Environmental training course recommendation methods, devices, equipment and storage media
By establishing an environmental training course catalog and keyword database, extracting keywords and calculating weights, and combining with enterprise environmental portrait matching courses, the problem of low efficiency in environmental training course recommendations in the existing technology has been solved, precise push and automated recommendations have been achieved, and the improvement of The company's environmental awareness and management level.
Patent Information
- Application Number
- CN202111196057.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-10-14
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2041-10-14
AI Technical Summary
The recommended methods for existing environmental training courses have a long cycle and low efficiency, which cannot achieve accurate delivery, waste manpower and material resources, and are greatly affected by human factors, making it difficult to achieve better recommendation results.
By establishing an environmental training course catalog and keyword database, extracting course keywords and calculating weights, combining corporate environmental data and basic information to build corporate environmental portraits, generating tags, matching courses with enterprise tags, and automatically pushing courses with high similarity.
It has improved the degree of automation and efficiency of course push, enhanced the environmental awareness and supervision of corporate employees in accordance with the law, and promoted the sustainable development of the company.
Smart Images

Figure CN113919331B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an environmental training course recommendation method, device, equipment and storage medium. Background Art
[0002] In order to achieve legal green operation of enterprises and make enterprises assume environmental responsibilities, during normal operation of different levels of waste-producing enterprises, in order to reduce pollution disputes, achieve pollution prevention, improve the environmental awareness of enterprise employees, improve the management level of enterprises, and ultimately enhance the market competitiveness of enterprises, the traditional method is to select a third-party agency and send special recommendation staff to recommend environmental training courses to each enterprise. However, this recommendation method has a long time cycle, low efficiency, and will waste a lot of manpower and material resources. In addition, under the influence of human factors, it is impossible to achieve accurate course delivery and achieve good recommendation effects. Therefore, an AI-based environmental training course recommendation method is proposed to recommend environmental training courses to many enterprises, so as to eliminate human influence factors and improve the accuracy of environmental training course recommendations.
[0003] Therefore, the prior art still needs to be improved and developed. Summary of the invention
[0004] In view of the above-mentioned deficiencies in the prior art, the purpose of the present invention is to provide an environmental training course recommendation method, device, equipment and storage medium, aiming to solve the problems of the existing environmental training course recommendation method having a long cycle, low efficiency, waste of manpower and material resources and inability to achieve accurate delivery.
[0005] In order to solve the above technical problems, the technical solutions adopted by the present invention to solve the above technical problems are as follows:
[0006] In a first aspect, the present invention provides an environmental training course recommendation method, which includes:
[0007] Establish an environmental training course catalog, and establish an environmental training course keyword library based on the network hot words of each sub-category course under each major category in the environmental training course catalog, and establish an environmental training course storage database using the environmental training course keyword library and the environmental training course catalog;
[0008] Obtaining a knowledge carrier of the environment training course to be uploaded, extracting keywords from the knowledge carrier, and calculating the weights of the keywords;
[0009] Matching the keywords extracted from the knowledge carrier with the environmental training course keyword library, classifying the environmental training courses to be uploaded into corresponding environmental training course directories, and inputting the classification results into the environmental training course storage database for storage;
[0010] Obtain the environmental data of the enterprise, perform metrological certification and supervision on the obtained environmental data, verify the validity of the data, and use the environmental data as historical environmental statistical data and combine it with the environmental statistical data obtained by monitoring equipment to establish an enterprise environmental monitoring database;
[0011] Obtaining basic enterprise information, enterprise waste generation types, and multi-dimensional enterprise information combined with environmental statistical data in the enterprise environmental monitoring database to construct an environmental profile of the enterprise and generate an enterprise label, wherein the multi-dimensional enterprise information includes one or more of enterprise operating condition monitoring data, production and operation data, environmental credit data, and tax data;
[0012] Obtain the company's existing environmental training courses and establish a corporate label library based on the company name, corporate label and the company's environmental training courses;
[0013] The labels of the enterprise to be assigned courses are matched with the enterprises in the enterprise label library one by one to calculate the label similarity. When the label similarity is less than the preset threshold, the course similarity is calculated based on the label of the enterprise to be assigned courses and the course keywords. The course similarities are sorted from high to low, and the top three environmental training courses in each major category are pushed to the enterprise to be assigned courses; when the label similarity is greater than or equal to the preset threshold, the same type of environmental training courses with the highest label similarity are pushed to the enterprise to be assigned courses.
[0014] The method, wherein extracting keywords from the knowledge carrier and calculating the weights of the keywords, includes:
[0015] The knowledge carrier includes one or more of text, image, audio, and video;
[0016] When the knowledge carrier is text, the TF-IDF method is used to extract keywords in the text, and TF and IDF are multiplied as the weight of the keyword, where TF represents the frequency of a word appearing in the text, and IDF represents the frequency of a word appearing in other texts;
[0017] When the knowledge carrier is an image, prepare classified picture data and classification labels, use the prepared pictures for network training, build a CNN image classification network, input the pictures to be classified into the CNN image classification network for classification, add category keywords according to the category name, and use the TF-IDF method to calculate the keyword weight;
[0018] When the knowledge carrier is audio, an audio-to-text conversion plug-in is used to extract text descriptions in the audio, and a TF-IDF method is used to extract keywords and calculate the weights of the keywords;
[0019] When the knowledge carrier is a video, the video is separated into audio and image, and the same method as that for the image and audio is used to extract keywords and calculate the weights of the keywords.
