Target product determination method and device, electronic equipment and storage medium

Abstract

Embodiments of the invention provide a target product determination method and apparatus, an electronic device and a storage medium. The method comprises the steps of extracting product information of a product; obtaining a logic constraint condition and a mathematical operation relation aiming at the product information; calculating product attribute data of the product based on the logic constraint condition and the mathematical operation relation; the target product is determined from the products through the product attribute data, a complete industrial product model selection process is achieved, and efficient and accurate model selection is achieved through automatic data extraction, logic constraint and mathematical operation, automatic calculation and intelligent screening.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic product selection, and particularly to a method for determining a target product, an apparatus for determining a target product, an electronic device, and a computer-readable storage medium. Background Art

[0002] In the process of industrial product selection, designers usually need to manually extract multiple parameters from product manuals, such as module, number of teeth, inner hole diameter, etc., and construct a selection relationship based on these parameters. If the selection depends on designers manually extracting parameters from the manual and constructing a selection relationship, it will lead to low selection efficiency and frequent errors. Summary of the Invention

[0003] Embodiments of the present invention provide a method, an apparatus, an electronic device, and a computer-readable storage medium for determining a target product to overcome or at least partially solve the above problems.

[0004] Embodiments of the present invention disclose a method for determining a target product, including:

[0005] Extracting product information of the product;

[0006] Obtaining logical constraint conditions and mathematical operation relationships for the product information;

[0007] Calculating product attribute data of the product based on the logical constraint conditions and the mathematical operation relationships;

[0008] Determining a target product from the products through the product attribute data.

[0009] Optionally, the step of extracting product information of the product includes

[0010] Obtaining image information of a product manual for the product;

[0011] Performing a preprocessing operation on the image information to generate target image information; the preprocessing operation includes at least a grayscale operation, a binarization operation, a denoising operation, and a skew correction operation;

[0012] Performing text region detection on the target image information to determine a text region;

[0013] Performing a character segmentation operation on the text region to extract character features for the text region;

[0014] Generating text information for expressing the product information based on the character features.

[0015] Optionally, it further includes:

[0016] Determine the product type and specification category information for the product;

[0017] Based on the product type and the specification category information, construct and display a product information list for the text information.

[0018] Optionally, before the step of determining the target product from the product through the product attribute data, it further includes:

[0019] Based on preset dimension values, generate a multi-dimensional array using the product attribute data;

[0020] Construct a product attribute database and store the multi-dimensional array in the product attribute database.

[0021] Optionally, the step of determining the target product from the product through the product attribute data includes:

[0022] Obtain the target dimension value input by the user;

[0023] Determine the target product from the product attribute database based on the target dimension value.

[0024] Optionally, it further includes:

[0025] Construct a constraint relation data group using the logical constraint conditions and the mathematical operation relations;

[0026] Store the constraint relation data group.

[0027] Optionally, the step of storing the constraint relation data group includes:

[0028] Determine the storage format and unique identifier for the constraint relation data group;

[0029] Store the constraint relation data group based on the storage format and the unique identifier.

[0030] An embodiment of the present invention also discloses a target product determination device, including:

[0031] A product information extraction module for extracting the product information of the product;

[0032] A logical constraint condition and mathematical operation relation acquisition module for acquiring the logical constraint conditions and mathematical operation relations for the product information;

[0033] A product attribute data calculation module for calculating the product attribute data of the product based on the logical constraint conditions and the mathematical operation relations;

[0034] A target product determination module, configured to determine a target product from the products based on the product attribute data.

[0035] An embodiment of the present invention also discloses an electronic device, including a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus;

[0036] The memory is used to store a computer program;

[0037] When the processor is used to execute the program stored on the memory, the method described in the embodiment of the present invention is implemented.

[0038] An embodiment of the present invention also discloses a computer-readable storage medium, on which instructions are stored. When executed by one or more processors, the processors are caused to execute the method described in the embodiment of the present invention.

[0039] The embodiments of the present invention have the following advantages:

[0040] In the embodiment of the present invention, by extracting product information of the product; obtaining logical constraint conditions and mathematical operation relationships for the product information; calculating product attribute data of the product based on the logical constraint conditions and the mathematical operation relationships; and determining a target product from the products based on the product attribute data, a complete industrial product selection process is realized. Through automated data extraction, logical constraint and mathematical operation, automatic calculation, and intelligent screening, efficient and accurate selection is achieved. Description of the Drawings

[0041] Figure 1 is a flowchart of the steps of a target product determination method provided in an embodiment of the present invention;

[0042] Figure 2 is a schematic diagram of image information of a product specification provided in an embodiment of the present invention;

