Job coloring method, device, equipment and storage medium for enterprise personnel

Abstract

The present invention relates to artificial intelligence technology, and discloses a method, device, equipment and storage medium for coloring the positions of enterprise personnel. The method comprises: obtaining enterprise entry information of enterprise personnel; when there are preset keywords in the enterprise entry information, coloring the names of enterprise personnel according to preconfigured position coloring rules and the positions corresponding to the keywords; when there are no preset keywords, using a pre-trained position prediction neural network model to perform position prediction classification on the enterprise entry information to obtain a position prediction result, and when the position prediction result is in the position coloring rule, coloring is performed, and when it is not in the position coloring rule, the enterprise entry information is imported into a pre-constructed artificial coloring database. The present invention can optimize data classification results and increase data classification flexibility by combining rule classification and neural network classification.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and computer-readable storage medium for coloring the positions of enterprise personnel. Background Art

[0002] With the development of the information age, the amount of enterprise data has expanded rapidly. However, most of the data is discrete. Only by classifying and summarizing can we better explore the value of the data.

[0003] The current classification process mostly classifies data through preset rules. If you want to adjust the classification results of the data, you can only adjust the set rules, which lacks flexibility and operability. Summary of the invention

[0004] The present invention provides a method, device, equipment and storage medium for coloring the positions of enterprise personnel, the main purpose of which is to optimize data classification results and increase data classification flexibility by combining rule classification and neural network classification.

[0005] To achieve the above purpose, the present invention provides a method for dyeing the job title of enterprise personnel, comprising:

[0006] Obtaining enterprise entry information of enterprise personnel in a pre-built enterprise database, and querying whether the enterprise entry information contains preset keywords according to a preset keyword set;

[0007] When the enterprise input information contains a preset keyword, the job title corresponding to the keyword is queried, and the name of the enterprise personnel is colored according to the pre-configured job coloring rule and the job title;

[0008] When the enterprise input information does not contain the preset keywords, the enterprise input information is segmented and quantized to obtain a segmentation vector set, and the pre-trained job prediction neural network model is used to perform job prediction classification on the segmentation vector set to obtain a job prediction result;

[0009] Determining whether the job prediction result matches the job coloring rule;

[0010] When the job prediction result matches the job coloring rule, the name of the enterprise personnel is colored according to the job coloring rule and the job prediction result;

[0011] When the job prediction result does not match the job coloring rule, the enterprise input information is sent to a pre-constructed manual coloring database.

[0012] Optionally, the using a pre-trained job prediction neural network model to perform job prediction classification on the word segmentation vector set to obtain a job prediction result includes:

[0013] Using the input layer network of the pre-trained job prediction neural network model, the word segmentation vector set is self-attentive weighted to obtain an attention-enhanced word segmentation vector set, and the attention-enhanced word segmentation vector set is filled and spliced ​​according to a preset format rule to obtain a text quantization matrix;

[0014] Using the feature extraction network of the job prediction neural network model to perform a convolution operation on the text quantization matrix to obtain a convolution matrix set;

[0015] Performing a maximum pooling operation on the convolution matrix set to obtain a pooling matrix set, and performing a flattening operation on the pooling matrix set to obtain a feature sequence set;

[0016] The fully connected layer network of the job prediction neural network model is used to perform job classification prediction on the feature sequence set to obtain a job prediction result.

[0017] Optionally, the enterprise input information is segmented and quantized to obtain a segmentation vector set, including:

[0018] Deleting punctuation marks and duplicate data from the enterprise input information to obtain standard text data;

[0019] Performing a word segmentation operation on the standard text data, and marking position information of the word segmentation results to obtain a word segmentation sequence;

[0020] A quantization encoding operation is performed on the word segmentation sequence to obtain a word segmentation vector set.

[0021] Optionally, before performing job prediction classification on the word segmentation vector set using the pre-trained job prediction neural network model, the method further includes:

[0022] Get pre-built entry-level job prediction neural network models and text sample sets;

[0023] Extracting a group of text samples from the text sample set in sequence, and performing network forward calculation on the text samples using the primary job prediction neural network model to obtain a predicted job category;

[0024] Using a multi-classification cross entropy loss function, calculate the loss value between the true label of the text sample and the predicted job category, and minimize the loss value to obtain the model parameters when the loss value is minimized;

[0025] Reversely updating the internal parameters in the primary job prediction neural network model using the model parameters to obtain an updated job prediction neural network model;

[0026] Determining the convergence of the loss value;

[0027] When the loss value has not converged, returning to the above step of sequentially extracting a group of text samples from the text sample set, and iteratively training the updated job prediction neural network model;

[0028] When the loss value converges, the finally trained updated job prediction neural network model is used as the trained job prediction neural network model.