[0020] The method, wherein the keywords extracted from the knowledge carrier are matched with the environmental training course keyword library, and the environmental training courses to be uploaded are classified into corresponding environmental training course directories, comprises:
[0021] The keywords that hit the course keyword library are selected and grouped from the keywords extracted from the knowledge carrier to obtain a keyword sequence. The total weight of each category is calculated based on the keyword sequence and keyword weight, and the environmental training courses to be uploaded are classified into the course category with the largest weight.
[0022] The method, wherein obtaining the environmental data of the enterprise comprises:
[0023] The environmental data includes one or more of the Internet of Things online monitoring data, environmental credit evaluation data, whether environmental liability insurance services have been purchased, and services that have been booked. When the enterprise is a small or medium-sized waste-producing enterprise or unit, the scope, object and content of monitoring are determined, the environmental monitoring data management directory is listed, the environmental detection method is determined, and the environmental data is detected and counted according to the environmental detection method;
[0024] When the enterprise is a key pollution prevention enterprise or unit, the first environmental data is obtained by testing according to the detection factors on the approved environmental impact assessment report, the second environmental data is obtained by testing according to the self-monitoring plan approved on the national pollutant discharge permit management information platform, the third environmental data is obtained by testing according to the customer's factory inspection system audit, the fourth environmental data is obtained by testing the indoor working environment of the enterprise, and the fifth environmental data is obtained by summarizing the first to fifth environmental data to obtain the environmental data of the key pollution prevention enterprise or unit.
[0025] The method, wherein the step of performing metrological authentication and supervision on the acquired environmental data and verifying the validity of the data comprises:
[0026] Check whether the environmental data comes from the monitoring equipment;
[0027] Check whether the monitoring equipment for environmental data has a weekly inspection certificate and whether the certificate is within the validity period;
[0028] Whether the traceability identification method is correct, whether it is carried out in accordance with the operating procedures, and whether the monitoring personnel are competent;
[0029] Review whether the entrusted inspection unit has dosage certification and whether it meets the authorized inspection conditions stipulated by law.
[0030] The method, wherein obtaining basic information of an enterprise includes:
[0031] Search the Internet for basic information about waste-generating enterprises to determine their types;
[0032] Searching for enterprise information on a registered enterprise network platform to obtain enterprise data information, wherein the enterprise data information includes one or more of enterprise name, enterprise type, establishment date, and legal representative;
[0033] Obtaining enterprise waste generation information according to the enterprise management platform, wherein the enterprise waste generation information includes one or more of waste generation type, waste generation main component analysis, common waste treatment methods, and waste production volume or weight per unit time;
[0034] Get the geographical location, waste treatment unit, and waste transportation unit of the enterprise.
[0035] The method, wherein when the tag similarity is less than a preset threshold, the course similarity is calculated based on the tag of the course enterprise to be assigned and the course keyword, the course similarity is sorted from high to low, and the top three environmental training courses in each category of course similarity are pushed to the course enterprise to be assigned, and the method further includes:
[0036] Update the enterprise name, enterprise label and pushed environment training courses of the enterprise to be assigned courses into the enterprise label library.
[0037] In a second aspect, an embodiment of the present invention further provides an environmental training course recommendation device, which includes:
[0038] A storage database establishment module is used to establish an environmental training course catalog, and to establish an environmental training course keyword library based on network hot words for each sub-category course under each major category in the environmental training course catalog, and to establish an environmental training course storage database using the environmental training course keyword library and the environmental training course catalog;
[0039] A keyword extraction module, used to obtain the knowledge carrier of the environmental training course to be uploaded, extract keywords from the knowledge carrier, and calculate the weight of the keywords;
[0040] A course classification module is used to match the keywords extracted from the knowledge carrier with the environmental training course keyword library, classify the environmental training courses to be uploaded into the corresponding environmental training course directory, and input the classification results into the environmental training course storage database for storage;
[0041] An environmental data acquisition module is used to acquire the environmental data of the enterprise, perform metrological authentication and supervision on the acquired environmental data, verify the validity of the data, and use the environmental data as historical environmental statistical data and combine it with the environmental statistical data obtained by the monitoring equipment to establish an enterprise environmental monitoring database;
[0042] An enterprise label generation module is used to obtain basic enterprise information, enterprise waste generation types, and multi-dimensional enterprise information, combined with environmental statistical data in the enterprise environmental monitoring database to construct an enterprise environmental protection portrait and generate an enterprise label, wherein the multi-dimensional enterprise information includes one or more of enterprise working condition monitoring data, production and operation data, environmental protection credit data, and tax data;
[0043] The enterprise label library establishment module is used to obtain the enterprise's existing environmental training courses and establish an enterprise label library based on the enterprise name, enterprise label and the enterprise's environmental training courses;
[0044] The course push module is used to match the labels of the enterprise to be assigned courses with the enterprises in the enterprise label library one by one to calculate the label similarity. When the label similarity is less than the preset threshold, the course similarity is calculated based on the label of the enterprise to be assigned courses and the course keywords, and the course similarity is sorted from high to low. The top three environmental training courses in each major category are pushed to the enterprise to be assigned courses; when the label similarity is greater than or equal to the preset threshold, the same type of environmental training courses with the highest label similarity are pushed to the enterprise to be assigned courses.
