A method and related device for on-site inspection and identification of medium and high risk personnel

Abstract

The present invention provides a method and related device for on-site inspection and identification of medium- and high-risk personnel, including obtaining a work plan sheet and a sign-in record sheet of medium- and high-risk operations to be identified, associating the work plan sheet and the sign-in record sheet and merging the contents with the same attributes to obtain a merged data table; using a pre-trained recognition model to identify the text content of the data table to extract feature data in the text content; processing the feature data to form a feature text, and matching the feature text with a preset hierarchical rule library to determine the hierarchical information of the data table; matching the on-site identification rules of the medium- and high-risk operations to be identified based on the hierarchical information, and identifying the data table according to the on-site identification rules. The present invention comprehensively, efficiently and accurately identifies the supervision of production site operations within the jurisdiction of each level of power operations, thereby providing accurate reference information for the management of power operation safety supervision.

Description

Technical Field

[0001] The present invention belongs to the technical field of power operation supervision and assessment, and in particular relates to a method for identifying medium- and high-risk personnel on-site supervision and related devices. Background Art

[0002] In the power operation system, each unit should carry out full-process supervision of production site operations within its jurisdiction based on the operation risk level, control strategy, and reference to the standards and key control points. Checking the supervision of medium- and high-risk personnel is an important way to supervise the implementation of supervision responsibilities. By identifying whether the supervisors of medium- and high-risk operation plans are actually in place, it can effectively prevent the supervision responsibilities from not being implemented.

[0003] There are no specific measures to investigate the supervision situation in the existing technology. A relatively close technology is a method for extracting key elements of power grid supervision indicators. This method takes the strengthening of supervision on power grid enterprises under the new situation of power reform as the background. By sorting out the power grid supervision documents issued in recent years, the specific requirements for power grid enterprises are classified and analyzed; the impact of supervision requirements on power grid development is analyzed, and the influencing factors of power grid development are summarized; based on ISM technology, the path of action of specific supervision requirements on power grid development is identified; based on sensitivity analysis technology, the impact of supervision factors on power grid development is quantified, and ANP technology is used to establish a method for identifying key elements that affect power grid development under supervision conditions, and combined with example power grid research, key supervision elements are extracted; the specific impact of specific supervision requirements on power grid development can be grasped and the action path can be clarified; the key elements that affect power grid development under supervision conditions are analyzed, and key supervision elements are extracted.

[0004] However, the method for extracting key elements of grid regulatory indicators is used to evaluate the impact of regulatory elements on grid development, and does not identify the implementation of power operation supervision. Summary of the invention

[0005] In view of this, the present invention aims to provide a method and related device for on-site inspection and identification of medium and high-risk personnel, so as to identify the implementation of power operation supervision.

[0006] In order to achieve the above object, the technical solution provided by the present invention is as follows:

[0007] In a first aspect, the present invention provides a method for on-site inspection and identification of medium- and high-risk personnel, comprising the following steps:

[0008] Obtain the work plan and sign-in record sheet for the medium and high risk work to be identified;

[0009] The work plan sheet and the sign-in record sheet are associated and the contents with the same attributes are merged to obtain a merged data sheet;

[0010] Using the pre-trained recognition model to recognize the text content of the data table to extract feature data from the text content, where the feature data is text data related to the hierarchical information;

[0011] After processing the feature data, the feature text is formed, and the feature text is matched with a preset hierarchical rule library to determine the hierarchical information of the data table;

[0012] Based on the hierarchical information, the in-place identification rules of the medium and high-risk operations to be identified are matched, and the data table is identified according to the in-place identification rules.

[0013] Furthermore, the process of establishing the hierarchical rule base includes:

[0014] Collect the corpus related to each level and the corpus that is definitely not related to each level in the historical plan data;

[0015] Generate the initial level corpus of each level based on the related corpus of each level, and generate the negative semantic corpus of each level based on the unrelated corpus. Both the initial level corpus and the negative semantic corpus include several key texts.

[0016] For each level, obtain the word frequency features of the key texts in the initial level corpus and sort them according to the word frequency;

[0017] Remove stop words and their frequency from the sorted initial level corpus;

[0018] The remaining word frequency features in the initial level corpus are used as weight features of the corresponding key texts;

[0019] The key texts of the initial level corpus are screened according to a preset weight threshold, and it is determined whether the screened initial level corpus meets the conditions of obvious distinction from the initial level corpora of other levels and the negative semantic corpus of the corresponding level;

[0020] If not, the weight threshold is readjusted and the screening is repeated until the screened initial level corpus meets the obvious distinction condition, and the screened initial level corpus is used as the level rule library of the corresponding level.

[0021] Furthermore, the in-place identification rules correspond one-to-one to each professional category at each level, and the professional categories at least include:

[0022] Substation categories, management unit categories, and professional categories of guarantee systems and supervision systems;

[0023] The substation category’s presence identification rules determine the presence of each level based on the job type and risk level attributes in the data table;

[0024] The presence identification rules of the management unit category judge the presence of each level based on the risk level attributes or the operation subject and risk level attributes in the data table;

[0025] When the professional categories of the guarantee system and supervision system are biotechnology, scheduling and marketing, the corresponding in-place identification rules judge the in-place status of each level based on the system type, professional category and risk level attributes in the data table;

[0026] When the professional category of the supervision system is infrastructure, the corresponding presence identification rules judge the presence of personnel based on the personnel dictionary table of the supervision system.

