 403 is used to determine the target material data item based on the search results and display the target material data item on the interactive interface.

[0165] This embodiment can dynamically generate query statements based on the multi-dimensional search conditions submitted by the user, allowing the user to flexibly combine different search sub-conditions to accurately locate OLED material data items that meet specific needs, which is beneficial to improving the accuracy and efficiency of material retrieval.

[0166] This application also provides an OLED material information retrieval device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the OLED material information retrieval method in Embodiment 1 above.

[0167] The following is for reference. Figure 5 , Figure 5This is a schematic diagram of the OLED material information retrieval device of this application. The OLED material information retrieval device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), etc., as well as fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The OLED material information retrieval device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0168] like Figure 5 As shown, the OLED material information retrieval device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the OLED material information retrieval device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the OLED material information retrieval device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows an OLED material information retrieval device with various systems, it should be understood that implementing or having all of the systems shown is not required. More or fewer systems may be implemented alternatively.

[0169] The OLED material information retrieval device provided in this application, employing the OLED material information retrieval method described in the above embodiments, can solve the technical problems of OLED material information retrieval methods. Compared with the prior art, the beneficial effects of the OLED material information retrieval device provided in this application are the same as those of the OLED material information retrieval method provided in the above embodiments, and other technical features in this OLED material information retrieval device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0170] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other elements in the process, method, article, or system that includes that element.

[0171] The sequence numbers of the above embodiments of the present invention are merely for description and do not represent the superiority or inferiority of the embodiments. They are only some embodiments of this application and are not intended to limit the scope of this application. All equivalent structural transformations made under the technical concept of this application and based on the content of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included within the protection scope of this application.

Claims

1. A method for retrieving OLED material information, characterized in that, The method includes: The system retrieves the current search criteria submitted by the user. The current search criteria include one or more preset search sub-criteria, which are pre-configured in the interactive interface based on different feature dimensions. The feature dimensions include: structural attribute dimension, performance parameter dimension, functional layer purpose dimension, and literature source dimension. Generate a target query statement based on the current search conditions; Data retrieval is performed in the standard material database according to the target query statement to obtain retrieval results. The standard material database stores several material data items, and each material data item includes field information corresponding to the different feature dimensions. The target material data item is determined based on the search results, and the target material data item is displayed on the interactive interface; The step of generating the target query statement based on the current search conditions includes: When the current search criteria include one or more preset search sub-criteria, obtain the user input field at the preset search sub-criteria; The field type of the user input field is determined, and the target retrieval logic corresponding to the field type is selected from the preset field logic mapping relationship. The preset field logic mapping relationship is a pre-set correspondence between different preset field types and different preset retrieval logics. Based on the target retrieval logic and the user input field, query statement units are generated, and target query statements are formed according to the query statement units. The query statement units include: range query statement units, text query statement units, and structure query statement units. The step of generating query statement units based on the target retrieval logic and the user input fields includes: When the target retrieval logic is a range retrieval logic for a corresponding numerical range field, the user input field is converted into a range query statement unit in the database query language; When the target retrieval logic is a text matching logic for a corresponding text string field, the user input field is converted into a text query statement unit in the database query language; When the target retrieval logic is the similarity matching logic of the corresponding molecular structure field, the script calling instruction is initialized according to the user input field and determined as a structure query statement unit. The script calling instruction is used to call the preset molecular structure similarity calculation script. The step of retrieving data from the standard materials database according to the target query statement and obtaining the search results includes: The range query statement unit and the text query statement unit are executed in the standard material database to obtain initial search results, which include several candidate material data items. Determine whether a structured query statement unit exists in the target query statement; If so, the target molecular structure code in the user input field and the candidate molecular structure code in the initial search result are used as input parameters and input to the preset molecular structure similarity calculation script for fusion to obtain a similarity calculation result; the similarity calculation result is a weighted average fusion result of molecular fingerprint similarity and molecular substructure similarity; the molecular fingerprint similarity is the similarity between the molecular fingerprint of the target molecular structure code and the molecular fingerprint of the candidate molecular structure code; the molecular substructure similarity is the ratio between the length of the longest common subsequence of the target molecular structure code and the candidate molecular structure code, and the length of the structure corresponding to the target molecular structure code and the length of the structure corresponding to the candidate molecular structure code; The target material data item is determined from each candidate material data item as the retrieval result based on the preset similarity threshold and the similarity calculation result.