[0045] In a third aspect, an embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the environmental training course recommendation method as described in any one of the above schemes are implemented.
[0046] In a fourth aspect, an embodiment of the present invention 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 steps of the environmental training course recommendation method as described in any of the above solutions are implemented.
[0047] Beneficial effects: The present invention provides a method, device, equipment and storage medium for recommending environmental training courses. The method includes: extracting keywords from the knowledge carrier of the environmental training course and calculating the weight, then matching with the keywords of the existing environmental training course to complete the classification of the environmental training course, then building an enterprise portrait according to the enterprise's environmental data, enterprise basic information, enterprise waste type and multi-dimensional enterprise information, generating enterprise labels, establishing an enterprise label library in combination with the enterprise's existing environmental training courses and enterprise names, and matching the labels of the enterprises to be assigned courses with the enterprises in the enterprise label library to complete the push of environmental training courses. The present invention adopts the method to improve the degree of automation of pushing courses to enterprises, and avoids the traditional staff recommending environmental training courses to each enterprise, greatly improving the efficiency of recommending relevant environmental training courses to relevant enterprises. After the enterprise adopts the relevant environmental training courses, it not only increases the environmental protection awareness of the enterprise employees, but also effectively strengthens the legal supervision and management of the enterprise's environmental protection data by the enterprise employees, and strengthens the style of work of the relevant departments, promotes the enterprise to vigorously carry out relevant environmental protection publicity work, and ensures the sustainable development of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] Figure 1 The present invention provides a flowchart of a specific implementation of the environmental training course recommendation method provided in an embodiment of the present invention.
[0049] Figure 2 A CNN image classification network diagram provided for an embodiment of the present invention.
[0050] Figure 3 This is an overall flow chart of the classification of environmental training courses provided by an embodiment of the present invention.
[0051] Figure 4 A flow chart of a method for acquiring environmental data for small and medium-sized waste-producing enterprises or units provided in an embodiment of the present invention.
[0052] Figure 5 A flow chart of a method for acquiring environmental data of key pollution prevention enterprises or units provided in an embodiment of the present invention.
[0053] Figure 6 A specific flow chart for measuring, authenticating and supervising acquired environmental data provided by an embodiment of the present invention.
[0054] Figure 7 A flow chart of a method for obtaining basic enterprise information provided in an embodiment of the present invention.
[0055] Figure 8 A schematic diagram of an enterprise portrait provided for an embodiment of the present invention.
[0056] Fig. 9A schematic diagram of functional modules of an environmental training course recommendation device provided by an embodiment of the present invention;
[0057] Fig.10 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0058] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0059] In order to solve the problems in the prior art of environmental training course recommendation methods, such as long cycle, low efficiency, waste of manpower and material resources, and inability to achieve accurate delivery, this embodiment provides an environmental training course recommendation method, specifically, Figure 1 As shown, the environmental training course recommendation method of a preferred embodiment of the present invention comprises the following steps:
[0060] Step S100, establish an environmental training course catalog, and establish an environmental training course keyword library based on the network hot words of each sub-category course under each major category in the environmental training course catalog, and establish an environmental training course storage database using the environmental training course keyword library and the environmental training course catalog.
[0061] Specifically, the existing environmental training courses are first classified, and their types include but are not limited to basic courses, special courses, industry courses, environmental protection publicity courses, and environmental law-related courses. The existing courses that have been clearly classified are placed under each major category. The specific classification method can be exemplified by referring to Table 1. It can be seen from the table that under each major category, there are many sub-category courses. By searching the Internet for hot words for each sub-category course on the Internet, a keyword library for environmental training courses can be established. The environmental training course storage database is established using the environmental training course keyword library and the environmental training course catalog. All environmental training courses and their corresponding keywords are stored in the environmental training course storage database.
[0062]
[0063] Table 1
[0064] Step S200, obtaining a knowledge carrier of the environment training course to be uploaded, extracting keywords from the knowledge carrier, and calculating the weights of the keywords.
[0065] Environmental training courses are mainly in two forms: Word and PPT. Different knowledge carriers can be summarized from them, and keywords are extracted for each carrier, and the weight of each keyword is calculated.
[0066] In some embodiments, before step S200, the method further includes a step in which the teacher of the environmental training course to be uploaded prepares at least three keywords related to the course so that the classification of the course can be more accurate.
[0067] Subsequently, keywords in the course are automatically extracted. Specifically, the knowledge carrier includes one or more of text, image, audio, and video;
[0068] When the knowledge carrier is text, the TF-IDF method is used to extract keywords from the text, and TF and IDF are multiplied as the weight of the keyword. TF-IDF is an important algorithm for information processing and data mining, where TF represents the frequency of a word appearing in a text. The higher the frequency, the more likely it is a keyword. IDF indicates the frequency of a word appearing in other texts
[0069] When the knowledge carrier is an image, prepared classified picture data and classification labels are used, and the prepared pictures are used for network training to build a CNN image classification network. The pictures to be classified are input into the CNN image classification network for classification. According to the category name, category keywords are added, and the keyword weights are calculated using the TF-IDF method.