[0029] Optionally, after sending the enterprise input information to a pre-built manual dyeing database, the method further includes:

[0030] When the positions of each enterprise personnel in the manual coloring database are marked and colored, or when the position prediction result is manually modified, a key-value pair including manual marking and enterprise input information is obtained;

[0031] The key-value pairs are filled into the text sample set to optimize the job prediction neural network model for training.

[0032] Optionally, before coloring the names of the enterprise personnel according to the preconfigured job coloring rules and the job titles, the method includes:

[0033] Obtain a pre-built job system table, configure a unique coloring identifier for each job in the job system table, and obtain a primary coloring rule;

[0034] The pre-built counter is used to limit the number of people in each position in the primary coloring rule to obtain the position coloring rule.

[0035] In order to solve the above problems, the present invention also provides a job dyeing device for enterprise personnel, the device comprising:

[0036] A rule entry classification module is used to obtain enterprise entry information of enterprise personnel in a pre-built enterprise database, and query whether the enterprise entry information contains preset keywords according to a preset keyword set, and when the enterprise entry information contains preset keywords, query the position corresponding to the keyword, and color the name of the enterprise personnel according to the pre-configured position coloring rule and the position;

[0037] A model prediction classification module is used to perform word segmentation and quantization encoding operations on the enterprise input information when the enterprise input information does not contain preset keywords to obtain a word segmentation vector set, and use a pre-trained job prediction neural network model to perform job prediction classification on the word segmentation vector set to obtain a job prediction result;

[0038] The position coloring module is used to determine whether the position prediction result matches the position coloring rule, and when the position prediction result matches the position coloring rule, the name of the enterprise personnel is colored according to the position coloring rule and the position prediction result, and when the position prediction result does not match the position coloring rule, the enterprise input information is sent to a pre-built manual coloring database.

[0039] Optionally, the using a pre-trained job prediction neural network model to perform job prediction classification on the word segmentation vector set to obtain a job prediction result includes:

[0040] Using the input layer network of the pre-trained job prediction neural network model, the word segmentation vector set is self-attentive weighted to obtain an attention-enhanced word segmentation vector set, and the attention-enhanced word segmentation vector set is filled and spliced ​​according to a preset format rule to obtain a text quantization matrix;

[0041] Using the feature extraction network of the job prediction neural network model to perform a convolution operation on the text quantization matrix to obtain a convolution matrix set;

[0042] Performing a maximum pooling operation on the convolution matrix set to obtain a pooling matrix set, and performing a flattening operation on the pooling matrix set to obtain a feature sequence set;

[0043] The fully connected layer network of the job prediction neural network model is used to perform job classification prediction on the feature sequence set to obtain a job prediction result.

[0044] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0045] at least one processor; and,

[0046] a memory communicatively connected to the at least one processor; wherein,

[0047] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned method of job coloring of enterprise personnel.

[0048] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one computer program is stored. The at least one computer program is executed by a processor in an electronic device to implement the above-mentioned method for coloring the positions of enterprise personnel.

[0049] The embodiment of the present invention first classifies enterprise personnel by keyword query, and then uses the position prediction neural network model to intelligently identify the enterprise input information of unclassified enterprise personnel, predict the possible positions of enterprise personnel, obtain position prediction results, and perform coloring classification according to the position prediction results, wherein the position prediction neural network model is a multi-classification neural network based on text recognition, which can increase recognition accuracy and recognition efficiency. In addition, it can also record manually adjusted classification data for timed optimization of the position prediction neural network model, and gradually optimize the classification results of data. Therefore, the embodiment of the present invention provides a method, device, equipment and storage medium for coloring the positions of enterprise personnel, which can optimize data classification results and increase the flexibility of data classification by combining rule classification and neural network classification. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic flow chart of a method for coloring the positions of enterprise personnel provided by one embodiment of the present invention;