[0043] Figure 3 is a schematic diagram of a product information list provided in an embodiment of the present invention;

[0044] Figure 4 is a structural block diagram of a target product determination device provided in an embodiment of the present invention;

[0045] Figure 5 is a hardware structural block diagram of an electronic device provided in an embodiment of the present invention;

[0046] Figure 6 is a schematic diagram of a computer-readable medium provided in an embodiment of the present invention. Detailed Embodiments

[0047] To make the above objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] Referring to Figure 1 , a flowchart of the steps of a target product determination method provided in an embodiment of the present invention is shown, which may specifically include the following steps:

[0049] Step 101, extract the product information of the product;

[0050] Step 102, obtain the logical constraint conditions and mathematical operation relationships for the product information;

[0051] Step 103, calculate the product attribute data of the product based on the logical constraint conditions and the mathematical operation relationships;

[0052] Step 104, determine the target product from the product through the product attribute data.

[0053] In the embodiment of the present invention, the product information of the product can be extracted to collect and extract the key information of the product from various different sources (such as product manuals, databases, drawings, etc.). These information are the basis for subsequent selection and calculation.

[0054] By extracting the product information of the product, the system can obtain the basic attributes of the product, such as:

[0055] Geometric dimensions (module, number of teeth, inner hole diameter, etc.); material properties; performance parameters;

[0056] Beneficial effects:

[0057] Provide a data basis for subsequent selection and calculation.

[0058] Realize the digitization and structuring of product information, which is convenient for subsequent processing.

[0059] In the embodiment of the present invention, the logical constraint conditions and mathematical operation relationships for the product information can be obtained;

[0060] Purpose:

[0061] This step aims to clarify the mutual relationships between product attributes, including logical constraints (such as "if... then...") and mathematical operations (such as formula calculations).

[0062] The logical constraint conditions and mathematical operation relationships reflect the internal laws and selection requirements of product design.

[0063] For example:

[0064] Users can define complex logical constraint conditions and mathematical operation relationships;

[0065] Logical constraint: IF (how) type AND (and) modulus THEN (then) number of teeth.

[0066] Mathematical operation relationships: including addition, subtraction, multiplication and other operation relationships.

[0067] For example, the relationship between the inner hole diameter, the modulus and the number of teeth can be inner hole diameter = modulus × number of teeth - constant.

[0068] Beneficial effects:

[0069] Establish an association model between product attributes to ensure the rationality and accuracy of the selection results.

[0070] Realize the automation and intelligence of the selection process and reduce manual intervention.

[0071] Allow users to customize constraint conditions to enhance the flexibility and adaptability of the system.

[0072] An embodiment of the present invention can also calculate the product attribute data of the product based on the logical constraint condition and the mathematical operation relationship, so as to utilize the logical constraint condition and the mathematical operation relationship obtained in step 102, and combine the product information extracted in step 101 to automatically calculate the various attribute data of the product. Through the fast computing power of the computer, complex computing tasks can be efficiently completed.

[0073] In practical applications, product selection refers to selecting the most suitable product from many available products according to specific requirements and conditions. This process usually involves comprehensive evaluation and comparison of multiple aspects such as the function, performance, price, reliability, and compatibility of the product.

[0074] Determining product attribute data is the basis and key of product selection for the following reasons:

[0075] Clarify the selection basis: Product attribute data is the basis for quantifying product performance and characteristics, and can objectively reflect the advantages and disadvantages of the product.

[0076] Achieve precise matching: By comparing product attribute data with requirement parameters, products that meet the requirements can be precisely screened out.

[0077] Improve the selection efficiency: Structured product attribute data is convenient for computer processing and analysis, improving the selection efficiency.

[0078] Reduce selection errors: Accurate product attribute data can avoid selection mistakes caused by incomplete or incorrect information.

[0079] Exemplarily, the various attribute data of the product can be calculated in the following manner.

[0080] It is assumed that the inner hole diameter of the gear is related to the module, number of teeth, and gear shape (type A or type B). For type B gears, the screw hole position is also related to the boss height. In addition, the range of the boss diameter is determined by the inner hole diameter and the root circle diameter. The boss diameter is 3 mm larger than the inner hole diameter and 2 mm smaller than the root circle diameter.

[0081] Identify product information, including data such as the module, number of teeth, root circle diameter, inner hole diameter of the gear, etc., and extract discrete values (e.g., number of teeth: 24, 27, 41, 35).

[0082] The user defines logical constraints and mathematical operation relationships:

[0083] Inner hole diameter = module × number of teeth - 5.

[0084] Boss diameter = inner hole diameter + 3, and, root circle diameter - 2.

[0085] Screw hole position = boss height / 2.