[0070] The images are mainly classified by supervised classification method. The main classification types are water-related (bridges, water surface detection balls, etc.), gas-related (vehicles, roads, factories, etc.), and solid waste-related (construction sites). In order to classify images, we must first prepare classified image data and classification labels, that is, pictures of bridges, water surface detection balls, vehicles, roads, factories, and construction sites. Use the prepared pictures for network training. The input items are pictures, and the output items are label data. Build a CNN image classification network, such as Figure 2 As shown, the picture to be classified is input into the CNN image classification network for classification, category keywords are added according to the category name, and the TF-IDF method is used to calculate the keyword weight.
[0071] When the knowledge carrier is audio, an audio-to-text conversion plug-in is used to extract text descriptions in the audio, and a TF-IDF method is used to extract keywords and calculate the weights of the keywords.
[0072] When the knowledge carrier is a video, the video is separated into audio and image, and the same method as that for the image and audio is used to extract keywords and calculate the weights of the keywords.
[0073] Step S300, matching the keywords extracted from the knowledge carrier with the environmental training course keyword library, classifying the environmental training courses to be uploaded into the corresponding environmental training course directory, and inputting the classification results into the environmental training course storage database for storage.
[0074] In this embodiment, after extracting keywords from the knowledge carrier using the above method, keywords that hit the course keyword library are selected from the keywords and grouped to obtain a keyword sequence. According to the keyword sequence and keyword weight, the total weight belonging to each major category is calculated, and the environmental training courses to be uploaded are classified into the course category with the largest weight, and then the classification results are input into the environmental training course storage database for storage.
[0075] Specifically, Figure 3 As shown in the figure, after summarizing the keywords provided by the teachers of the supporting courses and the keywords extracted from the knowledge carrier, the keywords that hit each course are selected and grouped according to the major categories to which the courses belong. For example, there are n keywords that hit the courses related to environmental protection law, and the keyword sequences obtained are P (p1, p2, ... p n ), calculate the total weight of each category based on the keyword sequence and keyword weight Among them, w i is the weight of the i-th keyword. The total weight of each category is calculated, and the course is classified into the course category with the largest weight. After the classification is completed, the course is input into the database for storage according to the classification results.
[0076] Step S400, obtain the environmental data of the enterprise, perform metrological authentication and supervision on the obtained environmental data, verify the validity of the data, use the environmental data as historical environmental statistical data and combine it with the environmental statistical data obtained by the monitoring equipment to establish an enterprise environmental monitoring database.
[0077] Specifically, the environmental data of the enterprise is obtained, and the environmental data includes one or more of the following: online monitoring data of the Internet of Things, environmental credit evaluation data, whether environmental liability insurance services have been purchased, and services that have been reserved. When the enterprise is a small or medium-sized waste-producing enterprise or unit, the scope, object, and content of monitoring are determined, the environmental monitoring data management directory is listed, the environmental detection method is determined, and the environmental data is detected and counted according to the environmental detection method;
[0078] When the enterprise is a key pollution prevention enterprise or unit, the first environmental data is obtained by testing according to the detection factors on the approved environmental impact assessment report, the second environmental data is obtained by testing according to the self-monitoring plan approved on the national pollutant discharge permit management information platform, the third environmental data is obtained by testing according to the customer's factory inspection system audit, the fourth environmental data is obtained by testing the indoor working environment of the enterprise, and the fifth environmental data is obtained by summarizing the first to fifth environmental data to obtain the environmental data of the key pollution prevention enterprise or unit.
[0079] Specifically, different monitoring scopes, objects and contents are determined for different types of enterprises, and a monitoring data management directory is listed so that we can have a clear idea and clear goals. At the same time, in the process of obtaining data, statistics are strictly carried out in accordance with various standards to ensure the accuracy of the data, such as Figure 4 and 5 As shown in the figure, they are flow charts of environmental data acquisition methods for small and medium-sized waste-producing enterprises or units and key pollution prevention enterprises or units, among which environmental impact assessment acceptance monitoring is referred to as environmental impact assessment acceptance monitoring, environmental testing indicators are carried out according to the testing factors in the environmental impact assessment report approval to carry out water, sound and air testing, and national pollutant discharge permit self-monitoring is carried out according to the self-monitoring plan approved on the national pollutant discharge permit management information platform to carry out relevant testing; customer system audits (such as ISO 9000, ISO 14000, ISO 18000 and ICTI) are also tested according to the detection factors on the factory environmental impact assessment report approval; if the environmental protection department audits the factory and finds that the factory needs to carry out relevant environmental protection rectification, such as the recent launch of the VOCS terminal rectification action, it is necessary to carry out rectification in accordance with the rectification requirements of the relevant staff of the environmental protection department. For specific detection requirements, please consult the staff of the corresponding environmental protection department; if the company office needs to carry out indoor air quality testing and drinking water testing due to bidding or government supervision, if the relevant department has clearly specified the detection factors, the relevant detection factors shall be used for testing. If no specific detection indicators are specified, the customer service of the testing agency (such as Guangdong Huake Testing) may recommend the project. For example, indoor air quality testing generally tests formaldehyde, TVOC, triphenyls (benzene, toluene and xylene) and ammonia and other detection factors.