[0051] Figure 2 A detailed flow chart of a step in a method for coloring the job of enterprise personnel provided by an embodiment of the present invention;

[0052] Figure 3 A detailed flow chart of a step in a method for coloring the job of enterprise personnel provided by an embodiment of the present invention;

[0053] Figure 4 A detailed flow chart of a step in a method for coloring the job of enterprise personnel provided by an embodiment of the present invention;

[0054] Figure 5 A functional module diagram of a job coloring device for enterprise personnel provided by an embodiment of the present invention;

[0055] Figure 6 A schematic diagram of the structure of an electronic device for implementing the method for coloring the positions of enterprise personnel provided in one embodiment of the present invention.

[0056] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0057] 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.

[0058] The embodiment of the present application provides a method for coloring the positions of enterprise personnel. In the embodiment of the present application, the execution subject of the method for coloring the positions of enterprise personnel includes but is not limited to at least one of the electronic devices such as the server and the terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for coloring the positions of enterprise personnel can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0059] Reference Figure 1 FIG. 1 is a flow chart of a method for coloring the positions of enterprise personnel provided by an embodiment of the present invention. In this embodiment, the method for coloring the positions of enterprise personnel includes:

[0060] S1. Obtain enterprise entry information of enterprise personnel in a pre-built enterprise database, and query whether the enterprise entry information contains preset keywords according to a preset keyword set.

[0061] In the embodiment of the present invention, the enterprise input information includes identity information, business record information, position information, etc. of the enterprise personnel.

[0062] Furthermore, in the embodiment of the present invention, the keyword set includes but is not limited to the finance department, sales department, administration department, product department and company board members, etc.

[0063] Specifically, the embodiment of the present invention uses a database query engine to query the enterprise input information according to the keyword set to obtain a result of whether the enterprise input information contains the keyword.

[0064] When the enterprise input information contains preset keywords, S2, the positions corresponding to the keywords are queried, and the names of the enterprise personnel are colored according to the pre-configured position coloring rules and the positions.

[0065] Among them, the job coloring rules are coloring rules that are adaptively configured by the enterprise based on color psychology and the number of people in each occupation in the enterprise.

[0066] For more details, please refer to Figure 2As shown, in the embodiment of the present invention, before coloring the names of the enterprise personnel according to the preconfigured job coloring rules and the job, the method includes:

[0067] S21, obtaining a pre-built job system table, configuring a unique coloring identifier for each job in the job system table, and obtaining a primary coloring rule;

[0068] S22. Using a pre-built counter, limit the number of people in each position in the primary coloring rule to obtain a position coloring rule.

[0069] According to the above operation process in the embodiment of the present invention, it is obtained that: blue (B) corresponds to the company's board members, shareholders, COO and other senior management; black (M) corresponds to the company's core managers (a company can only have one); dark gray (F) corresponds to the finance department; pink (S) corresponds to the sales department; cyan (C) corresponds to the administrative department; blue (R) corresponds to the product department; dark red (H) corresponds to the human resources department; orange (T) corresponds to the company's IT R&D department; yellow (E) corresponds to other departments of the company that are not related to communication technology; aqua blue (Q) corresponds to the procurement department; light red (A) corresponds to the service department; white (N) corresponds to contacts without positions; light red (X) corresponds to the customer service department; brown (U) corresponds to the public relations department.

[0070] When the enterprise input information contains preset keywords, it indicates that the identity and position information of the enterprise personnel has been defined, and the information can be directly classified and colored according to the pre-configured position coloring rules.

[0071] When the enterprise input information does not contain preset keywords, S3, the enterprise input information is segmented and quantized to obtain a set of segmentation vectors, and the pre-trained job prediction neural network model is used to perform job prediction classification on the segmentation vector set to obtain a job prediction result.

[0072] Among them, the job prediction neural network model is a multi-classification neural network model based on text recognition, which includes an input layer network, a feature extraction network and a fully connected layer network. The input layer network contains an attention configuration mechanism for obtaining a word segmentation feature vector containing contextual features; the feature extraction network contains a convolutional layer, a pooling layer and a flatten layer for extracting and reducing features; the fully connected layer is used for feature recognition and multi-classification operations.

