Self-examination content generation method based on graphic and text database, computer equipment and medium

Abstract

The present application discloses a method for generating self-inspection content based on a graphic database and its equipment and medium. The method determines each target self-inspection area in a store based on the store type and store location, and then determines the target self-inspection questions corresponding to the target self-inspection area and the answer standards corresponding to the self-inspection questions from the standard graphic database. Since the self-inspection content is automatically generated according to the requirements of food safety laws and regulations and internal management systems, it does not require operators to obtain and interpret it, thereby solving the technical problems of narrow acquisition channels and strong professionalism of relevant documents, and poor guidance for practitioners with low cultural levels; in addition, a standard example diagram of the self-inspection content is also given, so that operators can understand food safety laws and regulations and internal management systems more intuitively based on the more instructive standard example diagram, thereby simplifying the store self-inspection content, allowing operators to conduct self-inspections of the store self-inspection areas more conveniently and quickly, and improving the store self-inspection efficiency.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a self-examination content generation method based on a graphic and text database, a computer device, and a storage medium. Background Art

[0002] As people's living standards improve, it is particularly important to inspect food business information of catering service units. Therefore, how to simplify the content of store self-inspection and improve the efficiency of store self-inspection, so as to reduce food safety risks, is an urgent problem to be solved. Summary of the invention

[0003] The present application provides a self-inspection content generation method based on a graphic database, a computer device, and a storage medium, aiming to simplify the store's self-inspection content and improve the store's self-inspection efficiency, thereby reducing food safety hazards.

[0004] In a first aspect, the present application provides a method for generating self-examination content based on a graphic and text database, the method comprising:

[0005] Upon receiving a self-check instruction triggered by a user, obtaining the business place type and business place location of the target place to which the current user belongs, and determining each target self-check area corresponding to the target place based on the business place type and business place location;

[0006] Obtaining target self-inspection questions matching each target self-inspection area in a standard graphic database, so that the user can inspect each target self-inspection area of ​​the target location based on the self-inspection question information;

[0007] Obtaining a standard image instance and a standard text instance corresponding to the target self-examination question from the standard image and text database as a target answer standard, so as to verify the answer to the question uploaded by the user based on the target answer standard;

[0008] Based on the target inspection sequence, the self-inspection question information and the target answer standard, the target self-inspection content corresponding to the current user is generated, so that the user can conduct self-inspection and rectification of his own business premises based on the target self-inspection content.

[0009] The above-mentioned self-inspection content generation method based on the image and text database, when receiving the self-inspection instruction triggered by the user, obtains the business premises type and business premises location of the target place to which the current user belongs, and determines the target self-inspection areas corresponding to the target place based on the business premises type and business premises location; obtains the target self-inspection questions matching the target self-inspection areas in the standard image and text database, so that the user can check the target self-inspection areas of the target place based on the self-inspection question information; obtains the standard image instance and standard text instance corresponding to the target self-inspection question in the standard image and text database as the target answer standard, so as to verify the answer to the question uploaded by the user based on the target answer standard; based on the target inspection order, the self-inspection question information and the target answer standard, generates the target self-inspection content corresponding to the current user, so that the user can self-inspect and rectify his own business premises based on the target self-inspection content. Through the above method, the present application determines each target self-inspection area in the store based on the store type and store location, and then determines the target self-inspection questions corresponding to the target self-inspection area and the answer standards corresponding to the self-inspection questions from the standard image and text database. Since the self-inspection content is automatically generated according to the requirements of food safety regulations and internal management systems, it does not need to be obtained and interpreted by operators, which reduces the professionalism of the relevant documents. In addition, in addition to generating self-inspection content, standard example diagrams of self-inspection content are also given, so that operators can more intuitively understand food safety regulations and internal management systems based on more instructive standard example diagrams, thereby simplifying the store's self-inspection content and allowing operators to conduct self-inspections of store self-inspection areas more conveniently and quickly, improving store self-inspection efficiency, reducing store self-inspection costs, and reducing food safety risks.

[0010] In a second aspect, the present application further provides a self-examination content generation device based on a graphic and text database, the device comprising:

[0011] An inspection area determination module is used to obtain the business place type and business place location of the target place to which the current user belongs when receiving the self-inspection instruction triggered by the user, and determine each target self-inspection area corresponding to the target place based on the business place type and business place location;

[0012] A self-inspection question matching module is used to obtain target self-inspection questions matching each target self-inspection area in a standard image and text database, so that the user can inspect each target self-inspection area of ​​the target place based on the self-inspection question information;

[0013] An answer standard acquisition module, used to acquire a standard image instance and a standard text instance corresponding to the target self-examination question in the standard image and text database as a target answer standard, so as to verify the answer to the question uploaded by the user based on the target answer standard;

[0014] The self-inspection content generation module is used to generate the target self-inspection content corresponding to the current user based on the target inspection sequence, the self-inspection question information and the target answer standard, so that the user can conduct self-inspection and rectification of his own business premises based on the target self-inspection content.

[0015] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor;

[0016] The memory is used to store computer programs;

[0017] The processor is used to execute the computer program and implement the above-mentioned self-check content generation method based on the graphic and text database when executing the computer program.

[0018] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the self-examination content generation method based on a graphic and text database as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For catering practitioners, other drawings can be obtained based on these drawings without any creative work.

[0020] Figure 1 is a structural schematic diagram of a computer device provided in an embodiment of the present application;

[0021] Figure 2 It is a schematic flow chart of a method for generating self-examination content based on a graphic and text database provided in an embodiment of the present application;

[0022] Figure 3 It is a schematic diagram of self-examination questions and their corresponding answer options and pattern examples provided in the embodiment of the present application;

[0023] Figure 4 It is a schematic diagram of an interface of a verification section provided in an embodiment of the present application;

[0024] Figure 5 It is a structural schematic diagram of a self-examination content generation device based on a graphic and text database provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0027] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0028] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0029] See also Figure 1 , Figure 1 1 is a schematic diagram of a computer device 100 provided in an embodiment of the present application. The computer device 100 may include a processor 1001 and a memory 1002, wherein the processor 1001 and the memory 1002 may be connected via a bus, and the bus may be any applicable bus such as an Inter-integrated Circuit (I2C) bus.

[0030] Exemplarily, the computer device 100 may be a server or a terminal. The server may be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. The terminal may be an electronic device such as a smartphone, a tablet computer, a laptop computer, and a desktop computer.

[0031] The memory 1002 may include a storage medium and an internal memory. The storage medium may store an operating system and a computer program. The computer program includes program instructions, which, when executed, may enable the processor 1001 to execute the self-check content generation method based on the graphic database described in any embodiment.

[0032] The processor 1001 is used to provide computing and control capabilities and support the operation of the entire computer device 100 .

[0033] The processor 1001 may be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other types of processors such as programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components. A general-purpose processor may be a microprocessor, or a general-purpose processor may be any conventional processor.