[0080] Furthermore, in order to ensure the authenticity and validity of the acquired data, it is also necessary to conduct metrological certification and supervision on the acquired environmental data, such as Figure 6 As shown, it includes:
[0081] S401. Check whether the environmental data is derived from monitoring equipment;
[0082] S402. Check whether the monitoring equipment for environmental data has a weekly inspection certificate and whether the certificate is within the validity period;
[0083] S403. Whether the traceability identification method is correct, whether it is carried out in accordance with the operating procedures, and whether the monitoring personnel are competent;
[0084] S404. Review whether the entrusted inspection unit has dosage certification and whether it meets the authorized inspection conditions stipulated by law.
[0085] The above verification method can avoid the generation of artificial false data and prevent inaccurate data caused by improper operation and other factors.
[0086] At the same time, in order to further improve the accuracy of the data, an enterprise environmental monitoring database is established within the enterprise platform, using the environmental data as historical environmental statistical data and combining it with the environmental statistical data obtained by monitoring equipment. The data management method is converted from manual recording to computer management, and the monitoring data obtained by each monitoring device is entered into the enterprise environmental monitoring database.
[0087] Step S500, obtain basic enterprise information, enterprise waste generation types and multi-dimensional enterprise information, combine with environmental statistical data in the enterprise environmental monitoring database to build an enterprise environmental portrait, and generate an enterprise label, wherein the multi-dimensional enterprise information includes one or more of enterprise operating condition monitoring data, production and operation data, environmental credit data, and tax data.
[0088] Specifically, Figure 7 As shown, the methods for obtaining basic enterprise information include:
[0089] S501. Search the basic information of the waste-generating enterprises on the Internet to determine the type of the waste-generating enterprises;
[0090] S502, searching for enterprise information on a registered enterprise network platform to obtain enterprise data information, wherein the enterprise data information includes one or more of enterprise name, enterprise type, establishment date, and legal representative;
[0091] S503, obtaining enterprise waste generation information according to the enterprise management platform, wherein the enterprise waste generation information includes one or more of waste generation type, waste generation main component analysis, common waste treatment methods, and waste production volume or weight per unit time;
[0092] S504. Obtain the enterprise's geographical location, waste treatment unit, and waste transportation unit.
[0093] By obtaining the basic information of the enterprise, the type of waste produced by the enterprise, and multi-dimensional enterprise information, the environmental statistical data in the enterprise environmental monitoring database is combined to build the enterprise environmental protection portrait and generate enterprise labels. The content of the generated enterprise portrait is as follows: Figure 8As shown, the basic information module is used to display the basic information of the enterprise; the pollutant information module is used to display the enterprise's waste types, main component analysis of waste, common waste treatment methods, waste production volume or weight per unit time, etc.; the enterprise credit module is used to display the multi-dimensional information of the enterprise, so as to evaluate the environmental credit level of the enterprise; the spatial location module is used to display the enterprise's geographical location, land area, transportation difficulty and other information; other modules are used to display other information such as the enterprise's common cooperation units. The generated enterprise portraits and enterprise labels can provide a more intuitive understanding of the status of the enterprise.
[0094] Step S600, obtaining the existing environmental training courses of the enterprise, and establishing an enterprise label library according to the enterprise name, enterprise label and the environmental training courses of the enterprise.
[0095] Obtain the existing environmental training courses of the enterprise, establish a mapping relationship between the enterprise name, enterprise label and enterprise environmental training courses, and form an enterprise label library. The enterprise label library can be used to quickly find out what existing environmental training courses a certain enterprise or an enterprise with a certain enterprise label has.
[0096] Step S700, match the labels of the enterprise to be assigned courses with the enterprises in the enterprise label library one by one to calculate the label similarity. When the label similarity is less than the preset threshold, calculate the course similarity based on the label of the enterprise to be assigned courses and the course keywords, sort the course similarities from high to low, and push the top three environmental training courses in each major category to the enterprise to be assigned courses; when the label similarity is greater than or equal to the preset threshold, push the same type of environmental training courses as the enterprise with the highest label similarity to the enterprise to be assigned courses.
[0097] Specifically, in order to push environmental training courses to enterprises more quickly and accurately, the same enterprise label generation method as mentioned above is used in this embodiment to generate labels for the enterprises to be assigned courses, and the labels of the enterprises to be assigned courses are matched one by one with the enterprises in the enterprise label library to calculate the label similarity. When the label similarity is greater than or equal to the preset threshold, the environmental training courses of the same type as the enterprise with the highest label similarity are pushed to the enterprise to be assigned courses. When the label similarity is less than the preset threshold, the course similarity is calculated based on the label of the enterprise to be assigned courses and the course keywords, and the course similarities are sorted from high to low. When there are multiple courses in the same course category, the top three environmental training courses in each category are selected for push to the enterprise. If there are courses with the same similarity, they are sorted according to the reading volume, evaluation volume and evaluation level of the courses to complete the push of environmental training courses. Preferably, in this embodiment, the preset threshold is 85%.