[0073] For more details, please refer to Figure 3 As shown, in the embodiment of the present invention, the enterprise input information is segmented and quantized to obtain a segmentation vector set, including:

[0074] S301, deleting punctuation marks and duplicate data from the enterprise input information to obtain standard text data;

[0075] S302, performing a word segmentation operation on the standard text data, and marking position information of the word segmentation results to obtain a word segmentation sequence;

[0076] S303: Perform a quantization encoding operation on the word segmentation sequence to obtain a word segmentation vector set.

[0077] The embodiment of the present invention makes the text data neater by deleting punctuation marks and repeated data, thereby increasing recognition accuracy and efficiency, and then performs word segmentation operations through tools such as the Jieba word segmentation tool or the Chinese word segmentation system. In order to subsequently increase the attention weight, the embodiment of the present invention adds position information to each word segmentation result, so that the word segmentation quantification result has a contextual relationship.

[0078] For further reference, Figure 4 As shown, in the embodiment of the present invention, the pre-trained job prediction neural network model is used to perform job prediction classification on the word segmentation vector set to obtain a job prediction result, including:

[0079] S311, using the input layer network of the pre-trained job prediction neural network model to perform self-attention weight configuration on the word segmentation vector set to obtain an attention-enhanced word segmentation vector set, and according to a preset format rule, performing filling and splicing operations on the attention-enhanced word segmentation vector set to obtain a text quantization matrix;

[0080] S312, using the feature extraction network of the job prediction neural network model to perform a convolution operation on the text quantization matrix to obtain a convolution matrix set;

[0081] S313, performing a maximum pooling operation on the convolution matrix set to obtain a pooling matrix set, and performing a flattening operation on the pooling matrix set to obtain a feature sequence set;

[0082] S314. Use the fully connected layer network of the job prediction neural network model to perform job classification prediction on the feature sequence set to obtain a job prediction result.

[0083] In an embodiment of the present invention, each word segmentation vector set is set to x, then x1, x2..., xn are obtained, where n is the number of word segments. Then, through the attention mechanism, the word segmentation vector set is configured with three random weights, so that each word segmentation vector becomes three vectors, for example, x1 becomes q1, k1, v1, x2 becomes q2, k2, v2..., and the q set, k set, and v set are obtained. In order to obtain the relationship between the contexts, a vector in the q set is inner-producted with each vector in the k set in turn to obtain a vector-associated numerical set, and then the vector-associated numerical set is normalized using the softmax function to obtain an attention weight set a1, a2...an, and finally, each v vector in the v set and each attention weight in the attention weight set are weighted according to the corresponding relationship between each word segmentation to obtain an attention-enhanced word segmentation vector set. Then, the attention-enhanced word segmentation vectors of each word segmentation are made the same character length through a padding operation, and then the character lengths are spliced ​​to obtain a text quantization matrix.

[0084] Then, the text quantization matrix is ​​subjected to feature extraction through convolutional pooling operations to obtain a feature sequence set, and each feature sequence is spliced ​​through a fully connected layer, and the job classification type of each spliced ​​feature is calculated to obtain a job prediction result.

[0085] Furthermore, in an embodiment of the present invention, before using the pre-trained job prediction neural network model to perform job prediction classification on the word segmentation vector set, the method further includes:

[0086] Get pre-built entry-level job prediction neural network models and text sample sets;

[0087] Extracting a group of text samples from the text sample set in sequence, and performing network forward calculation on the text samples using the primary job prediction neural network model to obtain a predicted job category;

[0088] Using a multi-classification cross entropy loss function, calculate the loss value between the true label of the text sample and the predicted job category, and minimize the loss value to obtain the model parameters when the loss value is minimized;

[0089] Reversely updating the internal parameters in the primary job prediction neural network model using the model parameters to obtain an updated job prediction neural network model;

[0090] Determining the convergence of the loss value;

[0091] When the loss value has not converged, returning to the above step of sequentially extracting a group of text samples from the text sample set, and iteratively training the updated job prediction neural network model;

[0092] When the loss value converges, the finally trained updated job prediction neural network model is used as the trained job prediction neural network model.

[0093] The embodiment of the present invention controls the training process of the model through the multi-classification cross entropy loss function and the gradient descent method. To avoid overfitting of the model, the embodiment of the present invention monitors the convergence of the loss value by recording the loss value. When the loss value of the model converges, indicating that the accuracy of the model tends to be stable, the training process can be stopped to obtain a trained job prediction neural network model.