[0034] In one embodiment, the processor 1001 is used to run a computer program stored in the memory 1002 to implement the following steps:

[0035] Upon receiving a self-check instruction triggered by a user, obtaining the business place type and business place location of the target place to which the current user belongs, and determining each target self-check area corresponding to the target place based on the business place type and business place location;

[0036] Obtaining target self-inspection questions matching each target self-inspection area in a standard graphic database, so that the user can inspect each target self-inspection area of ​​the target location based on the self-inspection question information;

[0037] Obtaining a standard image instance and a standard text instance corresponding to the target self-examination question from the standard image and text database as a target answer standard, so as to verify the answer to the question uploaded by the user based on the target answer standard;

[0038] Based on the target inspection sequence, the self-inspection question information and the target answer standard, the target self-inspection content corresponding to the current user is generated. The target self-inspection content is used to instruct the user to self-inspect and evaluate whether each self-inspection area, management and operation of the store comply with food safety regulations and internal management system requirements, so that the user can conduct self-inspection and rectification of his own business premises based on the target self-inspection content.

[0039] In one embodiment, before the processor 1001 is implemented in the standard graphic database to obtain the target self-check questions matching each target self-check area, it is also used to implement:

[0040] Based on the preset crawler rules, crawl the relevant regulations of catering operations in various regions, self-inspection items of various stores, and relevant verification specification examples;

[0041] According to each self-inspection area in each region, the catering business-related regulations, self-inspection items of various stores, and relevant verification specification cases are classified to obtain the self-inspection content and corresponding self-inspection standard text corresponding to each self-inspection area in each region;

[0042] Generate a text standard database based on the self-inspection content corresponding to each self-inspection area in each region and its corresponding self-inspection standard text;

[0043] Collect images and / or videos of various self-inspection areas in various stores, select images and / or videos that meet the self-inspection standard text from the images and / or videos as standard image instances, and generate an image standard database based on the standard instances;

[0044] Establish at least one standard image instance corresponding to each self-check standard text, obtain the correspondence between the text standard database and the image standard database based on the correspondence between the self-check standard text and the standard image instance, and generate the standard image-text database based on the text standard database, the image standard database and the correspondence between the text standard database and the image standard database.

[0045] In one embodiment, the processor 1001 is used to establish at least one standard image instance corresponding to each self-check standard text, obtain the corresponding relationship between the text standard database and the image standard database based on the corresponding relationship between the self-check standard text and the standard image instance, and further implement:

[0046] Selecting at least one keyword corresponding to a self-check standard text, determining associated sentences containing the keywords corresponding to the self-check standard text, and calculating an associated feature vector corresponding to the self-check standard text according to preset associated information and each associated sentence;

[0047] Selecting at least one relevant word corresponding to a standard image instance, determining a relevant sentence containing the relevant word corresponding to the standard image instance, and calculating a relevant feature vector corresponding to the standard image instance according to preset relevant texts and each relevant sentence;

[0048] Importing the associated feature vector corresponding to the self-check standard text into the image standard database, and determining each standard image instance corresponding to each self-check standard text in the image standard database based on the associated feature vector corresponding to each standard image instance in the image standard database;

[0049] Based on each standard image instance corresponding to each self-check standard text, the corresponding relationship between the self-check standard text and the standard image instance is obtained, and based on each self-check standard text and its corresponding standard image instance, the corresponding relationship between the text standard database and the image standard database is obtained.

[0050] In one embodiment, the processor 1001, in implementing the classification of the catering business-related regulations, the self-inspection items of various stores, and the relevant verification specification cases according to the self-inspection areas in various regions, respectively obtains the self-inspection content corresponding to each self-inspection area in each region and its corresponding self-inspection standard text, and is also used to implement:

[0051] Based on at least one first keyword corresponding to each self-inspection area in each region, at least one input text is determined according to the relevant regulations on catering operations, the self-inspection items of various stores, and the relevant verification specification examples, each input text includes multiple words, and each word corresponds to at least one word vector;

[0052] Preprocessing each input text to obtain at least one second keyword corresponding to the catering business-related regulations, the self-inspection items of various stores, and the relevant inspection regulations, wherein the preprocessing includes word segmentation, removal of stop words or punctuation marks, part-of-speech restoration, and word frequency statistics;

[0053] Calculating associations between each of the first keywords and each of the second keywords, and determining at least one corresponding target keyword from each of the second keywords according to the associations;

[0054] According to the at least one target keyword, determining at least one associated sentence in the catering business-related regulations, the self-inspection items of various stores, and the relevant verification specification examples, wherein each associated sentence includes at least one target keyword;

[0055] The associated sentences are determined as the self-inspection contents corresponding to each self-inspection area in each region and the corresponding self-inspection standard texts.

[0056] In one embodiment, after implementing the step of determining the associated sentences as the self-examination contents corresponding to the self-examination areas in each region and the self-examination standard texts corresponding thereto, the processor 1001 is further configured to implement:

[0057] Based on the self-inspection content corresponding to each self-inspection area in each region and its corresponding self-inspection standard text, generate the verification section corresponding to each self-inspection area, and generate each self-inspection question in each verification section according to different related sentences;

[0058] When the current user's answer information to each self-examination question is received, each self-examination question is diagnosed based on each self-examination standard text and each corresponding standard image instance, and a diagnosis report corresponding to each self-examination area is generated.

[0059] In one embodiment, before the processor 1001 implements the step of diagnosing each self-examination question based on each self-examination standard text and each corresponding standard image instance upon receiving the answer information of the current user to each self-examination question, and generating a diagnosis report corresponding to each self-examination area, it is further configured to implement:

[0060] Collecting non-standard instances of each self-inspection area corresponding to each type of store, and collecting rectification process information of each type of store from non-standard to standard self-inspection area, wherein the rectification process information includes comparison pictures before and after rectification;

[0061] Based on the comparison charts before and after the rectification, answer options corresponding to each self-examination question are generated, so that the current user can make selections based on the situation of his own store to generate corresponding answer information.

[0062] In one embodiment, before the processor 1001 generates the target self-inspection content corresponding to the current user based on the target inspection sequence, the self-inspection question information, and the target answer standard so that the user can self-inspect and rectify his own business premises based on the target self-inspection content, it is also used to implement:

[0063] Obtaining relative position information of the current user in an area corresponding to the target location, and obtaining a self-checking area in the target location;

[0064] Determine a path calculation algorithm based on the selection operation of the current user, and calculate a target self-check path with the relative position information as the starting point and each self-check area in the target location as each target point;

[0065] The target inspection sequence is generated according to the sequence of the self-inspection areas in the target location in the target self-inspection path.

[0066] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0067] See also Figure 2 , Figure 2is a schematic flow chart of a method for generating self-check content based on a graphic database provided in an embodiment of the present application. Figure 2 As shown, the method for generating self-examination content based on a graphic and text database may include steps S101 to S104.