[0086] The system automatically calculates the inner hole diameter and boss diameter of type B gears according to the formula and fills them with the module and number of teeth recognized by OCR. For example, when the module is 0.8 and the number of teeth is 20, the system calculates that the inner hole diameter is 16 mm (0.8 × 20 - 5) and the boss diameter is 19 mm.

[0087] Through the above example, the following beneficial effects can be achieved:

[0088] 1. Clear selection basis:

[0089] In the example, product attribute data such as the "inner hole diameter", "boss diameter", and "screw hole position" of the gear are clear data that can quantify whether the product meets the production requirements. These product attribute data quantify the geometric dimensions and characteristics of the gear and are important bases for selection. Through these data, it is possible to objectively evaluate whether the gear meets the usage requirements.

[0090] 2. Achieve precise matching:

[0091] In the example, through the user-defined mathematical operation relationship (such as "inner hole diameter = module × number of teeth - 5"), the inner hole diameter of the gear can be calculated. By comparing the calculated inner hole diameter with the actual requirements, gears that meet the requirements can be precisely screened. For example, if the required inner hole diameter is 16 mm, gears with a module of 0.8 and a number of teeth of 20 can be screened out.

[0092] 3. Improve selection efficiency:

[0093] In the example, the system automatically recognizes product information through OCR and automatically calculates product attribute data according to formulas. This significantly reduces the workload of manual reference to manuals and calculations, and improves the selection efficiency. Especially when a large number of gears need to be selected, the advantages of this automated selection method are more obvious.

[0094] 4. Reduce selection errors:

[0095] In the example, by automatically calculating and filling data by computer, errors that may occur in manual calculation and input are avoided. For example, when manually calculating the inner hole diameter, calculation errors or data input errors may occur. However, automatic calculation by the system can avoid these errors and improve the accuracy of selection.

[0096] In the embodiments of the present invention, by calculating the product attribute data of the product based on the logical constraint conditions and the mathematical operation relationships, the following beneficial effects are achieved:

[0097] Improve calculation efficiency and accuracy, and avoid errors in manual calculation.

[0098] Realize automatic filling and updating of product attribute data, and reduce repetitive labor.

[0099] Provide complete attribute data for subsequent selection and comparison.

[0100] In the embodiments of the present invention, a target product is determined from the products through the product attribute data, and based on the product attribute data calculated in step 103, combined with the user's selection requirements, a target product that meets the conditions is screened out from all candidate products.

[0101] By setting screening conditions (such as attribute ranges, performance indicators, etc.), quickly locate the best selection result.

[0102] For example, set the inner hole diameter range to screen out gears that meet the conditions.

[0103] In the embodiments of the present invention, a target product is determined from the products through the product attribute data, and the following beneficial effects are achieved:

[0104] Realize automation and intelligence of product selection, and improve selection efficiency.

[0105] According to user needs, provide accurate selection results and improve user satisfaction.

[0106] Support multi-dimensional screening and comparison to help users make the best decision.

[0107] In the embodiment of the present invention, by extracting the product information of the product; obtaining the logical constraint conditions and mathematical operation relationships for the product information; calculating the product attribute data of the product based on the logical constraint conditions and the mathematical operation relationships; and determining the target product from the product through the product attribute data, a complete industrial product selection process is realized. Through automated data extraction, logical constraints and mathematical operations, automatic calculation, and intelligent screening, efficient and accurate selection is achieved.

[0108] Based on the above embodiment, a variant embodiment of the above embodiment is proposed. Here, it should be noted that for the sake of brief description, only the differences from the above embodiment are described in the variant embodiment.

[0109] In an optional embodiment of the present invention, the step of extracting the product information of the product includes obtaining the image information of the product manual for the product;

[0110] Performing a preprocessing operation on the image information to generate target image information; the preprocessing operation at least includes grayscale operation, binarization operation, denoising operation, and skew correction operation;

[0111] Performing text region detection on the target image information to determine the text region;

[0112] Performing a character segmentation operation on the text region to extract the character features for the text region;

[0113] Generating text information for expressing the product information based on the character features.

[0114] OCR (Optical Character Recognition) is a technology that converts the text in an image into machine-readable text. Simply put, OCR technology enables a computer to "understand" the text on a picture and extract it for operations such as editing, searching, and storing.

[0115] The following is a detailed description of the implementation principle of OCR:

[0116] 1. Initial image preprocessing:

[0117] Image acquisition:

[0118] First, obtain the image information of the product manual containing product information through devices such as scanners, digital cameras, or mobile phones.

[0119] Grayscale operation:

[0120] Convert the color image to a grayscale image to simplify subsequent processing.