[0094] S4, judging whether the job prediction result matches the job coloring rule;

[0095] When the job prediction result matches the job coloring rule, S5, coloring the name of the enterprise personnel according to the job coloring rule and the job prediction result;

[0096] When the job prediction result does not match the job coloring rule, S6, sending the enterprise input information to the pre-built artificial coloring database

[0097] When the job prediction result is within the job coloring rules, coloring can be performed. However, in the specific implementation process, there may be special reasons such as incomplete information or job changes, which may cause the model to fail to recognize or make model recognition errors, requiring manual intervention.

[0098] In detail, in an embodiment of the present invention, after sending the enterprise input information to a pre-built manual dyeing database, the method further includes:

[0099] When the positions of each enterprise personnel in the manual coloring database are marked and colored, or when the position prediction result is manually modified, a key-value pair including manual marking and enterprise input information is obtained;

[0100] The key-value pairs are filled into the text sample set to optimize the job prediction neural network model for training.

[0101] In the embodiment of the present invention, the database will record the classification data manually adjusted by the user for model training, regularly optimize the classification model of the job prediction neural network model, and then optimize the data classification results.

[0102] The embodiment of the present invention first classifies enterprise personnel by keyword query, and then uses the position prediction neural network model to intelligently identify the enterprise input information of unclassified enterprise personnel, predict the possible positions of enterprise personnel, obtain the position prediction results, and perform coloring classification according to the position prediction results, wherein the position prediction neural network model is a multi-classification neural network based on text recognition, which can increase the recognition accuracy and recognition efficiency. In addition, the manually adjusted classification data can also be recorded for the timed optimization of the position prediction neural network model, and the classification results of the data can be gradually optimized. Therefore, a method for coloring the positions of enterprise personnel provided by the embodiment of the present invention can optimize the data classification results and increase the flexibility of data classification by combining rule classification and neural network classification.

[0103] like Figure 5 1 is a functional module diagram of a job dyeing device for enterprise personnel provided by an embodiment of the present invention.

[0104] The enterprise personnel position coloring device 100 of the present invention can be installed in an electronic device. According to the functions to be implemented, the enterprise personnel position coloring device 100 can include a rule entry classification module 101, a model prediction classification module 102 and a position coloring module 103. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0105] In this embodiment, the functions of each module / unit are as follows:

[0106] The rule entry classification module 101 is used to obtain enterprise entry information of enterprise personnel in a pre-built enterprise database, and query whether the enterprise entry information contains preset keywords according to a preset keyword set, and when the enterprise entry information contains preset keywords, query the position corresponding to the keyword, and color the name of the enterprise personnel according to the pre-configured position coloring rule and the position;

[0107] The model prediction classification module 102 is used to perform word segmentation and quantization encoding operations on the enterprise input information to obtain a word segmentation vector set when the enterprise input information does not contain a preset keyword, and use a pre-trained job prediction neural network model to perform job prediction classification on the word segmentation vector set to obtain a job prediction result;

[0108] The position coloring module 103 is used to determine whether the position prediction result matches the position coloring rule, and when the position prediction result matches the position coloring rule, the name of the enterprise personnel is colored according to the position coloring rule and the position prediction result, and when the position prediction result does not match the position coloring rule, the enterprise input information is sent to a pre-built manual coloring database.

[0109] In detail, each module described in the job dyeing device 100 for enterprise personnel described in the embodiment of the present application is used in the same manner as described above. Figures 1 to 4 The same technical means are used as the job dyeing method for enterprise personnel described in the text, and can produce the same technical effects, so I will not go into details here.

[0110] like Figure 6 , which is a schematic diagram of the structure of an electronic device 1 for implementing a method for coloring the positions of enterprise personnel provided by an embodiment of the present invention.

[0111] The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a job coloring program for corporate personnel.

[0112] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is the control core (ControlUnit) of the electronic device 1, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (for example, executing the job coloring program of enterprise personnel, etc.), and calls the data stored in the memory 11 to execute various functions of the electronic device and process data.