2. The method as described in claim 1, characterized in that, Before the step of retrieving data from the standard materials database according to the target query statement and obtaining the search results, the following steps are included: Raw material data is collected from different data sources, and the raw material data is divided into material data sets corresponding to different material names based on the material names; According to the structured data template, extract field information of different feature dimensions under the same material name from each of the aforementioned material data sets; Based on the feature extraction results, material data items corresponding to different material names are determined, and a standard material database is constructed based on each of the material data items.

3. The method as described in claim 2, characterized in that, Following the step of constructing a standard material database based on each of the material data items, the method further includes: Receive a structured material data document and parse the structured material data document to obtain new material data items; Determine whether a material data item with the same name as the newly added material data item exists in the standard material database; If so, determine the target material name and update the newly added material data item to the material data item corresponding to the target material name; If not, then determine the name of the new material and add the name of the new material and the corresponding new material data item to the standard material database.

4. The method as described in claim 1, characterized in that, The step of determining the target material data item based on the search results and displaying the target material data item on the interactive interface includes: The target material data items are preprocessed according to preset display rules to obtain view data; Based on the view data, a visualization component is rendered and generated on the interactive interface to display summary information of the target material data item to the user; In response to the user's triggering operation on the visualization component, the target material data item is displayed to the user.

5. An OLED material information retrieval system, characterized in that, The system includes: The multi-dimensional filtering module is used to obtain the current search conditions submitted by the user. The current search conditions include one or more preset search sub-conditions. The preset search sub-conditions are pre-configured in the interactive interface based on different feature dimensions. The feature dimensions include: structural attribute dimension, performance parameter dimension, functional layer purpose dimension, and literature source dimension. The data retrieval module is used to generate a target query statement based on the current search conditions; perform data retrieval in the standard material database according to the target query statement, and obtain search results. The standard material database stores a number of material data items, and each material data item includes field information corresponding to the different feature dimensions. The user interaction module is used to determine the target material data item based on the search results and display the target material data item on the interactive interface; The data retrieval module is further configured to: obtain the user input field at the preset search sub-condition when the current search condition includes one or more preset search sub-conditions; determine the field type of the user input field; select the target search logic corresponding to the field type from the preset field logical mapping relationship, wherein the preset field logical mapping relationship is a pre-set correspondence between different preset field types and different preset search logics; generate query statement units based on the target search logic and the user input field; and compose a target query statement according to the query statement units, wherein the query statement units include: range query statement units, text query statement units, and structure query statement units; The data retrieval module is further configured to convert the user input field into a range query statement unit in a database query language when the target retrieval logic is a range retrieval logic corresponding to a numerical range type field; convert the user input field into a text query statement unit in a database query language when the target retrieval logic is a text matching logic corresponding to a text string type field; and initialize a script calling instruction based on the user input field and determine it as a structure query statement unit when the target retrieval logic is a similarity matching logic corresponding to a molecular structure type field. The script calling instruction is used to call a preset molecular structure similarity calculation script. The data retrieval module is further configured to execute the range query statement unit and the text query statement unit in the standard material database to obtain initial retrieval results, the initial retrieval results including several candidate material data items; determine whether there is a structure query statement unit in the target query statement; if so, input the target molecular structure code in the user input field and the candidate molecular structure code in the initial retrieval results as input parameters to the preset molecular structure similarity calculation script for fusion to obtain a similarity calculation result; the similarity calculation result is a weighted average fusion result of molecular fingerprint similarity and molecular substructure similarity; the molecular fingerprint similarity is the similarity between the molecular fingerprint of the target molecular structure code and the molecular fingerprint of the candidate molecular structure code; the molecular substructure similarity is the ratio between the longest common subsequence length of the target molecular structure code and the candidate molecular structure code, and the structure length corresponding to the target molecular structure code and the structure length corresponding to the candidate molecular structure code; and determine the target material data item as the retrieval result from each candidate material data item according to the preset similarity threshold and the similarity calculation result.

6. An OLED material information retrieval device, characterized in that, The OLED material information retrieval device includes: a memory, a processor, and an OLED material information retrieval program stored in the memory and executable on the processor. When the OLED material information retrieval program is executed by the processor, it implements the steps of the OLED material information retrieval method as described in any one of claims 1 to 4.

Images