[0068] Step S101: upon receiving a self-check instruction triggered by a user, obtaining the business place type and business place location of the target place to which the current user belongs, and determining each target self-check area corresponding to the target place based on the business place type and business place location;

[0069] It should be noted that the user in this embodiment is a store operator. The type of business premises and the location of the business premises of the target place can be obtained based on the store logo. The store logo can be obtained directly or indirectly. Direct acquisition is based on the unique identification information provided by the store for identification, which can be directly input by the user or identified by uploaded documents. Indirect acquisition is determined through intelligent question and answer with the user. When directly acquired, it can be further verified through the Internet to further determine the correctness of the information. Indirect acquisition can facilitate users of unregistered stores to obtain and authenticate store information, reducing food safety risks caused by unregistered or unlicensed stores in society.

[0070] In some embodiments, before obtaining the food business information of the operator through the above indirect method, the method further includes:

[0071] Display a welcome interface, wherein the welcome interface displays a welcome message and a prompt for obtaining food business information, wherein the prompt for obtaining food business information is used to prompt the operator to enter the unique identification information of the enterprise, wherein the unique identification information of the enterprise includes at least one of the following: a unified social credit code, a business license number, an organization code, a tax registration number, a bank account opening license number, and a company name;

[0072] Obtain the food business license of the enterprise in the background based on the unique identification information of the enterprise entered by the operator;

[0073] If the acquisition is successful, the main business format and business items will be extracted according to the food business license;

[0074] If the acquisition fails, the food business information intelligent acquisition option and the license intelligent image recognition option are displayed on the welcome interface;

[0075] If it is detected that the operator has selected the option of intelligently obtaining the food business information, the program will jump to the main business interface and obtain the food business information of the operator in the above-mentioned indirect manner;

[0076] If it is detected that the operator has selected the smart image recognition option of the license, the operator is prompted to upload the food business license, and the operator's food business information is extracted based on the food business license uploaded by the operator.

[0077] It can be seen that in the embodiment of the present application, before obtaining the operator's food business information indirectly, it is first determined whether the operator's food business information can be obtained directly, which is more accurate than food business information obtained indirectly; the direct method of obtaining the operator's food business information is first to see whether it is possible to directly obtain the company's unique identification information, and then obtain the company's food business license in the background based on the unique identification information. It is difficult for the operator to carry the food business license with him / her, which can save the operator's time in looking for the food business license and improve work efficiency; when the acquisition fails, the operator's food business information is extracted through the food business license uploaded by the operator, and the operator does not need to check the food business information on the food business license and then manually enter it, which can also improve work efficiency.

[0078] The type of business premises refers to the main business format of the store, which means the type of business or operating model that the store mainly engages in during its operation.

[0079] Displaying the main business format options on the main business format interface, wherein the main business format options include food sales operator options, catering service operator options, and unit canteen options;

[0080] Entering a corresponding main business format option details display interface according to the operator's selection operation of the main business format option, and displaying a blank of the business premises area in the question inquiry area of ​​the main business format option details display interface;

[0081] The specific category of the operator's main business format is determined based on the area filled in by the operator for the business premises area, and an example diagram of the business premises layout and equipment arrangement is displayed based on the specific category of the main business format.

[0082] Among them, food sales operators are mainly responsible for selling pre-packaged food or bulk food directly to consumers, and their main business formats include at least one of the following: wholesalers that mainly sell food, shopping malls and supermarkets, convenience stores, specialty stores, concurrent food stores, concurrent drug stores, grocery stores, food traders, Internet food sales operators without physical stores, operators who use automatic equipment to sell food, and headquarters of food sales chain enterprises, etc. Catering service operators refer to service providers that provide food and beverages prepared on site and consumed immediately, and their main business formats include at least one of the following: large restaurants that mainly prepare and sell food, medium-sized restaurants, small restaurants, central kitchens, collective dining distribution units, pastry shops, beverage shops, small restaurants, snack shops, non-ready-to-eat food preparation and sales stores, operators who use automatic equipment to prepare and sell food, headquarters of catering service chain enterprises, catering service management companies, and other catering operators, etc. Canteens for centralized dining units usually refer to places set up within schools, enterprises, and institutions to provide collective dining services for students or employees. The specific categories of their main business formats include at least one of the following: school canteens, canteens for childcare institutions, canteens for nursing institutions, canteens for care institutions, canteens for medical institutions, canteens for confinement centers, canteens for childcare institutions, canteens for the elderly, canteens for training institutions, canteens for off-campus care institutions, canteens for government agencies and institutions, enterprise canteens, construction site canteens, and other canteens.

[0083] In some embodiments, the user may be asked about the production and operation site information through intelligent dialogue, and the production and operation site information includes generating an example diagram of the business site layout and equipment layout. The method may include:

[0084] In the question area of ​​the main business option details display interface, ask the user whether to choose to upload the layout diagram of the production and operation site;

[0085] If yes, receiving the layout diagram of the production and operation site uploaded by the user;

[0086] If not, fill in the blanks for the area of ​​production and operation sites in the question area of ​​the main business option details display interface;

[0087] The specific category of the operator's main business (i.e., the type of business premises) is determined based on the area filled in by the user for the production and operation site, for example, a restaurant, dining room, fast food restaurant, cafe, snack bar, bar, and an example diagram of the business premises layout and equipment arrangement is displayed and generated based on the specific category of the main business.

[0088] Among them, the example diagram of the business premises layout and equipment layout can change dynamically with the area input by the operator. If the area is within the area range of micro-catering, the example diagram of the business premises layout and equipment layout is the example diagram of the business premises layout and equipment layout of micro-catering; if the area is within the area range of small-sized catering, the example diagram of the business premises layout and equipment layout is the example diagram of the business premises layout and equipment layout of small-sized catering; if the area is within the area range of medium-sized catering, the example diagram of the business premises layout and equipment layout is the example diagram of the business premises layout and equipment layout of medium-sized catering. The example diagram of the business premises layout and equipment layout of the corresponding surface is displayed in real time through dynamic changes, which is convenient for operators to compare, determine and adjust, so as to find a place that suits their actual operation, so that the information of the production and operation site is more accurate.

[0089] It can be seen that in the embodiment of the present application, even if the user does not upload a layout map of the production and operation site, an approximate layout map of the production and operation site can be generated through intelligent dialogue, which is conducive to the subsequent self-inspection area division, rather than conducting self-inspection of all areas in general, regardless of whether the area exists in the production and operation site.

[0090] Specifically, the production and operation site can be divided into two major areas: dining area and food processing area. The food processing area can be further divided into receiving area, warehouse area, primary processing area, tableware washing area / room, tableware cleaning area / room, hot food processing area, cold food room, plant-based cold food production area, raw food room, homemade beverage area, pastry processing area, cold processed pastry room, meal preparation area / room, auxiliary area, simple production and sales area, etc. The dining area can be divided into the front door welcoming area, front desk management area, customer dining area, etc. The above-mentioned at least one self-inspection area can be determined based on the production and operation site information of the store. The self-inspection area can then be determined from the above-mentioned at least one area based on the production and operation specifications.