[0121] Binarization operation:

[0122] Convert the grayscale image to a black-and-white image to highlight the text area.

[0123] Denoising operation:

[0124] Remove the noise in the image to improve the image quality.

[0125] Skew correction operation:

[0126] Correct the skew in the image to ensure that the text is horizontal or vertical.

[0127] After completing the above preprocessing operations, the target image information can be obtained.

[0128] 2. Text area detection and character segmentation:

[0129] Perform text area detection on the target image information:

[0130] Use image processing techniques (such as edge detection, contour analysis) to find the text areas that may be contained in the image.

[0131] Character segmentation operation:

[0132] Segment the detected text areas into individual characters to prepare for character recognition.

[0133] 3. Feature extraction and character recognition:

[0134] Extract the features of the characters, such as:

[0135] Shape features: the contours, strokes, etc. of the characters.

[0136] Statistical features: the pixel distribution of the characters, etc.

[0137] Character recognition:

[0138] Use a classifier (such as a neural network, support vector machine) to recognize the extracted character features.

[0139] There are mainly two recognition methods:

[0140] Pattern matching: Match the character features with the pre-stored character templates.

[0141] Feature extraction: Analyze the features of the characters through an algorithm and compare them with the known character feature database.

[0142] 4. Post-processing:

[0143] Text correction:

[0144] Use a language model and a dictionary to correct the recognition results to improve the recognition accuracy.

[0145] Page layout analysis:

[0146] Analyze the page layout structure of the text and restore the typesetting format of the text.

[0147] Result output:

[0148] Output the recognition result as text information and store it in the database.

[0149] For product manuals, technical documents, etc., OCR can automatically extract information such as product names, models, parameters, etc.

[0150] For the text on product labels and packaging, OCR can automatically recognize information such as production dates, batch numbers, etc.

[0151] In industrial automation, OCR can be used to identify the identification codes on parts to achieve automated material management.

[0152] In an alternative embodiment of the present invention, it further includes:

[0153] Determine the product type and specification category information for the product;

[0154] Based on the product type and the specification category information, construct and display a product information list for the text information.

[0155] Reference Figure 2 , Figure 2 is a schematic diagram of the image information of a product instruction manual provided in an embodiment of the present invention;

[0156] The user uploads the image information of the product instruction manual to the system, and the OCR module automatically scans and recognizes the tables and text information in the manual to generate text information for expressing product information.

[0157] The system extracts and analyzes all product type and specification category information. Exemplarily, assuming the product is a gear, the specification category information can be product attribute data such as gear shape, module, number of teeth, inner hole diameter, material, etc.

[0158] Reference Figure 3 , Figure 3 is a schematic diagram of a product information list provided in an embodiment of the present invention;

[0159] The system can generate a product information list for the text information based on the product type and the specification category information, and display the list to the user to enable the user to check and correct the OCR recognition result.

[0160] In an alternative embodiment of the present invention, before the step of determining the target product from the product through the product attribute data, it further includes:

[0161] Generate a multi-dimensional array using the product attribute data based on a preset dimensional value;

[0162] Construct a product attribute database and store the multi-dimensional array in the product attribute database.

[0163] In practical applications, the embodiments of the present invention can determine the dimensional value for the product attribute data, and based on the dimensional value, generate a dimensional array using the product attribute data, so as to split the product attribute data into multiple dimensional arrays according to the determined dimensional value.

[0164] In a computer system, multi-dimensional arrays are stored in a nested data structure, and different types of data can be expressed in different dimensions. For example, modulus, number of teeth, material, etc. are all data in different dimensions. The embodiments of the present invention can determine the data organization method by determining the dimensional value of the product attribute data. The dimensional value can be used to represent the number of dimensions of the multi-dimensional array. For example, the multi-dimensional array can include one-dimensional array, two-dimensional array, three-dimensional array... n-dimensional array. The two-dimensional array can represent the combination of two dimensions of the modulus and the number of teeth of the product, while the three-dimensional array can store the combination of three dimensions of modulus, number of teeth and material at the same time.

[0165] By determining the dimensional value for the product attribute data, it can provide a basis for constructing a multi-dimensional array or database, ensuring the structuring and standardization of data storage.

[0166] The embodiments of the present invention generate a dimensional array using the product attribute data based on the dimensional value, so as to split the product attribute data into multiple dimensional arrays according to the determined dimensional value, thereby realizing the decomposition of complex product attribute data into smaller and more manageable dimensional arrays and improving the efficiency of data processing.

[0167] The embodiments of the present invention can also construct a database capable of storing and managing product attribute data.

[0168] The database can be a relational database (such as MySQL, PostgreSQL), or a NoSQL database (such as MongoDB), or a simple multi-dimensional array, to provide a unified data storage and management platform for facilitating subsequent data query, update and analysis.