[0113] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. The memory 11 may be an internal storage unit of an electronic device in some embodiments, such as a mobile hard disk of the electronic device. The memory 11 may also be an external storage device of an electronic device in other embodiments, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 11 may also include both an internal storage unit of the electronic device and an external storage device. The memory 11 may not only be used to store application software and various types of data installed in the electronic device, such as the code of the job coloring program of enterprise personnel, but also be used to temporarily store data that has been output or is to be output.

[0114] The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0115] The communication interface 13 is used for communication between the above-mentioned electronic device 1 and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0116] Figure 6 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 6The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0117] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0118] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0119] The job coloring program for enterprise personnel stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, the following can be achieved:

[0120] Obtaining enterprise entry information of enterprise personnel in a pre-built enterprise database, and querying whether the enterprise entry information contains preset keywords according to a preset keyword set;

[0121] When the enterprise input information contains a preset keyword, the job title corresponding to the keyword is queried, and the name of the enterprise personnel is colored according to the pre-configured job coloring rule and the job title;

[0122] When the enterprise input information does not contain the preset keywords, the enterprise input information is segmented and quantized to obtain a segmentation vector set, and the pre-trained job prediction neural network model is used to perform job prediction classification on the segmentation vector set to obtain a job prediction result;

[0123] Determining whether the job prediction result matches the job coloring rule;

[0124] When the job prediction result matches the job coloring rule, the name of the enterprise personnel is colored according to the job coloring rule and the job prediction result;

[0125] When the job prediction result does not match the job coloring rule, the enterprise input information is sent to a pre-constructed manual coloring database.

[0126] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0127] Furthermore, if the module / unit integrated in the electronic device 1 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. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0128] 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 of an electronic device, the computer program can implement:

[0129] Obtaining enterprise entry information of enterprise personnel in a pre-built enterprise database, and querying whether the enterprise entry information contains pre-set keywords according to a pre-set keyword set;

[0130] When the enterprise input information contains a preset keyword, the job title corresponding to the keyword is queried, and the name of the enterprise personnel is colored according to the pre-configured job coloring rule and the job title;

[0131] When the enterprise input information does not contain the preset keywords, the enterprise input information is segmented and quantized to obtain a segmentation vector set, and the pre-trained job prediction neural network model is used to perform job prediction classification on the segmentation vector set to obtain a job prediction result;

[0132] Determining whether the job prediction result matches the job coloring rule;

[0133] When the job prediction result matches the job coloring rule, the name of the enterprise personnel is colored according to the job coloring rule and the job prediction result;

[0134] When the job prediction result does not match the job coloring rule, the enterprise input information is sent to a pre-constructed manual coloring database.

[0135] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0136] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0137] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0138] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0139] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0140] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0141] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0142] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for job dyeing of enterprise personnel, characterized in that: The method comprises: Obtaining enterprise entry information of enterprise personnel in a pre-built enterprise database, and querying whether the enterprise entry information contains preset keywords according to a preset keyword set; When the enterprise input information contains a preset keyword, the position corresponding to the keyword is queried, and the name of the enterprise personnel is colored according to the pre-configured position coloring rule and the position; When the enterprise input information does not contain the preset keywords, the enterprise input information is segmented and quantized to obtain a segmentation vector set, and the pre-trained job prediction neural network model is used to perform job prediction classification on the segmentation vector set to obtain a job prediction result; Determining whether the job prediction result matches the job coloring rule; When the job prediction result matches the job coloring rule, the name of the enterprise personnel is colored according to the job coloring rule and the job prediction result; When the job prediction result does not match the job coloring rule, the enterprise input information is sent to a pre-constructed manual coloring database.

2. The job dyeing method for enterprise personnel according to claim 1, characterized in that: The pre-trained job prediction neural network model is used to perform job prediction classification on the word segmentation vector set to obtain a job prediction result, including: Using the input layer network of the pre-trained job prediction neural network model, the word segmentation vector set is self-attentive weighted to obtain an attention-enhanced word segmentation vector set, and the attention-enhanced word segmentation vector set is filled and spliced ​​according to a preset format rule to obtain a text quantization matrix; Using the feature extraction network of the job prediction neural network model to perform a convolution operation on the text quantization matrix to obtain a convolution matrix set; Performing a maximum pooling operation on the convolution matrix set to obtain a pooling matrix set, and performing a flattening operation on the pooling matrix set to obtain a feature sequence set; The fully connected layer network of the job prediction neural network model is used to perform job classification prediction on the feature sequence set to obtain a job prediction result.