[0091] It is understandable that different areas correspond to different inspection standards. Therefore, the area to which the target place belongs is determined in combination with the business location of the target place, and then the inspection standards corresponding to the area to which the target place belongs are combined to determine each target self-inspection area corresponding to the target place.

[0092] Step S102: acquiring target self-inspection questions matching each target self-inspection area in a standard graphic database, so that the user can inspect each target self-inspection area of ​​the target location based on the self-inspection question information;

[0093] In this embodiment, the standard graphic database is used to store the self-inspection questions corresponding to each self-inspection area, the standard text answers corresponding to each self-inspection question, and the graphic examples corresponding to the standard text answers as standard examples. The self-inspection questions in the standard graphic database cover all 48 items in the on-site inspection form for food business licenses. Based on each target self-inspection area, matching self-inspection questions are determined in the preset standard graphic database as target questions.

[0094] Furthermore, step S102 further includes:

[0095] Collect project information corresponding to various regulations and rules of various places, wherein the project information includes non-standard examples, standard examples, and rectification information from non-standard to standard;

[0096] Segment the project information into at least one text unit, and extract at least one entity information and relationship information corresponding to each entity from each text unit based on a language model;

[0097] Based on each of the entity information and the relationship information corresponding to each entity, construct a weighted undirected graph corresponding to the project information, wherein the nodes of the weighted undirected graph represent the entity information, and the edges of the weighted undirected graph represent the relationship information;

[0098] Performing hierarchical clustering on the weighted undirected graph to obtain information of each community, and generating the rectification specification knowledge graph based on the summaries corresponding to each community;

[0099] Based on the rectification specification knowledge graph, generate the standard graphic database;

[0100] In this embodiment, the GraphRAG indexing algorithm is used to construct a rectification standard knowledge graph. First, data such as non-standardized instances, standardized instances, and rectification information from non-standardized to standardized instances of various places are collected, and then the above data is preprocessed, including but not limited to text cleaning, removal of irrelevant information, and terminology standardization. Specifically, the following steps are included:

[0101] 1. Text unit segmentation: Segment the preprocessed project information to obtain basic text units that are convenient for subsequent analysis as text units (TextUnits).

[0102] 2. Entity and relationship extraction: Use the Large Language Model (LLM) to extract all entities (such as special rooms, open drains, floor drains, water seals, wall skirts, special room doors, food delivery windows, independent air conditioners, refrigerators, UV lamps, wash basins, tool cleaning pools, etc.), relationships (such as the corresponding questions of each self-inspection area and the corresponding relationship between the standard instances and non-standard instances of the questions) and key statements from each text unit. By optimizing prompts and multiple rounds of collection, we can ensure that the extraction results are of high quality even when processing large blocks of text.

[0103] 3. Knowledge graph construction and community segmentation: Use the extracted entities and relationships to build a homogeneous weighted undirected graph. Each node in the graph is used to represent each entity extracted above, the edge represents the relationship, and the weight of the edge represents the standardized count of the detected relationship instance.

[0104] The Leiden algorithm is applied to perform hierarchical clustering on the knowledge graph to form different communities. The Leiden algorithm optimizes the traditional Louvain algorithm to run faster and ensure connectivity within the community, making the community division more reasonable.

[0105] 4. Generate community summaries: For each community, generate summaries of the community and its members from the bottom up. Create a report-style summary for each community in the Leiden hierarchy. In order to understand the global structure and semantics of the dataset through the community summary.

[0106] 5. Store the knowledge graph: Store the constructed knowledge graph in the graph database Neo4j to facilitate subsequent query and analysis.

[0107] Step S103: obtaining a standard image instance and a standard text instance corresponding to the target self-examination question in the standard image and text database as a target answer standard, so as to verify the answer to the question uploaded by the user based on the target answer standard;

[0108] In this embodiment, a standard image instance and a standard text instance corresponding to the target self-examination question are obtained in the standard image and text database as the target answer standard.

[0109] Specifically, Figure 3 As shown, based on the self-inspection area selected by the operator, the target question corresponding to the self-inspection area is displayed on the display interface, and answer options are generated based on the standard example diagram corresponding to the target answer standard and the self-inspection area. The self-inspection questions instruct the operator to conduct self-inspections of the business premises on a regular basis, and instruct the operator to evaluate whether various management and operations comply with the requirements of food safety regulations and internal management systems.

[0110] The internal management system can be an internal management system of the industry or an internal management system of the association, etc.

[0111] Furthermore, when receiving the answer information of the current user to each self-examination question, diagnosing each self-examination question based on each self-examination standard text and each corresponding standard image instance, and generating a diagnosis report corresponding to each self-examination area, it also includes:

[0112] Collecting non-standard instances of each self-inspection area corresponding to each type of store, and collecting rectification process information of each type of store from non-standard to standard self-inspection area, wherein the rectification process information includes comparison pictures before and after rectification;

[0113] Based on the comparison charts before and after the rectification, answer options corresponding to each self-examination question are generated, so that the current user can make selections based on the situation of his own store to generate corresponding answer information.

[0114] In this embodiment, the self-inspection areas and items include but are not limited to: site selection, location and layout, food processing area, cleaning facilities, equipment and tools, food storage, ventilation and lighting, sanitary protection, hand washing and changing, special rooms, special operating areas, water for food and others.

[0115] The answer options may also be binary options such as "yes" or "no", or may be an input box, which may be used to input data such as text, voice, picture or video.

[0116] Step S104: Based on the target inspection sequence, the self-inspection question information and the target answer standard, generate the target self-inspection content corresponding to the current user. The target self-inspection content is used to instruct the user to self-inspect and evaluate whether each self-inspection area, each management and operation of the store complies with the requirements of food safety regulations and internal management systems, so that the user can conduct self-inspection and rectification of his own business premises based on the target self-inspection content.

[0117] In this embodiment, the target inspection order may be the inspection order of each self-inspection area in the optimal inspection path. The optimal inspection path may be a path calculation based on a global path planning algorithm. All path planning algorithms include RRT algorithm*, PRM algorithm, and Theta* algorithm. The specific planning algorithm may be determined based on the operator's selection operation or the site characteristics of the target site.

[0118] Furthermore, before generating the target self-inspection content corresponding to the current user based on the target inspection sequence, the self-inspection question information and the target answer standard so that the user can self-inspect and rectify his own business premises based on the target self-inspection content, the method further includes:

[0119] Obtaining relative position information of the current user in an area corresponding to the target location, and obtaining a self-checking area in the target location;

[0120] Determine a path calculation algorithm based on the selection operation of the current user, and calculate a target self-check path with the relative position information as the starting point and each self-check area in the target location as each target point;

[0121] The target inspection sequence is generated according to the sequence of the self-inspection areas in the target location in the target self-inspection path.

[0122] Exemplarily, when there are fewer obstacles in the target location or the walking area is spacious (that is, the width of the walking area is greater than a preset value), the RRT algorithm* or the PRM algorithm is determined to be the optimal path calculation algorithm; when the path calculation time is long, the RRT algorithm* is determined to be the optimal path calculation algorithm; when the path calculation time is short, the PRM algorithm is determined to be the optimal path calculation algorithm.