[0027] Furthermore, substation categories include key important substations and non-key important substations, and the corresponding in-place identification rules are as follows:

[0028] The identification rule of the key and important substations in place is to query the key substations from the work location attribute of the data table, and the project management unit attribute does not contain the district bureau name, and the operation plan number attribute does not contain data starting with JJ. If the operation type is operation type, and the risk level is intermediate or advanced, and there are sign-in records at the team level or power supply station level, the second-level organization level, and the municipal level, it is judged to be in place; if the operation type is non-operational, and the risk level is intermediate, and there are sign-in records at the team level or power supply station level, and the second-level organization level, it is judged to be in place; if the operation type is non-operational, and the risk level is advanced, and there are sign-in records at the team level or power supply station level, the second-level organization level, and the municipal level, it is judged to be in place;

[0029] The identification rule for the presence of non-critical important substations is to query the work location attribute of the data table and not include critical substations, and the project management unit attribute does not include the district bureau name, and the operation plan number attribute does not contain data starting with JJ; if the operation type is operation type, and the risk level is intermediate or advanced, and there are sign-in records at the team level or power supply station level, the second-level organization level, and the municipal level, then it is judged to be in place; if the operation type is non-operational, and the risk level is intermediate, and there are sign-in records at the team level or power supply station level, and the second-level organization level, then it is judged to be in place; if the operation type is non-operational, and the risk level is advanced, and there are sign-in records at the team level or power supply station level, the second-level organization level, and the municipal level, then it is judged to be in place.

[0030] Furthermore, the management unit category includes transmission management unit and distribution management unit, and the corresponding in-place identification rules are as follows:

[0031] The rule for identifying the presence of the transmission management unit is to query the records containing the transmission management unit from the project management unit attributes of the data table; if the attribute of the operating subject is the unit itself, and the risk level is intermediate or advanced, and there are check-in records at the team level or the power supply station level, the second-level organization level, and the prefectural and municipal levels, it is judged to be in place; if the attribute of the operating subject is an external unit, and the risk level is intermediate, and there are check-in records at the team level or the power supply station level, and the second-level organization level, it is judged to be in place; if the attribute of the operating subject is an external unit, and the risk level is advanced, and there are check-in records at the team level or the power supply station level, the second-level organization level, and the prefectural and municipal levels, it is judged to be in place;

[0032] The rule for identifying the presence of distribution management units is to query the records containing district bureaus from the project management unit attributes in the data table. If the risk level is intermediate or advanced, and there are sign-in records at the team level or power supply station level and at the secondary organization level and municipal level, it is judged to be in place.

[0033] Furthermore, when the professional categories of the guarantee system and supervision system are biotechnology, scheduling and marketing, the corresponding in-place identification rules are as follows:

[0034] The identification rule for the presence of dispatching professionals in the guarantee system is to select the guarantee system from the system type in the data table, and select the records of the dispatching profession from the professional category attribute, and then further identify according to the following rules: If the risk level attribute is medium risk level, and there are sign-in records at the team level or power supply station level, the secondary organization level, and the municipal level, it is judged to be in place; if the risk level attribute is high risk level, there are no less than 2 sign-in records at the team level or power supply station level, and there are sign-in records at the municipal level, it is judged to be in place;

[0035] The identification rule for the presence of infrastructure professionals in the guarantee system is to select the guarantee system from the system type in the data table, and select the records of infrastructure professionals in the professional category attribute, and then further identify according to the following rules: If the risk level attribute is medium risk or high risk level, and there is a sign-in record at one of the levels of the team level, power supply station level, secondary organization level, and prefecture-level city level, it is judged to be in place;

[0036] The identification rule for the marketing professional in place of the guarantee system is to select the guarantee system from the system type in the data table, and select the record of the marketing professional from the professional category attribute, and then further identify it according to the following rules: If the risk level attribute is medium risk or high risk level, and there is a sign-in record at one of the levels of the team level, power supply station level, secondary organization level, and prefecture-level city level, it is judged to be in place;

[0037] The rules for identifying the presence of biotechnology, dispatching, and marketing professionals in the supervision system are to select the supervision system from the system type in the data table, and select the records of biotechnology, dispatching, or marketing professionals in the professional category attribute, and then further identify them according to the following rules: If the risk level attribute is medium risk or high risk level, and the project management unit is a district bureau, it is judged to be in place if there are sign-in records at the power supply station, county bureau, and municipal level at the same time; if the project management unit is not a district bureau, it is judged to be in place if there are sign-in records at the secondary agency and municipal level at the same time.

[0038] Furthermore, when the professional category of the supervision system is infrastructure, the corresponding in-place identification rules are as follows:

[0039] In the personnel dictionary table of the inspection system, if the department to which the personnel belongs is the project management center and the check-in record obtained from the smart engineering system contains the check-in information of the personnel, then they are judged to be in place; if they are not personnel of the project management center and the check-in record obtained from the smart safety and supervision system contains the check-in information of the personnel, then they are judged to be in place.