3. The job dyeing method for enterprise personnel according to claim 1, characterized in that: The enterprise input information is segmented and quantized to obtain a segmentation vector set, including: Deleting punctuation marks and duplicate data from the enterprise input information to obtain standard text data; Performing a word segmentation operation on the standard text data, and marking position information of the word segmentation results to obtain a word segmentation sequence; A quantization encoding operation is performed on the word segmentation sequence to obtain a word segmentation vector set.

4. The job dyeing method for enterprise personnel according to claim 1, characterized in that: Before using the pre-trained job prediction neural network model to perform job prediction classification on the word segmentation vector set, the method further includes: Get pre-built entry-level job prediction neural network models and text sample sets; Extracting a group of text samples from the text sample set in sequence, and performing network forward calculation on the text samples using the primary job prediction neural network model to obtain a predicted job category; Using a multi-classification cross entropy loss function, the loss value between the true label of the text sample and the predicted job category is calculated, and the loss value is minimized to obtain the model parameters when the loss value is minimized; Reversely updating the internal parameters in the primary job prediction neural network model using the model parameters to obtain an updated job prediction neural network model; Determining the convergence of the loss value; When the loss value has not converged, returning to the above step of sequentially extracting a group of text samples from the text sample set, and iteratively training the updated job prediction neural network model; When the loss value converges, the finally trained updated job prediction neural network model is used as the trained job prediction neural network model.

5. The job dyeing method for enterprise personnel according to claim 4, characterized in that: After sending the enterprise input information to the pre-built manual dyeing database, the method further includes: When the positions of each enterprise personnel in the manual coloring database are marked and colored, or when the position prediction result is manually modified, a key-value pair including manual marking and enterprise input information is obtained; The key-value pairs are filled into the text sample set to optimize the job prediction neural network model for training.

6. The job dyeing method for enterprise personnel according to claim 1, characterized in that: Before coloring the names of the enterprise personnel according to the preconfigured job coloring rules and the job, the method includes: Obtain a pre-built job system table, configure a unique coloring identifier for each job in the job system table, and obtain a primary coloring rule; The pre-built counter is used to limit the number of people in each position in the primary coloring rule to obtain the position coloring rule.

7. A job dyeing device for enterprise personnel, characterized in that: The device comprises: A rule entry classification module is used to obtain enterprise entry information of enterprise personnel in a pre-built enterprise database, and query whether the enterprise entry information contains preset keywords according to a preset keyword set, and when the enterprise entry information contains preset keywords, query the position corresponding to the keyword, and color the name of the enterprise personnel according to the pre-configured position coloring rule and the position; A model prediction classification module is used to perform word segmentation and quantization encoding operations on the enterprise input information when the enterprise input information does not contain preset keywords to obtain a word segmentation vector set, and use a pre-trained job prediction neural network model to perform job prediction classification on the word segmentation vector set to obtain a job prediction result; The position coloring module is used to determine whether the position prediction result matches the position coloring rule, and when the position prediction result matches the position coloring rule, the name of the enterprise personnel is colored according to the position coloring rule and the position prediction result, and when the position prediction result does not match the position coloring rule, the enterprise input information is sent to a pre-built manual coloring database.

8. The job dyeing device for enterprise personnel as claimed in claim 7, characterized in that: The pre-trained job prediction neural network model is used to perform job prediction classification on the word segmentation vector set to obtain a job prediction result, including: Using the input layer network of the pre-trained job prediction neural network model, the word segmentation vector set is self-attentive weighted to obtain an attention-enhanced word segmentation vector set, and the attention-enhanced word segmentation vector set is filled and spliced ​​according to a preset format rule to obtain a text quantization matrix; Using the feature extraction network of the job prediction neural network model to perform a convolution operation on the text quantization matrix to obtain a convolution matrix set; Performing a maximum pooling operation on the convolution matrix set to obtain a pooling matrix set, and performing a flattening operation on the pooling matrix set to obtain a feature sequence set; The fully connected layer network of the job prediction neural network model is used to perform job classification prediction on the feature sequence set to obtain a job prediction result.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the job dyeing method for enterprise personnel as described in any one of claims 1 to 6.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for coloring the positions of enterprise personnel as described in any one of claims 1 to 6 is implemented.

Images