[0123] When there are many obstacles in the target location or the walking area is narrow (ie, the width of the walking area is less than a preset value), the Theta* algorithm is determined to be the optimal path calculation algorithm.

[0124] After determining the optimal path calculation algorithm, the relative position of the operator to the target business location is used as the starting position, and each self-inspection area is used as a plurality of target points, and the optimal inspection path corresponding to each self-inspection area is calculated by the optimal path calculation algorithm.

[0125] This embodiment provides a method for generating self-inspection content based on a graphic database, wherein the method obtains the business premises type and business premises location of the target place to which the current user belongs upon receiving a self-inspection instruction triggered by the user, and determines each target self-inspection area corresponding to the target place based on the business premises type and business premises location; obtains target self-inspection questions matching each target self-inspection area in the standard graphic database, so that the user can inspect each target self-inspection area of ​​the target place based on the self-inspection question information; obtains the standard image instance and standard text instance corresponding to the target self-inspection question in the standard graphic database as the target answer standard, so as to verify the answer to the question uploaded by the user based on the target answer standard; generates the target self-inspection content corresponding to the current user based on the target inspection sequence, the self-inspection question information and the target answer standard, so that the user can self-inspect and rectify his own business premises based on the target self-inspection content. In the above manner, the present application determines each target self-inspection area in the store based on the store type and store location, and then determines the target self-inspection questions corresponding to the target self-inspection area and the answer standards corresponding to the self-inspection questions from the standard graphic database. Since the self-inspection content is automatically generated according to the requirements of food safety laws and regulations and internal management systems, it does not need to be obtained and interpreted by operators, thus solving the technical problems of narrow acquisition channels, high professionalism of relevant documents, and lack of guidance for practitioners with low cultural levels. In addition, in addition to generating self-inspection content, standard example diagrams of self-inspection content are also given, so that operators can understand food safety laws and regulations and internal management systems more intuitively based on the more instructive standard example diagrams, thereby simplifying the store's self-inspection content and allowing operators to conduct self-inspections of store self-inspection areas more conveniently and quickly, improving store self-inspection efficiency, reducing store self-inspection costs, and reducing food safety risks.

[0126] Furthermore, in order to improve the efficiency of searching for self-check questions, the standard image and text database is divided into a text standard database and an image standard database, so that the self-check standard text and standard image instances corresponding to each self-check question can be searched in parallel in the two databases, thereby reducing the response time of the standard image and text database.

[0127] Specifically, before obtaining the target self-inspection questions matching each target self-inspection area in the standard graphic database, the method further includes:

[0128] Based on the preset crawler rules, crawl the relevant regulations of catering operations in various regions, self-inspection items of various stores, and relevant verification specification examples;

[0129] According to each self-inspection area in each region, the catering business-related regulations, self-inspection items of various stores, and relevant verification specification cases are classified to obtain the self-inspection content and corresponding self-inspection standard text corresponding to each self-inspection area in each region;

[0130] Generate a text standard database based on the self-inspection content corresponding to each self-inspection area in each region and its corresponding self-inspection standard text;

[0131] Collect images and / or videos of various self-inspection areas in various stores, select images and / or videos that meet the self-inspection standard text from the images and / or videos as standard image instances, and generate an image standard database based on the standard instances;

[0132] Establish at least one standard image instance corresponding to each self-check standard text, obtain the correspondence between the text standard database and the image standard database based on the correspondence between the self-check standard text and the standard image instance, and generate the standard image-text database based on the text standard database, the image standard database and the correspondence between the text standard database and the image standard database.

[0133] In a specific embodiment, in order to further improve the search efficiency of self-inspection problems and save storage space, when obtaining the self-inspection content corresponding to each self-inspection area in each region and its corresponding self-inspection standard text, the same self-inspection problems in each region and each self-inspection area are merged, and the different self-inspection problems in each region or each self-inspection area are classified and stored according to each region or each self-inspection area, so as to obtain a personalized database corresponding to each region or each self-inspection area.

[0134] In this embodiment, relevant documents issued by various regions are crawled from multiple official websites based on preset crawler rules to obtain relevant regulations on catering operations, self-inspection items of various stores, and relevant verification specification examples. Preprocessing is performed on the obtained relevant regulations on catering operations, self-inspection items of various stores, and relevant verification specification examples, and the preprocessing includes word segmentation, removal of stop words or punctuation marks, part of speech restoration, semantic analysis, and word frequency statistics.

[0135] Specifically, the step of establishing at least one standard image instance corresponding to each self-check standard text and obtaining the corresponding relationship between the text standard database and the image standard database based on the corresponding relationship between the self-check standard text and the standard image instance specifically further includes:

[0136] Selecting at least one keyword corresponding to a self-check standard text, determining associated sentences containing the keywords corresponding to the self-check standard text, and calculating an associated feature vector corresponding to the self-check standard text according to preset associated information and each associated sentence;

[0137] Selecting at least one relevant word corresponding to a standard image instance, determining a relevant sentence containing the relevant word corresponding to the standard image instance, and calculating a relevant feature vector corresponding to the standard image instance according to preset relevant texts and each relevant sentence;

[0138] Importing the associated feature vector corresponding to the self-check standard text into the image standard database, and determining each standard image instance corresponding to each self-check standard text in the image standard database based on the associated feature vector corresponding to each standard image instance in the image standard database;

[0139] Based on each standard image instance corresponding to each self-check standard text, the corresponding relationship between the self-check standard text and the standard image instance is obtained, and based on each self-check standard text and its corresponding standard image instance, the corresponding relationship between the text standard database and the image standard database is obtained.

[0140] In more embodiments, historical self-inspection data can also be analyzed, and stores that have passed all self-inspection areas can be recorded as standard stores. Standard image instances corresponding to each self-inspection area in the standard stores are obtained and stored separately as self-inspection questions corresponding to each self-inspection area and standard image instances corresponding to each self-inspection standard text.

[0141] Furthermore, the catering business-related regulations, self-inspection items of various stores and relevant inspection specification cases are classified according to the self-inspection areas in each region, and the self-inspection contents corresponding to the self-inspection areas in each region and the corresponding self-inspection standard texts are obtained respectively, which specifically include:

[0142] Based on at least one first keyword corresponding to each self-inspection area in each region, at least one input text is determined according to the relevant regulations on catering operations, the self-inspection items of various stores, and the relevant verification specification examples, each input text includes multiple words, and each word corresponds to at least one word vector;

[0143] Preprocessing each input text to obtain at least one second keyword corresponding to the catering business-related regulations, the self-inspection items of various stores, and the relevant inspection regulations, wherein the preprocessing includes word segmentation, removal of stop words or punctuation marks, part-of-speech restoration, and word frequency statistics;

[0144] Calculating associations between each of the first keywords and each of the second keywords, and determining at least one corresponding target keyword from each of the second keywords according to the associations;

[0145] According to the at least one target keyword, determining at least one associated sentence in the catering business-related regulations, the self-inspection items of various stores, and the relevant verification specification examples, wherein each associated sentence includes at least one target keyword;

[0146] The associated sentences are determined as the self-inspection contents corresponding to each self-inspection area in each region and the corresponding self-inspection standard texts.