[0040] In a second aspect, the present invention provides a device for supervising and identifying medium- and high-risk personnel, comprising:

[0041] A data acquisition module is used to obtain the work plan and sign-in record sheet of the medium and high risk work to be identified;

[0042] The data preprocessing module is used to associate the work plan sheet with the sign-in record sheet and merge the contents with the same attributes to obtain a merged data sheet;

[0043] A hierarchical recognition module, used to recognize the text content of the data table using a pre-trained recognition model to extract feature data from the text content, where the feature data is text data related to hierarchical information;

[0044] A hierarchical matching module is used to process the feature data to form feature text, and match the feature text with a preset hierarchical rule library to determine the hierarchical information of the data table;

[0045] The in-place identification module is used to match the in-place identification rules of the medium and high-risk operations to be identified based on the hierarchical information, and identify the data table according to the in-place identification rules.

[0046] Accordingly, the present invention also provides a computer device, the device comprising a processor and a memory:

[0047] The memory is used to store the computer program and send the instructions of the computer program to the processor;

[0048] The processor executes a method for on-site inspection and identification of medium- and high-risk personnel as described in the first aspect according to the instructions of the computer program.

[0049] Correspondingly, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, a method for on-site inspection and identification of medium- and high-risk personnel as in the first aspect is implemented.

[0050] In summary, the present invention provides a method and related device for on-site inspection and identification of medium- and high-risk personnel, including obtaining a work plan sheet and a sign-in record sheet of the medium- and high-risk operations to be identified, associating the work plan sheet and the sign-in record sheet and merging the contents with the same attributes to obtain a merged data table; using a pre-trained recognition model to identify the text content of the data table to extract feature data in the text content, the feature data being text data related to hierarchical information; processing the feature data to form a feature text, and matching the feature text with a preset hierarchical rule library to determine the hierarchical information of the data table; matching the on-site identification rules of the medium- and high-risk operations to be identified based on the hierarchical information, and identifying the data table according to the on-site identification rules. The present invention comprehensively, efficiently and accurately identifies the supervision of production site operations within the jurisdiction of each level of power operations, thereby providing accurate reference information for the management of power operation safety supervision, thereby ensuring the accuracy of power operation safety supervision results. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 A flowchart of a method for on-site inspection and identification of medium- and high-risk personnel provided by an embodiment of the present invention;

[0053] Figure 2 A flowchart for constructing a corpus rule library provided by an embodiment of the present invention;

[0054] Figure 3 A schematic diagram of matching feature data and a rule base provided in an embodiment of the present invention;

[0055] Figure 4 A block diagram of a device for inspecting and identifying medium- and high-risk personnel provided by an embodiment of the present invention;

[0056] Figure 5 A block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] See also Figure 1 This embodiment provides a method for identifying medium- and high-risk personnel on-site inspection, including the following steps:

[0059] S11: Obtain the work plan and sign-in record sheet for the medium and high risk work to be identified.

[0060] It should be noted that the operation plan and sign-in record data of the smart safety and supervision system are obtained by developing an automatic collection program. The smart safety and supervision system is an internal data system of the power system. The operation plan usually contains detailed information such as the time, location, participants, and operation type of the operation. The sign-in record sheet records the information of the actual on-site personnel, such as name, work number, arrival time, etc.

[0061] S12: Associating the work plan sheet with the sign-in record sheet and merging the contents with the same attributes to obtain a merged data sheet.

[0062] It should be noted that this step is to compare the relevant information (such as the personnel list) in the work plan sheet with the sign-in record sheet to ensure that the corresponding items in the two documents can be correctly associated. The obtained work plan sheet and the sign-in record sheet can be associated by the work plan number, and the attributes of the two can be merged to better analyze the data.

[0063] S13: Using the pre-trained recognition model to recognize the text content of the data table to extract feature data from the text content, where the feature data is text data related to the hierarchical information.

[0064] It should be noted that the unit levels to which the work plan belongs are identified based on the merged data table. The unit levels may include work teams, power supply stations, county power supply bureaus, secondary institutions, and municipal power supply bureaus. The identification items of each unit level include work team level identification, power supply station level identification, county power supply bureau level identification, secondary institution level identification, and municipal power supply bureau level identification.

[0065] Feature data is key information extracted from text, such as personnel's job level, job type, etc. This information is crucial for determining the risk level of the job.

[0066] S14: Processing the feature data to form feature text, and matching the feature text with a preset hierarchical rule library to determine hierarchical information of the data table.

[0067] It should be noted that the structured information extracted from the raw data in this step is convenient for computer processing. Then, a set of rules defined according to the organizational structure or job characteristics are used to determine the task requirements at different levels. The unit level to which the job belongs is determined by comparing the feature text with the hierarchical rule base.

[0068] S15: Matching the in-place identification rules of the medium and high risk operations to be identified based on the hierarchical information, and identifying the data table according to the in-place identification rules.