[0169] The embodiments of the present invention can also store the split multi-dimensional array in the product attribute database to ensure the orderliness and structuring of data storage, facilitate subsequent data retrieval and analysis, and realize the multi-dimensional storage and management of product attribute data, improving the efficiency and accuracy of data retrieval.

[0170] Multidimensional management of product attribute data is achieved by specifying dimension values, constructing a database, splitting dimension arrays, and storing data. This provides efficient data support for subsequent product selection, enabling the system to better handle complex product attribute data and improve the efficiency and accuracy of selection.

[0171] Exemplarily, product attribute data can be stored by the following method.

[0172] Suppose it is necessary to store product attribute data of a large number of gears, including module, number of teeth, material, inner hole diameter, etc. This data needs to support fast query and filtering for product selection.

[0173] 1. Determine the server type:

[0174] Data volume and access frequency:

[0175] If the data volume is large (above the million level) and the access frequency is high (support for high-concurrency queries is required), a high-performance server needs to be selected.

[0176] If the data volume is small and the access frequency is low, a server with a lower configuration can be selected.

[0177] Database type:

[0178] If a relational database (such as MySQL, PostgreSQL) is selected, a server that supports relational databases needs to be selected.

[0179] If a NoSQL database (such as MongoDB) is selected, a server that supports NoSQL databases needs to be selected.

[0180] Server configuration:

[0181] CPU: Select the number of CPU cores and main frequency according to the data volume and access frequency.

[0182] Memory: Select the memory size according to the data volume and database type.

[0183] Storage: Select the storage capacity and type (such as SSD, HDD) according to the data volume and data backup strategy.

[0184] Network: Select the network bandwidth according to the access frequency and data transmission volume.

[0185] Example:

[0186] Suppose the data volume is large, the access frequency is high, and a MySQL database is selected, then a cloud server with a higher configuration can be selected, for example:

[0187] CPU: 8 cores and 16 threads

[0188] Memory: 32GB

[0189] Storage: 500GB SSD

[0190] Network: 10Gbps

[0191] 2. Server construction:

[0192] Operating system installation:

[0193] Install an operating system on the server, such as Linux (CentOS, Ubuntu).

[0194] Database installation:

[0195] Install the MySQL database and configure it.

[0196] Database design:

[0197] Design the database table structure according to the dimensions of the product attribute data.

[0198] For example, a table named gears can be created, containing the following fields:

[0199] module (module number)

[0200] teeth (number of teeth)

[0201] material (material)

[0202] bore_diameter (inner hole diameter)

[0203] Data import:

[0204] Import the initial data into the database.

[0205] 3. Store the split multi-dimensional array on the server:

[0206] Data splitting:

[0207] Split the product attribute data into dimensional arrays, for example:

[0208] module_array: [0.5, 0.8, 1.0]

[0209] teeth_array: [20, 25, 30, 35, 40]

[0210] material_array: ["Steel", "Aluminum", "Plastic"]

[0211] Data conversion:

[0212] Convert the dimensional array into a data format that can be stored in a database. For example:

[0213] Convert the array into a JSON-formatted string.

[0214] Data storage:

[0215] Connect to the database through a programming language (such as Python, Java), and store the converted data into a database table.

[0216] For example, the following SQL statement can be used to store data into the gears table:

[0217] INSERT INTO gears(module,teeth,material,bore_diameter)VALUES(0.5,20,"Steel",15);

[0218] INSERT INTO gears(module,teeth,material,bore_diameter)VALUES(0.8,25,"Aluminum",20);

[0219] — Store other data in sequence

[0220] Storage of multi-dimensional arrays:

[0221] In practical applications, the storage of multi-dimensional arrays usually does not directly store the array as a whole into the database, but stores each element in the array as a separate record.

[0222] For example, for a three-dimensional array [module, teeth, material], it can be expanded into multiple records, and each record contains a module, a teeth, and a material.

[0223] Example code:

[0224]

[0225]

[0226] Through the above steps, the product attribute data can be efficiently stored in the server, providing data support for subsequent product selection.

[0227] In an optional embodiment of the present invention, the step of determining the target product from the product through the product attribute data includes:

[0228] Obtain the target dimensional value input by the user;

[0229] Determine a target product from the product attribute database based on the target dimension value.

[0230] In an embodiment of the present invention, a target dimension value input by a user can be obtained; a selection condition input by the user is received, that is, a specific attribute value that the user hopes the target product has. These target dimension values define the specific requirements of the user for the product.

[0231] For example, a user may wish to select a gear with a module of 0.8 and 25 teeth.