[0098] Furthermore, when the tag similarity is less than a preset threshold, the course similarity is calculated based on the tag of the course enterprise to be assigned and the course keyword, and the course similarity is sorted from high to low. After the top three environmental training courses with the highest course similarity in each category are pushed to the course enterprise to be assigned, the following is also included:
[0099] Update the enterprise name, enterprise label and pushed environment training courses of the enterprise to be assigned courses into the enterprise label library.
[0100] By continuously updating the enterprise tag library, more tag matching types can be provided for subsequent enterprises to be assigned courses, making it easier to find enterprises whose course similarity exceeds the preset threshold, thereby pushing environmental training courses to the enterprises to be assigned courses more quickly and accurately.
[0101] The present invention also provides an environmental training course recommendation device, such as Fig. 9 As shown, the device includes: a storage database establishment module 10, a keyword extraction module 20, a course classification module 30, an environment data acquisition module 40, an enterprise tag generation module 50, an enterprise tag library establishment module 60, and a course push module 70, wherein:
[0102] The storage database establishment module 10 is used to establish an environmental course catalog, and to establish an environmental course keyword library based on the network hot words of each sub-category course under each major category in the environmental course catalog, and to establish an environmental training course storage database using the environmental course keyword library and the environmental course catalog;
[0103] The keyword extraction module 20 is used to obtain the knowledge carrier of the environmental training course to be uploaded, extract keywords from the knowledge carrier, and calculate the weight of the keywords;
[0104] The course classification module 30 is used to match the keywords extracted from the knowledge carrier with the environmental course keyword library, classify the environmental training courses to be uploaded into the corresponding environmental course directory, and input the classification results into the environmental training course storage database for storage;
[0105] The environmental data acquisition module 40 is used to acquire the environmental data of the enterprise, perform metrological authentication and supervision on the acquired environmental data, verify the validity of the data, and use the environmental data as historical environmental statistical data and combine it with the environmental statistical data obtained by the monitoring equipment to establish an enterprise environmental monitoring database;
[0106] An enterprise label generation module 50 is used to obtain enterprise basic information, enterprise waste generation type and multi-dimensional enterprise information, and to construct an enterprise environmental profile and generate an enterprise label by combining environmental statistical data in the enterprise environmental monitoring database, wherein the multi-dimensional enterprise information includes one or more of enterprise working condition monitoring data, production and operation data, environmental credit data and tax data;
[0107] The enterprise label library establishment module 60 is used to obtain the existing environmental training courses of the enterprise and establish the enterprise label library according to the enterprise name, enterprise label and the environmental training courses of the enterprise;
[0108] The course push module 70 is used to match the labels of the enterprise to be assigned courses with the enterprises in the enterprise label library one by one to calculate the label similarity. When the label similarity is less than a preset threshold, the course similarity is calculated based on the label of the enterprise to be assigned courses and the course keywords, and the course similarities are sorted from high to low. The top three environmental training courses with the highest course similarity in each major category are pushed to the enterprise to be assigned courses; when the label similarity is greater than or equal to the preset threshold, the same type of environmental training courses as the enterprise with the highest label similarity are pushed to the enterprise to be assigned courses.
[0109] The present invention also provides a computer device, such as Fig.10 As shown, the computing device includes a processor, a memory, and a network interface connected through a system bus. The processor of the terminal device is used to provide computing and control capabilities. The memory of the terminal device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the terminal device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for recommending environmental training courses for a terminal device is implemented.
[0110] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0111] In summary, the present invention provides a method, device, equipment and storage medium for recommending environmental training courses. The method includes: extracting keywords from the knowledge carrier of the environmental training course and calculating the weight, then matching with the keywords of the existing environmental training course to complete the classification of the environmental training course, then building an enterprise portrait according to the enterprise's environmental data, enterprise basic information, enterprise waste type and multi-dimensional enterprise information, generating enterprise labels, combining the enterprise's existing environmental training courses and enterprise names to establish an enterprise label library, and matching the labels of the enterprises to be assigned courses with the enterprises in the enterprise label library to complete the push of environmental training courses. The present invention adopts the method to improve the degree of automation of pushing courses to enterprises, and avoids the traditional staff recommending environmental training courses to each enterprise, greatly improving the efficiency of recommending relevant environmental training courses to relevant enterprises. After the enterprise adopts the relevant environmental training courses, it not only increases the environmental protection awareness of the enterprise employees, but also effectively strengthens the legal supervision and management of the enterprise's environmental protection data by the enterprise employees, and strengthens the style of work of the relevant departments, promotes the enterprise to vigorously carry out relevant environmental protection publicity work, and ensures the sustainable development of the enterprise.