[0069] It should be noted that according to the specific requirements defined by the hierarchical information, for example, what qualifications of personnel are required to be present to supervise or execute a certain level of work. Finally, statistical analysis is conducted on the status of each unit level and each professional category: taking each unit as a group and each professional category as a classification, statistics are conducted on the status of each unit level and each unit category.

[0070] This embodiment provides a method for on-site inspection and identification of medium and high-risk personnel, which comprehensively, efficiently and accurately identifies the supervision of production site operations within the jurisdiction of each level of power operations, thereby providing accurate reference information for the management of power operation safety supervision, thereby ensuring the accuracy of power operation safety supervision results.

[0071] The content of the hierarchical rule base is the key identification criteria for the identification model identification team, power supply station, county power supply bureau, secondary organization, municipal power supply bureau and other levels. Using the tf-idf algorithm, data mining is performed on historical data to construct a hierarchical rule base. The construction process of the hierarchical rule base is as follows: Figure 2 As shown, the following steps are included:

[0072] S21: Collect the corpus related to each level and the corpus that is definitely not related to each level in the historical plan data.

[0073] It should be noted that sentence fragments related to the work team are collected from the historical plan data. Each sentence fragment related to the plan constitutes a work team document, and multiple work team documents constitute a work team corpus. In addition, based on actual business needs, for the work team level category, it is also necessary to collect sentence fragments that are not related to the work team in the historical data, repeat the previous steps, and construct a work team negative semantic corpus.

[0074] S22: generating an initial level corpus of each level based on the associated corpus of each level, and generating a negative semantic corpus of each level based on the unassociated corpus, wherein both the initial level corpus and the negative semantic corpus include a number of key texts.

[0075] It should be noted that the initial level corpus can be processed by using word segmentation tools, such as Jieba word segmentation. Then, the word frequency features of the class corpus are constructed using the tf-idf algorithm. Tf-idf uses the following formula to evaluate the word frequency-inverse document frequency in the corpus.

[0076]

[0077] in, Indicates the number of times a word appears in the jth article. represents the total number of words in the jth article; is the total number of documents, is the number of documents containing word word.

[0078] The initial level corpus is constructed by combining the word segmentation results and their word frequency features.

[0079] S23: For each level, obtain the word frequency features of the key texts in the initial level corpus and sort them according to the word frequency.

[0080] It should be noted that this step sorts the words according to the calculated TF-IDF values ​​to find the keywords that best represent a certain level.

[0081] S24: Remove stop words and their frequency from the sorted initial level corpus.

[0082] It should be noted that this step removes stop words in the text to reduce text noise.

[0083] S25: Use the remaining word frequency features in the initial level corpus as weight features of the corresponding key text.

[0084] It should be noted that the TF-IDF values ​​of the retained words are regarded as weighted features of the key text.

[0085] S26: Filter the key texts of the initial level corpus according to the preset weight threshold, and judge whether the filtered initial level corpus meets the obvious difference condition with the initial level corpus of other levels and the negative semantic corpus of the corresponding level. Whether the obvious difference condition is met can be judged by similarity / distance measurement, mutual information, cluster analysis and other methods.

[0086] It should be noted that a threshold is set to filter out the most important keywords. The filtered keywords should be able to clearly distinguish the differences between different levels.

[0087] S27: If not, then readjust the weight threshold and re-screen until the screened initial level corpus meets the condition of obvious distinction, and use the screened initial level corpus as the level rule library of the corresponding level.

[0088] It should be noted that if the screening results cannot clearly distinguish the levels, it is necessary to adjust the threshold and re-screen the process. The final set of keywords screened out constitutes the hierarchical rule library for subsequent text classification and hierarchical identification.

[0089] The following is an example of a hierarchical rule base divided into levels such as work teams, power supply stations, county power supply bureaus, and secondary institutions:

[0090]

[0091] Based on the hierarchical rule base constructed in the above steps, the input data received by the recognition model is the sample data of the plan and the check-in record. After receiving the sample data, the recognition model will extract the characteristic text data or characteristic data from the sample data, and then process the characteristic text data of the long text type into characteristic data using the word segmentation tool, and match the corresponding characteristic data with the corresponding hierarchical rule base. Figure 3 shown.

[0092] Furthermore, the matching of feature data and hierarchical rule base uses Levenshtein edit distance and regular matching to comprehensively judge the matching degree. The smaller the edit distance, the more matching the two texts are. When the edit distance between a keyword in the feature data and a keyword in the rule base is less than the set threshold, or when it is judged based on the regular method that a keyword in the feature data contains a keyword in the rule base, the number of matches of the keyword in the rule base is increased by one.

[0093] Next, the matching score of the feature data is calculated based on the following formula:

[0094]

[0095] where w i is the weight of the ith keyword in the rule base, t i is the number of matches of the i-th keyword in the rule base.

[0096] Finally, a reasonable threshold is set. When the score exceeds this threshold, it is considered that the text data corresponding to the feature data records the information of this level, and the recognition model classifies the text data into this level.