[0232] Exemplarily:

[0233] Provide a user-friendly interface that allows the user to input target dimension values.

[0234] Controls such as text boxes, drop-down menus, and sliders can be used to facilitate user input.

[0235] Verify the data input by the user to ensure the validity and correctness of the data.

[0236] Function:

[0237] Clarify the user's selection intention and provide a basis for subsequent screening.

[0238] Implement the interaction between the user and the system, and improve the flexibility and personalization of selection.

[0239] In an embodiment of the present invention, a target product can also be determined from the product attribute database based on the target dimension value, and queries and filters are performed in the product attribute database according to the target dimension value input by the user, so as to find all products that meet the user's selection conditions.

[0240] Exemplarily:

[0241] Use a database query language (such as SQL) or a programming language to construct a query statement according to the target dimension value.

[0242] Execute the query statement in the product attribute database to obtain the query result.

[0243] Process and sort the query results to filter out the optimal target product.

[0244] Function:

[0245] Realize the automation and intelligence of product selection and improve the selection efficiency.

[0246] Provide accurate selection results according to user needs and improve user satisfaction.

[0247] Support multi-dimensional filtering and comparison to help users make the best decision.

[0248] By receiving the target dimension values input by the user and querying and filtering in the database according to these values, the system can accurately find the target products required by the user.

[0249] For example, if the module, number of teeth, and inner hole diameter have been previously stored as a three-dimensional array, and the user inputs the target dimension value "three dimensions", the system will query the database, find all gears related to the module, number of teeth, and inner hole diameter, and present these gears to the user as the target products.

[0250] By receiving the target dimension values input by the user and querying and filtering in the database, the automation and intelligence of product selection are realized. This enables the user to quickly and accurately find the required target products, improving the selection efficiency and user satisfaction.

[0251] Optionally, it further includes:

[0252] Construct a constraint relationship data group by using the logical constraint conditions and the mathematical operation relationships;

[0253] Store the constraint relationship data group.

[0254] In the embodiment of the present invention, the logical constraint conditions and the mathematical operation relationships can be used to construct a constraint relationship data group, and the constraint relationship data group can be stored to achieve the persistent storage of the constraint relationship.

[0255] The user-defined logical constraint conditions and mathematical operation relationships (for example, "if the module = 0.5 and the number of teeth = 20, then the inner hole diameter = module × number of teeth - 5") are stored in the form of a structured data group.

[0256] In this way, these constraint relationships will not be lost due to system restart or user closing the application.

[0257] Reuse and sharing of constraint relationships:

[0258] Store the constraint relationship data group in the database or file system for subsequent quick call by users or the system.

[0259] This means that the user does not need to redefine the same constraint relationships every time, and can reuse the stored constraints, improving work efficiency.

[0260] Moreover, these constraints can be shared. For example, within a company, engineers can use the same constraints to improve work efficiency.

[0261] By using the logical constraint conditions and the mathematical operation relationships to construct a constraint relationship data group and storing the constraint relationship data group, the following beneficial effects can be achieved:

[0262] Improve the selection efficiency: Users can quickly load and apply the stored constraint relationships, avoiding repeated input and saving time. The system can automatically apply these constraints, reducing manual intervention and improving the selection speed.

[0263] Enhance the selection consistency: By storing and reusing constraint relationships, ensure that the selections made by different users or at different times follow the same rules, improving the consistency and reliability of the selection results.

[0264] Support complex selection logic: Complex logical constraints and mathematical operation relationships can be stored for convenient subsequent invocation, enabling the system to handle more complex selection scenarios.

[0265] Facilitate maintenance and management: Centralize the storage of constraint relationship data groups, making it convenient for administrators to maintain and manage.

[0266] Version control can be performed on the constraint relationships, tracking the modification history to ensure data integrity.

[0267] Achieve standardization of selection: For some common or industry-standard selection rules, they can be predefined and stored as constraint relationship data groups for users to directly use, achieving standardization of selection.

[0268] Specific description:

[0269] The constraint relationship data groups can adopt various storage formats, such as JSON, XML, or database tables.

[0270] When storing, a unique identifier can be assigned to each constraint relationship data group for convenient subsequent invocation.

[0271] The system can provide a user interface that allows users to browse, edit, and delete the stored constraint relationship data groups.

[0272] Through the above methods, this step effectively improves the efficiency, consistency, and usability of the product selection system, providing users with a better selection experience.

[0273] To enable those skilled in the art to better understand the embodiments of the present invention, the following uses a complete example to illustrate the embodiments of the present invention.