[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for recommending environmental training courses, characterized in that: include: Establish an environmental training course catalog, and establish an environmental training course keyword library based on the network hot words of each sub-category course under each major category in the environmental training course catalog, and establish an environmental training course storage database using the environmental training course keyword library and the environmental training course catalog; Acquire the knowledge carrier of the environment training course to be uploaded, extract keywords from the knowledge carrier, and calculate the weight of the keywords; the knowledge carrier includes one or more of text, image, audio, and video; Matching the keywords extracted from the knowledge carrier with the environmental training course keyword library, classifying the environmental training courses to be uploaded into corresponding environmental training course directories, and inputting the classification results into the environmental training course storage database for storage; Obtain the environmental data of the enterprise, perform metrological certification and supervision on the obtained environmental data, verify the validity of the data, and use the environmental data as historical environmental statistical data and combine it with the environmental statistical data obtained by monitoring equipment to establish an enterprise environmental monitoring database; Obtaining basic enterprise information, enterprise waste generation types, and multi-dimensional enterprise information combined with environmental statistical data in the enterprise environmental monitoring database to construct an environmental profile of the enterprise and generate an enterprise label, wherein the multi-dimensional enterprise information includes one or more of enterprise operating condition monitoring data, production and operation data, environmental credit data, and tax data; Obtain the company's existing environmental training courses and establish a corporate label library based on the company name, corporate label and the company's environmental training courses; The labels of the enterprise to be assigned courses are matched with the enterprises in the enterprise label library one by one to calculate the label similarity. When the label similarity is less than the preset threshold, the course similarity is calculated based on the label of the enterprise to be assigned courses and the course keywords, and the course similarity is sorted from high to low. The top three environmental training courses with the highest course similarity in each category are pushed to the enterprise to be assigned courses; when the label similarity is greater than or equal to the preset threshold, the same type of environmental training courses with the highest label similarity are pushed to the enterprise to be assigned courses; The step of extracting keywords from the knowledge carrier and calculating the weights of the keywords includes: When the knowledge carrier is text, the TF-IDF method is used to extract keywords in the text, and TF and IDF are multiplied as the weight of the keyword, where TF represents the frequency of a word appearing in the text, and IDF represents the frequency of a word appearing in other texts; When the knowledge carrier is an image, prepare classified picture data and classification labels, use the prepared pictures for network training, build a CNN image classification network, input the pictures to be classified into the CNN image classification network for classification, add category keywords according to the category name, and use the TF-IDF method to calculate the keyword weight; When the knowledge carrier is audio, an audio-to-text conversion plug-in is used to extract text descriptions in the audio, and a TF-IDF method is used to extract keywords and calculate the weights of the keywords; When the knowledge carrier is a video, the video is separated into audio and image, and the same method as that for the image and audio is used to extract keywords and calculate the weights of the keywords; The obtaining of the environmental data of the enterprise includes: The environmental data includes one or more of the Internet of Things online monitoring data, environmental credit evaluation data, whether environmental liability insurance services have been purchased, and services that have been booked. When the enterprise is a small or medium-sized waste-producing enterprise or unit, the scope, object and content of monitoring are determined, the environmental monitoring data management directory is listed, the environmental detection method is determined, and the environmental data is detected and counted according to the environmental detection method; When the enterprise is a key pollution prevention enterprise or unit, the first environmental data is obtained by testing according to the test factors on the environmental impact assessment report approval, the second environmental data is obtained by testing according to the self-monitoring plan approved on the national pollution discharge permit management information platform, the third environmental data is obtained by testing according to the customer's factory inspection system audit, the fourth environmental data is obtained by testing according to the rectification requirements put forward by the environmental protection department, and the fifth environmental data is obtained by testing the indoor working environment of the enterprise. The first to fifth environmental data are summarized to obtain the environmental data of the key pollution prevention enterprise or unit; The above mentioned measurement certification and supervision of the environmental data obtained and verification of the validity of the data include: Check whether the environmental data comes from the monitoring equipment; Check whether the monitoring equipment for environmental data has a weekly inspection certificate and whether the certificate is within the validity period; Whether the traceability identification method is correct, whether it is carried out in accordance with the operating procedures, and whether the monitoring personnel are competent; Review whether the entrusted inspection unit has dosage certification and whether it meets the authorized inspection conditions stipulated by law.
2. The method according to claim 1, characterized in that The keyword extracted from the knowledge carrier is matched with the environmental training course keyword library, and the environmental training course to be uploaded is classified into the corresponding environmental training course directory, including: The keywords that hit the course keyword library are selected and grouped from the keywords extracted from the knowledge carrier to obtain a keyword sequence. The total weight of each category is calculated based on the keyword sequence and keyword weight, and the environmental training courses to be uploaded are classified into the course category with the largest weight.
3. The method according to claim 1, characterized in that The basic information of the enterprise is obtained, including: Search the Internet for basic information about waste-generating enterprises to determine their types; Searching for enterprise information on a registered enterprise network platform to obtain enterprise data information, wherein the enterprise data information includes one or more of enterprise name, enterprise type, establishment date, and legal representative; Obtaining enterprise waste generation information according to the enterprise management platform, wherein the enterprise waste generation information includes one or more of waste generation type, waste generation main component analysis, common waste treatment methods, and waste production volume or weight per unit time; Get the geographical location, waste treatment unit, and waste transportation unit of the enterprise.