[0097] In some embodiments, according to the risk management and control work instruction document, the level of in-place requirements need to be identified from the system and professional dimensions. It mainly includes two major systems, "supervision system" and "security system", four professional categories, "biotechnology", "dispatching", "marketing", and "infrastructure", as well as substation categories and management unit categories. The idea of ​​identification is to query the qualified data according to the requirements of the work instruction document. Each rule corresponds to a batch of work plan data. According to the data screened out by each rule, the level of personnel in place is required to judge whether it meets the in-place standard. The in-place identification rule of the substation category is based on the job type and risk level attributes in the data table to judge the in-place status of each level; the in-place identification rule of the management unit category is based on the risk level attribute or the operation subject and risk level attribute in the data table to judge the in-place status of each level; when the professional categories of the security system and the supervision system are biotechnology, dispatching and marketing, the corresponding in-place identification rules are based on the system type, professional category and risk level attributes in the data table to judge the in-place status of each level; when the professional category of the supervision system is infrastructure, the corresponding in-place identification rules are based on the inspection system personnel dictionary table to judge the in-place status of personnel.

[0098] In some embodiments, the team level identification includes: extracting records whose keywords include "team" or "operation and inspection" and do not include "leader" from "affiliated units" and "affiliated departments", and classifying them as team level if they meet the conditions;

[0099] The power supply station level identification includes: extracting keywords including "power supply station" from "affiliated units" and "affiliated departments" and classifying them as power supply station level;

[0100] The identification of the county power supply bureau level includes: sorting out the power supply bureau list of each city power supply bureau according to different municipal bureaus to form a dictionary item, and then extracting the records whose keywords contain the name of the power supply bureau dictionary item from the "affiliated unit" of the data table, and excluding the records of the "work group and power supply station" level that have been identified, and classifying those that meet the conditions as the county power supply bureau level;

[0101] Second-level organization level identification includes: There are two cases for second-level organization level identification. In the first case, the "project management unit name" and "affiliated unit" attributes of each record are extracted from the data table. If the "project management unit name" attribute value contains "project management center" and the "affiliated unit" attribute value contains the "substation management" keyword, it is classified as a second-level organization level; in the second case, the affiliated unit is matched with the power supply bureau dictionary list, and the records of the power supply bureau whose "affiliated unit" contains the dictionary item are excluded, and the remaining units belong to the second-level organization level;

[0102] The identification of the municipal power supply bureau hierarchy includes: using the elimination method, except for the already classified work teams, power supply stations, county power supply bureaus, and secondary institutions, the rest can be classified into the municipal power supply bureau hierarchy.

[0103] In some embodiments, identification of the presence of key and important substations: query the "workplace" attribute of the data table to include "key substations", and the "project management unit" attribute does not include the district bureau name, and the "operation plan number" attribute does not include data starting with "JJ". Among them, "key substations" are maintained through a dictionary table. If the "operation type" is an operation type, and the "risk level" is intermediate or advanced, there are sign-in records at the team level or the power supply station level and the secondary organization level and the municipal level, it can be judged to be in place. If the "operation type" is a non-operation type, and the "risk level" is intermediate, there are sign-in records at the team level or the power supply station level and the secondary organization level, it can be judged to be in place. If the "operation type" is a non-operation type, and the "risk level" is advanced, there are sign-in records at the team level or the power supply station level and the secondary organization level and the municipal level, it can be judged to be in place.

[0104] Identification of non-critical important substations in place: query the "workplace" attribute of the data table to find data that does not contain "critical substations", and the "project management unit" attribute does not contain the district bureau name, and the "operation plan number" attribute does not contain data starting with "JJ". Among them, "critical substations" are maintained through a dictionary table. If the "operation type" is an operation type, and the "risk level" is intermediate or advanced, there are check-in records at the team level or the power supply station level, the second-level organization level, and the prefecture-level level, it can be judged to be in place. If the "operation type" is a non-operation type, and the "risk level" is intermediate, there are check-in records at the team level or the power supply station level, and the second-level organization level, it can be judged to be in place. If the "operation type" is a non-operation type, and the "risk level" is advanced, there are check-in records at the team level or the power supply station level, the second-level organization level, and the prefecture-level level, it can be judged to be in place.

[0105] In some embodiments, the identification of the presence of the power transmission management unit includes: querying the record containing the "power transmission management unit" from the "project management unit" attribute of the data table; if the "operation subject" attribute is "this unit", and the "risk level" is intermediate or advanced, there are check-in records at the team level or the power supply station level and the secondary organization level and the municipal level, it can be judged that it is in place; if the "operation subject" attribute is "external unit", and the "risk level" is intermediate, there are check-in records at the team level or the power supply station level and the secondary organization level, it can be judged that it is in place; if the "operation subject" attribute is "external unit", and the "risk level" is advanced, there are check-in records at the team level or the power supply station level and the secondary organization level and the municipal level, it can be judged that it is in place;

[0106] Identification of the presence of distribution management units includes: querying the records containing district bureaus from the "project management unit" attribute of the data table. If the "risk level" is intermediate or advanced, and there are sign-in records at the team level or power supply station level and the secondary organization level and the municipal level, it can be determined that the unit is in place.