[0274] Aim to solve the problems of cumbersome and error-prone manual reference to manuals and manual calculation of parameters during the selection process of industrial products. Through the combination of OCR technology, user-defined constraints, and multi-dimensional array storage, achieve the automation and intelligence of product selection.

[0275] Implementation steps:

[0276] 1. Manual input and OCR recognition:

[0277] The user uploads the product manual to the system.

[0278] The OCR module automatically scans and recognizes the table and text information in the manual.

[0279] The system extracts and analyzes the product attribute data (such as module, number of teeth, inner hole diameter, material, etc.).

[0280] The user corrects the OCR recognition result to generate a structured table.

[0281] 2. The user inputs logical and mathematical constraints:

[0282] The user manually inputs logical constraints (such as IF... THEN...) and mathematical operation relationships (such as formulas) in the system interface.

[0283] The system matches these constraints with the data recognized by OCR to generate a multi-dimensional relationship table.

[0284] Example:

[0285] IF module = 0.5 AND number of teeth = 20 THEN inner hole diameter = module × number of teeth - 5

[0286] The screw hole position of type B gear = boss height / 2

[0287] 3. The system automatically calculates and fills:

[0288] The system automatically calculates the product attributes according to the mathematical constraints defined by the user.

[0289] Fills the calculation results into the multi-dimensional relationship table.

[0290] Example:

[0291] When the module is 0.5 and the number of teeth is 20, the system automatically calculates the inner hole diameter to be 15 mm (0.5 × 20 - 5).

[0292] 4. Multi-dimensional array storage:

[0293] The system stores the calculation results and the analyzed data as a multi-dimensional array.

[0294] Convenient for subsequent query and operation by the user.

[0295] Example:

[0296] Three-dimensional array of module, number of teeth, and inner hole diameter:

[0297]

[0298]

[0299] 5. Generate a selection table:

[0300] The system converts a multi-dimensional array into a relational table.

[0301] The user can preview and adjust the selection results in real time.

[0302] The selection table can be exported to Excel or stored in the database.

[0303] Example: Complex mathematical operations in gear selection.

[0304] Background:

[0305] The inner hole diameter of the gear is related to the module, number of teeth, and gear shape (Type A or Type B). The position of the screw hole of the Type B gear is related to the boss height.

[0306] The range of the boss diameter is determined by the inner hole diameter and the root circle diameter.

[0307] The boss diameter is 3 mm larger than the inner hole diameter and 2 mm smaller than the root circle diameter.

[0308] Steps:

[0309] S1. OCR recognizes data:

[0310] The system OCR recognizes data such as the module, number of teeth, root circle diameter, inner hole diameter, etc. Discrete values are extracted (e.g., number of teeth: 24, 27, 41, 35).

[0311] S2. The user defines constraint relationships:

[0312] Inner hole diameter = module × number of teeth - 5

[0313] Boss diameter = inner hole diameter + 3 and root circle diameter - 2

[0314] Screw hole position = boss height / 2

[0315] S3. The system calculates and stores:

[0316] The system automatically calculates the inner hole diameter and boss diameter of the Type B gear.

[0317] It is filled with the module and number of teeth recognized by OCR.

[0318] Example: When the module is 0.8 and the number of teeth is 20, the inner hole diameter is 16 mm and the boss diameter is 19 mm.

[0319] S4. Multi-dimensional array storage:

[0320] The system stores all data as a multi-dimensional array (such as the above example).

[0321] Detailed example explanation:

[0322] Inner hole diameter calculation:

[0323] Formula: Inner hole diameter = module × number of teeth - 5

[0324] Example: When the module is 0.8 and the number of teeth is 20, the inner hole diameter = 0.8 × 20 - 5 = 16 mm

[0325] Calculation of boss diameter:

[0326] Formula: Boss diameter = inner hole diameter + 3 and root circle diameter - 2

[0327] Example: When the inner hole diameter is 16 mm and the root circle diameter is 21 mm, the boss diameter = 16 + 3 = 19 mm, and 21 - 2 = 19 mm

[0328] Calculation of screw hole position:

[0329] Formula: Screw hole position = boss height / 2 (the boss height needs to be obtained by other means)

[0330] The above solution realizes the intelligent product selection through automatic data extraction, user-defined constraints and system automatic calculation. The gear selection implementation example clearly shows how to apply these steps, and through specific formulas and examples, helps users understand the working principle of the system.

[0331] Specific beneficial effects are as follows:

[0332] Mathematical operation support: The system supports complex mathematical operation relationships such as addition, subtraction, and multiplication, allowing users to automatically calculate attribute values through the data recognized by OCR, reducing manual operations.

[0333] Multidimensional array storage: Product attribute data is stored through multidimensional arrays, supporting multi-dimensional data query and selection optimization, and capable of processing a large amount of product selection data.