4. The method according to claim 1, characterized in that: When the tag similarity is less than the preset threshold, the course similarity is calculated based on the tag of the course enterprise to be assigned and the course keyword, and the course similarity is sorted from high to low. After the top three environmental training courses with the highest course similarity in each category are pushed to the course enterprise to be assigned, the following is also included: Update the enterprise name, enterprise label and pushed environmental training courses of the enterprise to be assigned courses into the enterprise label library.
5. An environmental training course recommendation device, characterized in that: include: A storage database establishment module is used to establish an environmental training course catalog, and to establish an environmental training course keyword library based on network hot words for each sub-category course under each major category in the environmental training course catalog, and to establish an environmental training course storage database using the environmental training course keyword library and the environmental training course catalog; A keyword extraction module is used to obtain the knowledge carrier of the environmental training course to be uploaded, extract keywords from the knowledge carrier, and calculate the weight of the keywords; the knowledge carrier includes one or more of text, image, audio, and video; A course classification module is used to match the keywords extracted from the knowledge carrier with the environmental training course keyword library, classify the environmental training courses to be uploaded into the corresponding environmental training course directory, and input the classification results into the environmental training course storage database for storage; An environmental data acquisition module is used to acquire the environmental data of the enterprise, perform metrological authentication and supervision on the acquired environmental data, verify the validity of the data, and use the environmental data as historical environmental statistical data and combine it with the environmental statistical data obtained by the monitoring equipment to establish an enterprise environmental monitoring database; An enterprise label generation module is used to obtain basic enterprise information, enterprise waste generation types, and multi-dimensional enterprise information, combined with environmental statistical data in the enterprise environmental monitoring database to construct an enterprise environmental protection portrait and generate an enterprise label, wherein the multi-dimensional enterprise information includes one or more of enterprise working condition monitoring data, production and operation data, environmental protection credit data, and tax data; The enterprise label library establishment module is used to obtain the enterprise's existing environmental training courses and establish an enterprise label library based on the enterprise name, enterprise label and the enterprise's environmental training courses; The course push module is used to match the labels of the enterprise to be assigned courses with the enterprises in the enterprise label library one by one to calculate the label similarity. When the label similarity is less than the preset threshold, the course similarity is calculated based on the label of the enterprise to be assigned courses and the course keywords, and the course similarity is sorted from high to low. The top three environmental training courses with the highest course similarity in each category are pushed to the enterprise to be assigned courses; when the label similarity is greater than or equal to the preset threshold, the same type of environmental training courses with the highest label similarity are pushed to the enterprise to be assigned courses; The keyword extraction module is also used for: When the knowledge carrier is text, the TF-IDF method is used to extract keywords in the text, and TF and IDF are multiplied as the weight of the keyword, where TF represents the frequency of a word appearing in the text, and IDF represents the frequency of a word appearing in other texts; When the knowledge carrier is an image, prepare classified picture data and classification labels, use the prepared pictures for network training, build a CNN image classification network, input the pictures to be classified into the CNN image classification network for classification, add category keywords according to the category name, and use the TF-IDF method to calculate the keyword weight; When the knowledge carrier is audio, an audio-to-text conversion plug-in is used to extract text descriptions in the audio, and a TF-IDF method is used to extract keywords and calculate the weights of the keywords; When the knowledge carrier is a video, the video is separated into audio and image, and the same method as that for the image and audio is used to extract keywords and calculate the weights of the keywords; The environmental data acquisition module is also used for: The environmental data includes one or more of the Internet of Things online monitoring data, environmental credit evaluation data, whether environmental liability insurance services have been purchased, and services that have been booked. When the enterprise is a small or medium-sized waste-producing enterprise or unit, the scope, object and content of monitoring are determined, the environmental monitoring data management directory is listed, the environmental detection method is determined, and the environmental data is detected and counted according to the environmental detection method; When the enterprise is a key pollution prevention enterprise or unit, the first environmental data is obtained by testing according to the test factors on the environmental impact assessment report approval, the second environmental data is obtained by testing according to the self-monitoring plan approved on the national pollution discharge permit management information platform, the third environmental data is obtained by testing according to the customer's factory inspection system audit, the fourth environmental data is obtained by testing according to the rectification requirements put forward by the environmental protection department, and the fifth environmental data is obtained by testing the indoor working environment of the enterprise. The first to fifth environmental data are summarized to obtain the environmental data of the key pollution prevention enterprise or unit; Check whether the environmental data comes from the monitoring equipment; Check whether the monitoring equipment for environmental data has a weekly inspection certificate and whether the certificate is within the validity period; Whether the traceability identification method is correct, whether it is carried out in accordance with the operating procedures, and whether the monitoring personnel are competent; Review whether the entrusted inspection unit has dosage certification and whether it meets the authorized inspection conditions stipulated by law.
6. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the environmental training course recommendation method according to any one of claims 1 to 4 are implemented.
7. 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 steps of the environmental training course recommendation method according to any one of claims 1 to 4 are implemented.
Citation Information
Patent Citations
Network service recommending method and device
CN104166713A
Course matching method and system, computer equipment and storage medium
CN112052396A
Object recommendation method and device, computer equipment and medium
CN112579909A
Course recommendation method and device, server and storage medium
CN113139750A
Audio-visual teaching platform and recommendation subsystem, analysis subsystem, recommendation method, analysis method thereof
US20200051450A1