[0107] In some embodiments, the identification of the dispatching professional presence of the guarantee system includes: selecting the guarantee system from the "system type" of the data table, and selecting the record of the dispatching professional from the "professional category" attribute, and then further identifying according to the following rules; if the "risk level" attribute is a medium risk level, there are check-in records at the team level or the power supply station level and the secondary organization level and the prefecture-level level, it can be judged to be in place; if the "risk level" attribute is a high risk level, there are check-in records at the team level or the power supply station level for no less than 2 times and there are check-in records at the prefecture-level level, it can be judged to be in place;

[0108] The identification of the presence of infrastructure professionals in the barrier system includes: selecting the guarantee system from the "system type" of the data table, and selecting the records of infrastructure professionals in the "professional category" attribute, and then further identifying according to the following rules; if the "risk level" attribute is medium risk or high risk level, and there is a sign-in record at one of the levels of the team level, power supply station level, secondary organization level, and prefecture-level city level, it can be judged that it is in place;

[0109] The identification of whether the marketing major of the guarantee system is in place includes: selecting the guarantee system from the "system type" of the data table, and selecting the record of the marketing major from the "professional category" attribute, and then further identifying according to the following rules; if the "risk level" attribute is medium risk or high risk level, and there is a sign-in record at one of the levels of the team level, power supply station level, secondary organization level, and prefecture-level city level, it can be judged that it is in place;

[0110] The identification of the presence of biotechnology, dispatching, and marketing professionals in the supervision system includes: selecting the supervision system from the "System Type" in the data table, and selecting the records of biotechnology, dispatching, or marketing professionals in the "Professional Category" attribute, and then further identifying according to the following rules: If the "Risk Level" attribute is medium risk or high risk, and the "Project Management Unit" is a district bureau, it is necessary to have sign-in records at the power supply station, county bureau, and municipal level at the same time to be judged as in place; if the "Project Management Unit" is not a district bureau, it is necessary to have sign-in records at the secondary agency and municipal level at the same time to be judged as in place.

[0111] In some embodiments, the identification of the presence of infrastructure professionals in the supervision system includes: in the dictionary table of personnel in the inspection system, if the department to which the personnel belongs is the project management center, and the check-in record obtained from the smart engineering system contains the check-in information of the personnel, then it can be judged that they are in place; if they are not personnel of the project management center, and the check-in record obtained from the smart safety supervision system contains the check-in information of the personnel, then they can be judged to be in place.

[0112] Based on the same inventive concept, the embodiment of the present application also provides a medium- and high-risk personnel on-site inspection and identification device for implementing the medium- and high-risk personnel on-site inspection and identification method involved in the above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiment of the medium- and high-risk personnel on-site inspection and identification device provided below can be referred to the limitations of the medium- and high-risk personnel on-site inspection and identification method above, and will not be repeated here.

[0113] See also Figure 4 This embodiment provides a device for inspecting and identifying medium- and high-risk personnel, including:

[0114] A data acquisition module is used to obtain the work plan and sign-in record sheet of the medium and high risk work to be identified;

[0115] The data preprocessing module is used to associate the work plan sheet with the sign-in record sheet and merge the contents with the same attributes to obtain a merged data sheet;

[0116] A hierarchical recognition module, used to recognize the text content of the data table using a pre-trained recognition model to extract feature data from the text content, where the feature data is text data related to hierarchical information;

[0117] A hierarchical matching module is used to process the feature data to form feature text, and match the feature text with a preset hierarchical rule library to determine the hierarchical information of the data table;

[0118] The in-place identification module is used to match the in-place identification rules of the medium and high-risk operations to be identified based on the hierarchical information, and identify the data table according to the in-place identification rules.

[0119] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0120] Reference Figure 5 An embodiment of the present invention further provides a computer device, including: a memory and a processor and a computer program stored in the memory. When the computer program is executed on the processor, a method for on-site inspection and identification of medium- and high-risk personnel as described in any of the above methods is implemented.

[0121] The computer device may be a desktop computer, a notebook, a PDA, a cloud server or other computing device. The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 5 It is only an example of a computer device and does not constitute a limitation of the computer device. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0122] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0123] In some embodiments, the memory may be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Further, the memory may also include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as program code of a computer program. The memory may also be used to temporarily store data that has been output or is to be output.

[0124] An embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, a method for on-site inspection and identification of medium- and high-risk personnel as described in any of the above methods is implemented.