[0334] Flexible constraint definition: Users can define logical, geometric, and mathematical operation constraints through the system to ensure the accuracy and consistency of product selection.

[0335] Manual correction makes up for the disadvantage that the OCR tool recognition is not completely accurate

[0336] Users manually input the text description in the product manual as logical or mathematical algebraic operation constraints, reducing the system development difficulty.

[0337] It should be noted that, for the method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the described action sequences, because according to the embodiments of the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential for the embodiments of the present invention.

[0338] Referring to Figure 4 , a structural block diagram of a target product determination device provided in an embodiment of the present invention is shown, which may specifically include the following modules:

[0339] A product information extraction module 401, configured to extract product information of a product;

[0340] A logical constraint condition and mathematical operation relationship acquisition module 402, configured to acquire logical constraint conditions and mathematical operation relationships for the product information;

[0341] A product attribute data calculation module 403, configured to calculate product attribute data of the product based on the logical constraint conditions and the mathematical operation relationships;

[0342] A target product determination module 404, configured to determine a target product from the products through the product attribute data.

[0343] For the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0344] In addition, an embodiment of the present invention further provides an electronic device, as Figure 5 shown, including a processor 501, a communication interface 502, a memory 503, and a communication bus 504. Among them, the processor 501, the communication interface 502, and the memory 503 complete mutual communication through the communication bus 504.

[0345] The memory 503 is used to store a computer program;

[0346] The processor 501, when executing the program stored in the memory 503, implements the target product determination method described in any one of the above embodiments:

[0347] The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0348] The communication interface is used for communication between the above terminal and other devices.

[0349] The memory may include a Random Access Memory (RAM), or may also include a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0350] The above-mentioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0351] As Figure 6 shown, in another embodiment provided by the present invention, a computer-readable storage medium 601 is further provided. Instructions are stored in the computer-readable storage medium. When it runs on a computer, it causes the computer to execute the target product determination method described in the above embodiment.

[0352] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the purpose of the present invention and the scope protected by the claims, and all of them belong to the protection scope of the present invention.

[0353] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the embodiments of the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0354] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0355] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0356] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0357] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0358] When the above-mentioned 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 such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may 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 the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0359] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for determining a target product, characterized in that, Including: Extracting product information of the product; Obtaining logical constraint conditions and mathematical operation relationships for the product information; Calculating product attribute data of the product based on the logical constraint conditions and the mathematical operation relationships; Determining a target product from the product through the product attribute data.

2. The method according to claim 1, wherein The step of extracting product information of the product includes Obtaining image information of a product manual for the product; Performing a preprocessing operation on the image information to generate target image information; The preprocessing operation at least includes a grayscale operation, a binarization operation, a denoising operation, and a skew correction operation; Performing text region detection on the target image information to determine a text region; Performing a character segmentation operation on the text region to extract character features for the text region; Generating text information for expressing the product information based on the character features.

3. The method according to claim 2, wherein Also including: Determining product type and specification category information for the product; Based on the product type and the specification category information, constructing and displaying a product information list for the text information.

4. The method according to claim 1, wherein Before the step of determining a target product from the product through the product attribute data, it further includes: Generating a multi-dimensional array using the product attribute data based on a preset dimension value; Constructing a product attribute database and storing the multi-dimensional array in the product attribute database.

5. The method according to claim 4, wherein The step of determining a target product from the product through the product attribute data includes: Obtaining a target dimension value input by a user; Determining a target product from the product attribute database based on the target dimension value.

6. The method according to any one of claims 1 to 5, characterized in that Also including: Constructing a constraint relationship data group using the logical constraint conditions and the mathematical operation relationships; Storing the constraint relationship data group.

7. The method according to claim 6, characterized in that, The step of storing the constraint relationship data group includes: Determining a storage format and a unique identifier for the constraint relationship data group; Storing the constraint relationship data group based on the storage format and the unique identifier.

8. A target product determination device, characterized in that, Including: A product information extraction module for extracting product information of a product; A logical constraint condition and mathematical operation relationship acquisition module for obtaining logical constraint conditions and mathematical operation relationships for the product information; A product attribute data calculation module for calculating product attribute data of the product based on the logical constraint conditions and the mathematical operation relationships; A target product determination module for determining a target product from the product through the product attribute data.

9. An electronic device, characterized in that, Including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete communication with each other through the communication bus; The memory is used for storing a computer program; When the processor is used to execute the program stored on the memory, it implements the method according to any one of claims 1-7.

10. A computer-readable storage medium, on which instructions are stored, and when executed by one or more processors, cause the processors to execute the method according to any one of claims 1-7.

Images