[0147] Furthermore, after determining the associated sentences as the self-inspection contents corresponding to the self-inspection areas in each region and the self-inspection standard texts corresponding to the self-inspection areas in each region, the method further includes:

[0148] Based on the self-inspection content corresponding to each self-inspection area in each region and its corresponding self-inspection standard text, generate the verification section corresponding to each self-inspection area, and generate each self-inspection question in each verification section according to different related sentences;

[0149] When the current user's answer information to each self-examination question is received, each self-examination question is diagnosed based on each self-examination standard text and each corresponding standard image instance, and a diagnosis report corresponding to each self-examination area is generated.

[0150] For example, Figure 4 As shown, Figure 4 It is a schematic diagram of an operator interface of a verification section interface provided in an embodiment of the present application, obtaining the food safety laws and regulations and internal management systems, and identifying the verification items in the food safety laws and regulations and internal management systems that are associated with the food business information;

[0151] Generate multiple verification sections and self-examination content corresponding to each verification section according to the verification items;

[0152] Displaying multiple verification section options corresponding to the verification items on the verification section interface;

[0153] Jump to the self-check interface corresponding to the check section according to the operator's selection operation on the check section, and display the self-check content, the standard example diagram of the self-check content, and the answer options for the self-check content on the self-check interface;

[0154] According to the operator's selection operation of the answer option for the self-examination content, the next self-examination content, the next standard example diagram of the self-examination content, and the answer option for the next self-examination content are displayed.

[0155] For example, if the check item is a special room, a special room section is generated, which includes at least one self-inspection content related to the special room, such as whether the special room has an open ditch, whether the floor drain has a water seal, whether the wall skirt is laid to the top, whether it is equipped with an automatically closing special room door, whether it is equipped with an open and close food delivery window, whether it is equipped with an independent air conditioner, whether it is equipped with a refrigerator, whether it is equipped with an ultraviolet lamp, whether the entrance is equipped with a wash basin, whether it is equipped with a tool washing basin, etc. Similarly, there is no fixed order for displaying the above self-inspection content.

[0156] Specifically, multiple verification sections are generated according to the verification items; at least one first keyword corresponding to each verification section is determined; multiple food safety regulations and standard documents and internal management system standard documents are captured from industry-related websites; multiple input texts are determined according to the texts of the multiple food safety regulations and standard documents, each input text includes multiple words, and each word has a corresponding vocabulary vector; the input text is preprocessed to obtain multiple second keywords, and the preprocessing includes but is not limited to word segmentation, removal of stop words or punctuation marks, part of speech restoration, and word frequency statistics; the association relationship between the at least one first keyword and the multiple second keywords is calculated; at least one target keyword is determined from the multiple second keywords according to the association relationship; multiple related sentences are determined according to the at least one target keyword, each of the related sentences includes some keywords in the at least one keyword; the related sentences are determined as the self-inspection content corresponding to the verification section.

[0157] Specifically, the method further includes: displaying the self-inspection content on the self-inspection interface.

[0158] In this embodiment, firstly, keywords and non-keywords in the self-examination content are determined;

[0159] Delete non-keywords in the self-examination content and retain non-keywords;

[0160] Processing the self-examination content retaining non-keywords to obtain simplified self-examination content;

[0161] According to the corresponding part-of-speech coding file, answer extraction and question generation are performed according to the semantics of each word in each sentence in the simplified self-check content to obtain self-check content questions;

[0162] Displaying self-examination content questions according to the self-examination content on the self-examination interface;

[0163] Among them, according to the part of speech classification and coding, each type of keyword is coded by one letter, and the keywords can be divided into: self-inspection content, self-inspection object, self-inspection location, attribute, existence and indicator word. The above six types of keywords are respectively coded by d, o, l, s, y and the indicator word itself.

[0164] Furthermore, the method also includes: diagnosing and generating a food business diagnosis report based on the current user's selection operation of the answer options to the self-examination content, and the food business diagnosis report refers to a written report formed after a comprehensive inspection and evaluation of the food business enterprise.

[0165] In some embodiments, the verification section interface also displays the degree of self-inspection completion, which is determined based on the completed verification section. The operator's selection operation of answering options to the self-inspection content is used to perform a diagnosis and generate a food business diagnosis report.

[0166] Specifically, when it is determined based on the degree of completion of the self-inspection that the inspection of multiple inspection sections has been completed, a diagnosis is performed based on the operator's selection operation of the answer options to the self-inspection content corresponding to each inspection section and a food business diagnosis report is generated.

[0167] The degree of self-check completion can be displayed in the form of a progress bar, a percentage, a score, or other forms of display, which are not listed here. Specifically, according to the degree of self-check completion, it can be determined that multiple check blocks have completed the check by displaying all progress bars, or by determining that multiple check blocks have completed the check when the score is 1 or the percentage is 100%.

[0168] In an embodiment of the present application, when it is determined based on the degree of self-inspection completion that multiple inspection sections have been completed, a diagnosis is performed and a food business diagnosis report is generated based on the operator's selection operation of the answer options to the self-inspection content corresponding to each inspection section, and no diagnosis is performed or a food business diagnosis report is generated when there are incomplete inspection sections. This can achieve the purpose of reminding the operator to conduct further self-inspection and prevent the generated food business diagnosis report from being incomplete, which may cause the operator to mistakenly believe that they have completed all self-inspections and achieved qualified results, thereby increasing food safety risks.

[0169] In order to better illustrate the effect of the embodiment of the present application, the current self-inspection content is a wall skirt as an example. When the current self-inspection content is whether the wall skirt is laid to the top, when the operator's self-inspection content is whether the entrance is equipped with a wash basin and whether it is equipped with a tool cleaning pool, the actual business map uploaded can at least partially reflect whether the wall skirt is laid to the top. Therefore, when the actual business map uploaded by the operator for the self-inspection content of whether the wall skirt is laid to the top cannot determine whether the self-inspection content is in compliance, further judgment is made through the actual business map uploaded by the operator for the self-inspection content of whether the entrance is equipped with a wash basin and whether it is equipped with a tool cleaning pool, thereby achieving the purpose of diagnosis.

[0170] In some embodiments, the answer options include binary confirmation options of "yes" and "no" and a selection input box, and the method further includes:

[0171] When the operator's answer option to the self-examination content is "yes" to confirm the option, prompt the operator to input the actual business diagram in the selection input box;

[0172] Receiving actual business diagrams uploaded by the business operator for the standard example diagrams of the self-examination content, wherein the actual business diagrams refer to real pictures or diagrams taken or drawn by the business operator during the actual business operation process;

[0173] The method of diagnosing and generating a food business diagnosis report based on the operator's selection of answer options to the self-examination content includes:

[0174] A diagnosis is performed based on the actual operation diagram and a food operation diagnosis report is generated. The food operation diagnosis report refers to a written report formed after a comprehensive inspection and evaluation of the food operation enterprise.