[0125] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera / terminal device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0126] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0127] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0128] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0129] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. 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 identifying medium- and high-risk personnel on-site inspection, characterized in that: The steps include: Obtain the work plan and sign-in record sheet for the medium and high risk work to be identified; Associating the work plan sheet with the sign-in record sheet and merging contents with the same attributes to obtain a merged data sheet; Using a pre-trained recognition model to recognize text content of the data table to extract feature data from the text content, wherein the feature data is text data related to hierarchical information; Processing the feature data to form feature text, and matching the feature text with a preset hierarchical rule library to determine hierarchical information of the data table; Matching the in-place identification rules of the medium- and high-risk operations to be identified based on the hierarchical information, and identifying the data table according to the in-place identification rules; The in-place identification rules correspond one-to-one to each professional category at each level, and the professional categories at least include: Substation categories, management unit categories, and professional categories of guarantee systems and supervision systems; The substation category's presence identification rule determines the presence of each level based on the job type and risk level attributes in the data table; The presence identification rule of the management unit category determines the presence of each level based on the risk level attribute or the operation subject and the risk level attribute in the data table; When the professional categories of the assurance system and the supervision system are biotechnology, scheduling and marketing, the corresponding in-place identification rules judge the in-place status of each level based on the system type, professional category and risk level attributes in the data table; When the professional category of the supervision system is infrastructure, the corresponding presence identification rule determines the presence of personnel based on the inspection system personnel dictionary table; The substation categories include key and important substations and non-key and important substations, and the corresponding in-place identification rules are as follows: The identification rule of the key and important substations in place is to query the key substations from the work location attribute of the data table, and the project management unit attribute does not contain the district bureau name, and the operation plan number attribute does not contain data starting with JJ. If the operation type is operation type, and the risk level is intermediate or advanced, and there are sign-in records at the team level or power supply station level, the second-level organization level, and the municipal level, it is judged to be in place; if the operation type is non-operational, and the risk level is intermediate, and there are sign-in records at the team level or power supply station level, and the second-level organization level, it is judged to be in place; if the operation type is non-operational, and the risk level is advanced, and there are sign-in records at the team level or power supply station level, the second-level organization level, and the municipal level, it is judged to be in place; The identification rule for the presence of non-critical important substations is to query the work location attribute of the data table and not include critical substations, and the project management unit attribute does not include the district bureau name, and the operation plan number attribute does not contain data starting with JJ; if the operation type is operation type, and the risk level is intermediate or advanced, and there are sign-in records at the team level or power supply station level, the second-level organization level, and the municipal level, then it is judged to be in place; if the operation type is non-operational, and the risk level is intermediate, and there are sign-in records at the team level or power supply station level, and the second-level organization level, then it is judged to be in place; if the operation type is non-operational, and the risk level is advanced, and there are sign-in records at the team level or power supply station level, the second-level organization level, and the municipal level, then it is judged to be in place.

2. The method for inspecting and identifying medium- and high-risk personnel according to claim 1 is characterized in that: The process of establishing the hierarchical rule base includes: Collect the corpus related to each level and the corpus that is definitely not related to each level in the historical plan data; Generating an initial level corpus of each level based on the associated corpus of each level, and generating a negative semantic corpus of each level based on the unassociated corpus, wherein both the initial level corpus and the negative semantic corpus include a number of key texts; For each level, the word frequency features of the key texts in the initial level corpus are obtained and sorted according to the word frequency; Removing stop words and their word frequencies from the sorted initial level corpus; Using the remaining word frequency features in the initial level corpus as the corresponding weight features of the key text; The key text of the initial level corpus is screened according to a preset weight threshold, and it is determined whether the screened initial level corpus meets the condition of obvious distinction from the initial level corpora of other levels and the negative semantic corpus of the corresponding level; If not, the weight threshold is readjusted and the screening is performed again until the screened initial level corpus meets the condition of obvious distinction, and the screened initial level corpus is used as the level rule library of the corresponding level.

3. The method for inspecting and identifying medium- and high-risk personnel according to claim 1 is characterized in that: The management unit categories include transmission management units and distribution management units, and the corresponding in-place identification rules are as follows: The rule for identifying the presence of the transmission management unit is to query the records containing the transmission management unit from the project management unit attributes of the data table; if the attribute of the operating subject is the unit itself, and the risk level is intermediate or advanced, and there are check-in records at the team level or the power supply station level, the second-level organization level, and the prefectural and municipal levels, it is judged to be in place; if the attribute of the operating subject is an external unit, and the risk level is intermediate, and there are check-in records at the team level or the power supply station level, and the second-level organization level, it is judged to be in place; if the attribute of the operating subject is an external unit, and the risk level is advanced, and there are check-in records at the team level or the power supply station level, the second-level organization level, and the prefectural and municipal levels, it is judged to be in place; The rule for identifying the presence of distribution management units is to query the records containing district bureaus from the project management unit attributes in the data table. If the risk level is intermediate or advanced, and there are sign-in records at the team level or power supply station level and at the secondary organization level and municipal level, it is judged to be in place.

4. The method for inspecting and identifying medium- and high-risk personnel according to claim 1 is characterized in that: When the professional categories of the guarantee system and the supervision system are biotechnology, scheduling and marketing, the corresponding in-place identification rules are as follows: The identification rule for the presence of dispatching professionals in the guarantee system is to select the guarantee system from the system type in the data table, and select the records of the dispatching profession from the professional category attribute, and then further identify according to the following rules: If the risk level attribute is medium risk level, and there are sign-in records at the team level or power supply station level, the secondary organization level, and the municipal level, it is judged to be in place; if the risk level attribute is high risk level, there are no less than 2 sign-in records at the team level or power supply station level, and there are sign-in records at the municipal level, it is judged to be in place; The identification rule for the presence of infrastructure professionals in the guarantee system is to select the guarantee system from the system type in the data table, and select the records of infrastructure professionals in the professional category attribute, and then further identify according to the following rules: If the risk level attribute is medium risk or high risk level, and there is a sign-in record at one of the levels of the team level, power supply station level, secondary organization level, and prefecture-level city level, it is judged to be in place; The identification rule for the marketing professional in place of the guarantee system is to select the guarantee system from the system type in the data table, and select the record of the marketing professional from the professional category attribute, and then further identify it according to the following rules: If the risk level attribute is medium risk or high risk level, and there is a sign-in record at one of the levels of the team level, power supply station level, secondary organization level, and prefecture-level city level, it is judged to be in place; The rules for identifying the presence of biotechnology, dispatching, and marketing professionals in the supervision system are to select the supervision system from the system type in the data table, and select the records of biotechnology, dispatching, or marketing as the professional category attribute, and then further identify according to the following rules: If the risk level attribute is medium risk or high risk level, and the project management unit is a district bureau, it is judged to be in place if there are sign-in records at the power supply station, county bureau, and municipal level at the same time; if the project management unit is not a district bureau, it is judged to be in place if there are sign-in records at the secondary agency and municipal level at the same time.

5. The method for inspecting and identifying medium- and high-risk personnel according to claim 1 is characterized in that: When the professional category of the supervision system is infrastructure, the corresponding in-place identification rules are as follows: In the personnel dictionary table of the inspection system, if the department to which the personnel belongs is the project management center and the check-in record obtained from the smart engineering system contains the check-in information of the personnel, then they are judged to be in place; if they are not personnel of the project management center and the check-in record obtained from the smart safety and supervision system contains the check-in information of the personnel, then they are judged to be in place.

6. A device for supervising and identifying medium- and high-risk personnel, characterized in that: include: A data acquisition module is used to obtain the work plan and sign-in record sheet of the medium and high risk work to be identified; A data preprocessing module, used to associate the work plan sheet with the sign-in record sheet and merge the contents with the same attributes to obtain a merged data sheet; A hierarchical identification module, used to identify the text content of the data table using a pre-trained identification model to extract feature data from the text content, wherein the feature data is text data related to hierarchical information; A hierarchical matching module, used for processing the characteristic data to form characteristic text, and matching the characteristic text with a preset hierarchical rule library to determine the hierarchical information of the data table; An in-place identification module, used for matching the in-place identification rules of the medium- and high-risk operations to be identified based on the hierarchical information, and identifying the data table according to the in-place identification rules; The in-place identification rules correspond one-to-one to each professional category at each level, and the professional categories at least include: Substation categories, management unit categories, and professional categories of guarantee systems and supervision systems; The substation category's presence identification rule determines the presence of each level based on the job type and risk level attributes in the data table; The presence identification rule of the management unit category determines the presence of each level based on the risk level attribute or the operation subject and the risk level attribute in the data table; When the professional categories of the assurance system and the supervision system are biotechnology, scheduling and marketing, the corresponding in-place identification rules judge the in-place status of each level based on the system type, professional category and risk level attributes in the data table; When the professional category of the supervision system is infrastructure, the corresponding presence identification rule determines the presence of personnel based on the inspection system personnel dictionary table; The substation categories include key and important substations and non-key and important substations, and the corresponding in-place identification rules are as follows: The identification rule of the key and important substations in place is to query the key substations from the work location attribute of the data table, and the project management unit attribute does not contain the district bureau name, and the operation plan number attribute does not contain data starting with JJ. If the operation type is operation type, and the risk level is intermediate or advanced, and there are sign-in records at the team level or power supply station level, the second-level organization level, and the municipal level, it is judged to be in place; if the operation type is non-operational, and the risk level is intermediate, and there are sign-in records at the team level or power supply station level, and the second-level organization level, it is judged to be in place; if the operation type is non-operational, and the risk level is advanced, and there are sign-in records at the team level or power supply station level, the second-level organization level, and the municipal level, it is judged to be in place; The identification rule for the presence of non-critical important substations is to query the work location attribute of the data table and not include critical substations, and the project management unit attribute does not include the district bureau name, and the operation plan number attribute does not contain data starting with JJ; if the operation type is operation type, and the risk level is intermediate or advanced, and there are sign-in records at the team level or power supply station level, the second-level organization level, and the municipal level, then it is judged to be in place; if the operation type is non-operational, and the risk level is intermediate, and there are sign-in records at the team level or power supply station level, and the second-level organization level, then it is judged to be in place; if the operation type is non-operational, and the risk level is advanced, and there are sign-in records at the team level or power supply station level, the second-level organization level, and the municipal level, then it is judged to be in place.

7. A computer device, characterized in that: The device comprises a processor and a memory: The memory is used to store a computer program and send instructions of the computer program to the processor; The processor executes a method for inspecting and identifying medium- and high-risk personnel as described in any one of claims 1-5 according to the instructions of the computer program.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements a method for inspecting and identifying medium- and high-risk personnel as described in any one of claims 1-5.

Images