[0175] Specifically, the diagnosis is performed according to the actual operation diagram, including:

[0176] Obtain the operator's actual business map for the current self-inspection content, and use image recognition algorithms to identify the target area corresponding to the current self-inspection content;

[0177] Determining whether the current self-inspection content meets the licensing requirements according to the target area corresponding to the current self-inspection content, and providing a first confidence level for whether the current self-inspection content meets the licensing requirements;

[0178] When the first confidence level is lower than a preset threshold, obtaining actual operation diagrams of other self-inspection contents in the inspection item corresponding to the current self-inspection content;

[0179] Identify the target area corresponding to the current self-inspection content based on the actual operating diagram of other self-inspection contents;

[0180] Determine whether the current self-inspection content meets the licensing requirements based on the target area corresponding to the current self-inspection content identified in the actual operation map of other self-inspection contents, and give a second confidence level;

[0181] Whether the current self-examination content meets the licensing requirements is determined according to the first confidence level and the second confidence level.

[0182] Among them, judging whether the current self-inspection content meets the licensing requirements based on the first confidence and the second confidence can be done by assigning a greater weight to the first confidence and a relatively smaller weight to the second confidence, because the first confidence is the actual business map uploaded by the operator based on the current verification content, and the second confidence is the actual business map uploaded by the operator based on other verification content, so the first confidence is more accurate; or it can be done by assigning a greater weight to the second confidence and a relatively smaller weight to the first confidence, because it is precisely because of the poor quality of the actual business map uploaded by the operator based on the current verification content that the first confidence is too low, which introduces the need to judge based on the second confidence, so the second confidence is more credible.

[0183] When the embodiment of the present application cannot determine whether the current self-inspection content complies with the licensing provisions based on the actual business diagram corresponding to the current verification content, the actual business diagram uploaded by other verification content is introduced to determine whether the current verification content complies with the licensing provisions. The operator does not need to upload the actual business diagram corresponding to the current verification content again, thereby facilitating the operator to improve the efficiency of self-inspection. It should be noted that the method of the embodiment of the present application cannot be used as a reference through other secondary recognitions, because the current recognition is mostly for the recognition of a single target, and there are no related photos before and after. The method of the present application is derived from the limitations of the special scenarios of the embodiment of the present application, thereby reducing the re-upload of pictures. Other recognitions can only upload multiple photos for the same recognition target, while the present application can achieve multiple recognitions by uploading a photo once for the same recognition target.

[0184] See also Figure 5 , Figure 5 1 is a schematic diagram of a self-checking content generating device 900 based on a graphic database provided in an embodiment of the present application. The device comprises:

[0185] The inspection area determination module 910 is used to obtain the business place type and business place location of the target place to which the current user belongs when receiving the self-inspection instruction triggered by the user, and determine each target self-inspection area corresponding to the target place based on the business place type and business place location;

[0186] The self-inspection question matching module 920 is used to obtain target self-inspection questions matching each target self-inspection area from the standard graphic database, so that the user can inspect each target self-inspection area of ​​the target place based on the self-inspection question information;

[0187] The answer standard acquisition module 930 is used to acquire the standard image instance and the standard text instance corresponding to the target self-examination question in the standard image and text database as the target answer standard, so as to verify the answer to the question uploaded by the user based on the target answer standard;

[0188] The self-inspection content generation module 940 is used to generate the target self-inspection content corresponding to the current user based on the target inspection sequence, the self-inspection question information and the target answer standard. The target self-inspection content is used to instruct the user to self-inspect and evaluate whether each self-inspection area, management and operation of the store comply with the requirements of food safety regulations and internal management systems, so that the user can conduct self-inspection and rectification of his own business premises based on the target self-inspection content.

[0189] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0190] A computer-readable storage medium is also provided in an embodiment of the present application. The computer-readable storage medium stores a computer program. The computer program includes program instructions. The processor executes the program instructions to implement any one of the self-examination content generation methods based on the graphic database provided in the embodiments of the present application.

[0191] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0192] The computer-readable storage medium may be an internal storage unit of the computer device of the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital card (Secure Digital, SD), a flash card (Flash Card), etc. equipped on the computer device.

[0193] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for generating self-examination content based on a graphic and text database, characterized in that: The method comprises: Upon receiving a self-check instruction triggered by a user, obtaining the business place type and business place location of the target place to which the current user belongs, and determining each target self-check area corresponding to the target place based on the business place type and business place location; Obtaining target self-inspection questions matching each target self-inspection area in a standard graphic database, so that the user can inspect each target self-inspection area of ​​the target location based on the target self-inspection questions; Obtaining a standard image instance and a standard text instance corresponding to the target self-examination question from the standard image and text database as a target answer standard, so as to verify the answer to the question uploaded by the user based on the target answer standard; Based on the target inspection sequence, the target self-inspection questions and the target answer standards, the target self-inspection content corresponding to the current user is generated. The target self-inspection content is used to instruct the user to self-inspect and evaluate whether each self-inspection area, each management and operation of the store complies with the requirements of food safety regulations and internal management systems, so that the user can conduct self-inspection and rectification of his own business premises based on the target self-inspection content; Wherein, before obtaining the target self-inspection questions matching each target self-inspection area in the standard graphic database, the method further includes: Based on the preset crawler rules, crawl the relevant regulations of catering operations in various regions, self-inspection items of various stores, and relevant verification specification examples; According to each self-inspection area in each region, the catering business-related regulations, self-inspection items of various stores, and relevant verification specification cases are classified to obtain the self-inspection content and corresponding self-inspection standard text corresponding to each self-inspection area in each region; Generate a text standard database based on the self-inspection content corresponding to each self-inspection area in each region and its corresponding self-inspection standard text; Collect images and / or videos of various self-inspection areas in various stores, select images and / or videos that meet the self-inspection standard text from the images and / or videos as standard image instances, and generate an image standard database based on the standard image instances; Establishing at least one standard image instance corresponding to each self-check standard text, obtaining the corresponding relationship between the text standard database and the image standard database based on the corresponding relationship between the self-check standard text and the standard image instance, and generating the standard image-text database based on the text standard database, the image standard database and the corresponding relationship between the text standard database and the image standard database; Among them, the catering business-related regulations, self-inspection items of various stores and relevant inspection specification cases are classified according to the self-inspection areas in each region, and the self-inspection contents corresponding to the self-inspection areas in each region and the corresponding self-inspection standard texts are obtained respectively, which specifically include: Based on at least one first keyword corresponding to each self-inspection area in each region, at least one input text is determined according to the relevant regulations on catering operations, the self-inspection items of various stores, and the relevant verification specification examples, each input text includes multiple words, and each word corresponds to at least one word vector; Preprocessing each input text to obtain at least one second keyword corresponding to the catering business-related regulations, self-inspection items of various stores, and relevant inspection regulations, wherein the preprocessing includes word segmentation, removal of stop words or punctuation marks, part-of-speech restoration, and word frequency statistics; Calculating associations between each of the first keywords and each of the second keywords, and determining at least one corresponding target keyword from each of the second keywords according to the associations; According to the at least one target keyword, determining at least one associated sentence in the catering business-related regulations, the self-inspection items of various stores, and the relevant verification specification examples, wherein each associated sentence includes at least one target keyword; The associated sentences are determined as the self-inspection contents corresponding to each self-inspection area in each region and the corresponding self-inspection standard texts.

2. The method for generating self-examination content based on a graphic and text database according to claim 1, characterized in that: The step of establishing at least one standard image instance corresponding to each self-check standard text and obtaining the corresponding relationship between the text standard database and the image standard database based on the corresponding relationship between the self-check standard text and the standard image instance specifically further includes: Selecting at least one keyword corresponding to a self-check standard text, determining associated sentences containing the keywords corresponding to the self-check standard text, and calculating an associated feature vector corresponding to the self-check standard text according to preset associated information and each associated sentence; Selecting at least one relevant word corresponding to a standard image instance, determining a relevant sentence containing the relevant word corresponding to the standard image instance, and calculating a relevant feature vector corresponding to the standard image instance according to preset relevant texts and each relevant sentence; Importing the associated feature vector corresponding to the self-check standard text into the image standard database, and determining each standard image instance corresponding to each self-check standard text in the image standard database based on the associated feature vector corresponding to each standard image instance in the image standard database; Based on each standard image instance corresponding to each self-check standard text, the corresponding relationship between the self-check standard text and the standard image instance is obtained, and based on each self-check standard text and its corresponding standard image instance, the corresponding relationship between the text standard database and the image standard database is obtained.

3. The method for generating self-examination content based on a graphic and text database according to claim 1, characterized in that: After determining the associated sentences as the self-inspection contents corresponding to the self-inspection areas in each region and the corresponding self-inspection standard texts, the method further includes: Based on the self-inspection content corresponding to each self-inspection area in each region and its corresponding self-inspection standard text, generate the verification section corresponding to each self-inspection area, and generate each self-inspection question in each verification section according to different related sentences; When the current user's answer information to each self-examination question is received, each self-examination question is diagnosed based on each self-examination standard text and each corresponding standard image instance, and a diagnosis report corresponding to each self-examination area is generated.

4. The method for generating self-examination content based on a graphic and text database according to claim 1, characterized in that: When receiving the answer information of the current user to each self-examination question, diagnosing each self-examination question based on each self-examination standard text and each corresponding standard image instance, and generating a diagnosis report corresponding to each self-examination area, it also includes: Collecting non-standard instances of each self-inspection area corresponding to each type of store, and collecting rectification process information of each type of store from non-standard to standard self-inspection area, wherein the rectification process information includes comparison pictures before and after rectification; Based on the comparison charts before and after the rectification, answer options corresponding to each self-examination question are generated, so that the current user can make selections based on the situation of his own store to generate corresponding answer information.

5. The method for generating self-examination content based on a graphic and text database according to any one of claims 1 to 4, characterized in that: Before generating the target self-inspection content corresponding to the current user based on the target inspection sequence, the target self-inspection questions and the target answer standard so that the user can conduct self-inspection and rectification of his own business premises based on the target self-inspection content, the method further includes: Obtaining relative position information of the current user in an area corresponding to the target location, and obtaining a self-checking area in the target location; Determine a path calculation algorithm based on the selection operation of the current user, and calculate a target self-check path with the relative position information as the starting point and each self-check area in the target location as each target point; The target inspection sequence is generated according to the sequence of the self-inspection areas in the target location in the target self-inspection path.

6. A self-examination content generation device based on a graphic and text database, characterized in that: The device comprises: An inspection area determination module is used to obtain the business place type and business place location of the target place to which the current user belongs when receiving the self-inspection instruction triggered by the user, and determine each target self-inspection area corresponding to the target place based on the business place type and business place location; A self-inspection question matching module is used to obtain target self-inspection questions matching each target self-inspection area in a standard image and text database, so that the user can inspect each target self-inspection area of ​​the target place based on the target self-inspection questions; An answer standard acquisition module, used to acquire a standard image instance and a standard text instance corresponding to the target self-examination question in the standard image and text database as a target answer standard, so as to verify the answer to the question uploaded by the user based on the target answer standard; A self-inspection content generation module is used to generate a target self-inspection content corresponding to the current user based on the target inspection sequence, the target self-inspection questions and the target answer standard. The target self-inspection content is used to instruct the user to self-inspect and evaluate whether each self-inspection area, each management and operation of the store complies with the requirements of food safety regulations and internal management systems, so that the user can conduct self-inspection and rectification of his own business premises based on the target self-inspection content; The device further comprises a graphic and text database generation module, which is used to: Based on the preset crawler rules, crawl the relevant regulations of catering operations in various regions, self-inspection items of various stores, and relevant verification specification examples; According to each self-inspection area in each region, the catering business-related regulations, self-inspection items of various stores, and relevant verification specification cases are classified to obtain the self-inspection content and corresponding self-inspection standard text corresponding to each self-inspection area in each region; Generate a text standard database based on the self-inspection content corresponding to each self-inspection area in each region and its corresponding self-inspection standard text; Collect images and / or videos of various self-inspection areas in various stores, select images and / or videos that meet the self-inspection standard text from the images and / or videos as standard image instances, and generate an image standard database based on the standard image instances; Establishing at least one standard image instance corresponding to each self-check standard text, obtaining the corresponding relationship between the text standard database and the image standard database based on the corresponding relationship between the self-check standard text and the standard image instance, and generating the standard image-text database based on the text standard database, the image standard database and the corresponding relationship between the text standard database and the image standard database; Wherein, the graphic and text database generation module is also used for: Based on at least one first keyword corresponding to each self-inspection area in each region, at least one input text is determined according to the relevant regulations on catering operations, the self-inspection items of various stores, and the relevant verification specification examples, each input text includes multiple words, and each word corresponds to at least one word vector; Preprocessing each input text to obtain at least one second keyword corresponding to the catering business-related regulations, the self-inspection items of various stores, and the relevant inspection regulations, wherein the preprocessing includes word segmentation, removal of stop words or punctuation marks, part-of-speech restoration, and word frequency statistics; Calculating associations between each of the first keywords and each of the second keywords, and determining at least one corresponding target keyword from each of the second keywords according to the associations; According to the at least one target keyword, determining at least one associated sentence in the catering business-related regulations, the self-inspection items of various stores, and the relevant verification specification examples, wherein each associated sentence includes at least one target keyword; The associated sentences are determined as the self-inspection contents corresponding to each self-inspection area in each region and the corresponding self-inspection standard texts.

7. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is used to execute the computer program and implement the self-examination content generation method based on the graphic and text database as described in any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for generating self-examination content based on a graphic and text database according to any one of claims 1 to 5 is implemented.

Images