A method for evaluating enterprise digitalization level and related equipment

Abstract

The present invention provides an evaluation method and related equipment for the digital level of an enterprise, which are applied to the field of data processing technology. The application processes target enterprise information to generate digital index information of the target enterprise; obtains an initial enterprise evaluation model matching the digital index information of the target enterprise and a training data set matching the initial enterprise evaluation model; processes the initial enterprise evaluation model based on the training data set to generate a target enterprise evaluation model; processes the digital index information of the target enterprise and the industry information of the target enterprise based on the target enterprise evaluation model to generate an initial digital value of the target enterprise; processes the target event information matching the target enterprise information and the funding information of the target enterprise to generate a digital adjustment factor; processes the initial digital value and the digital adjustment factor of the target enterprise based on the target enterprise evaluation model to generate the digital level information of the target enterprise.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an evaluation method for enterprise digitalization level and related equipment. Background Art

[0002] The growth potential of an enterprise is based on the subjectivity of the enterprise, and is determined by corporate culture, innovation capability, core technology, industry positioning, operation model, management level, team spirit, business capability and industrial upgrading capability. It is the comprehensive productivity of the enterprise. At present, in terms of the evaluation of the digital level of enterprises, the existing methods often have the following shortcomings: the collection of enterprise information is not comprehensive enough, and may only focus on some aspects, such as a single dimension such as equipment system or data resources, which cannot comprehensively reflect the overall digital level of the enterprise. In the construction of the evaluation model, there is a lack of in-depth processing and feature extraction of the training data set, which makes it difficult to accurately capture the risk factors that affect the digitalization of the enterprise, resulting in limited accuracy and reliability of the evaluation model. Insufficient consideration of target event information and enterprise funding information cannot fully reflect the dynamic impact of external events and funding conditions on the digital level of the enterprise, making the evaluation results not flexible and close to the actual situation.

[0003] Existing evaluation methods usually cannot systematically generate comprehensive evaluation factors, digital scores and digital level information, and it is difficult to provide comprehensive, quantitative and hierarchical evaluation results, which is not conducive to enterprises accurately understanding their own digitalization level and formulating targeted development strategies.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of this application is to provide an evaluation method and related equipment for the digital level of an enterprise, which at least overcomes the problems existing in the prior art to a certain extent, by obtaining various types of information of the target enterprise, subdividing the enterprise information, generating different indicator information from the equipment list, production and sales data, employee data and network communication information, and then comprehensively obtaining digital indicator information. Then, the training data set is extracted, and the training set and the validation set are divided. After classifier prediction and preset algorithm training, the target feature data is obtained by comparing the results to construct a target enterprise evaluation model. Then, the model processes the industry information and digital indicator information to generate an initial digital value, and processes the target event and capital information to obtain a digital adjustment factor. Finally, the model processes the initial digital value and the adjustment factor to generate a comprehensive evaluation factor, and further obtains the digital score, thereby determining the digital level information. This method fully considers various factors of the enterprise and provides a systematic and accurate approach and tool for the digital level evaluation of the enterprise.

[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present invention.

[0007] According to one aspect of the present application, a method for evaluating the digitalization level of an enterprise is provided, including: obtaining target enterprise information, target event information matching the target enterprise information, industry information of the target enterprise, and funding information of the target enterprise; processing the target enterprise information to generate digitalization index information of the target enterprise; obtaining an initial enterprise evaluation model matching the digitalization index information of the target enterprise and a training data set matching the initial enterprise evaluation model; processing the initial enterprise evaluation model based on the training data set to generate a target enterprise evaluation model; processing the digitalization index information of the target enterprise and the industry information of the target enterprise based on the target enterprise evaluation model to generate an initial digitalization value of the target enterprise; processing the target event information matching the target enterprise information and the funding information of the target enterprise to generate a digitalization adjustment factor; processing the initial digitalization value of the target enterprise and the digitalization adjustment factor based on the target enterprise evaluation model to generate digitalization level information of the target enterprise.

[0008] Another aspect of the present application is an evaluation device for the digitalization level of an enterprise, characterized in that it includes: an acquisition module, used to acquire target enterprise information, target event information matching the target enterprise information, industry information of the target enterprise and funding information of the target enterprise; acquire an initial enterprise evaluation model matching the digitalization indicator information of the target enterprise and a training data set matching the initial enterprise evaluation model; a processing module, used to process the target enterprise information to generate the digitalization indicator information of the target enterprise; process the initial enterprise evaluation model based on the training data set to generate the target enterprise evaluation model; process the digitalization indicator information of the target enterprise and the industry information of the target enterprise based on the target enterprise evaluation model to generate an initial digitalization value of the target enterprise; process the target event information matching the target enterprise information and the funding information of the target enterprise to generate a digitalization adjustment factor; process the initial digitalization value of the target enterprise and the digitalization adjustment factor based on the target enterprise evaluation model to generate the digitalization level information of the target enterprise.

[0009] According to another aspect of the present application, an electronic device is characterized in that it includes: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the above-mentioned enterprise digitalization level evaluation method by executing the executable instructions.

[0010] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a second processor, the method for evaluating the enterprise digitization level is implemented.

[0011] According to another aspect of the present application, a computer program product is provided, including a computer program, characterized in that when the computer program is executed by a third processor, the computer program implements the above-mentioned enterprise digitalization level evaluation method.

[0012] The present application provides an evaluation method and related equipment for the digital level of an enterprise. The server obtains various types of information of the target enterprise, performs segmented processing on the enterprise information, generates different indicator information from the equipment list, production and sales data, employee data and network communication information, and then obtains the digital indicator information in a comprehensive manner. Then, the training data set is extracted, and the training set and the validation set are divided. After the classifier is predicted and the preset algorithm is trained, the target feature data is obtained by comparing the results to construct the target enterprise evaluation model. Then, the model processes the industry information and the digital indicator information to generate the initial digital value, and processes the target event and capital information to obtain the digital adjustment factor. Finally, the model processes the initial digital value and the adjustment factor to generate a comprehensive evaluation factor, and further obtains the digital score to determine the digital level information. This method fully considers various factors of the enterprise and provides a systematic and accurate approach and tool for the digital level evaluation of the enterprise.

[0013] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A flow chart showing a method for evaluating the digitalization level of an enterprise provided by an embodiment of the present application;

[0015] Figure 2 A schematic diagram of the structure of an enterprise digitalization level evaluation device provided by an embodiment of the present application is shown;

[0016] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application is shown;

[0017] Figure 4 A schematic diagram of a storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0018] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0019] Combine the following Figure 1 To describe the evaluation method of the enterprise digital level according to the exemplary embodiment of the present application. It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present application, and the embodiments of the present application are not limited in this regard. On the contrary, the embodiments of the present application can be applied to any applicable scenario.

[0020] In one implementation, the present application also proposes a method for evaluating the digitalization level of an enterprise and related equipment. Figure 1 The following schematically shows a flow chart of a method for evaluating the digitalization level of an enterprise according to an embodiment of the present application. Figure 1 As shown, the method is applied to a server, comprising:

[0021] S101, obtaining target enterprise information, target event information matching the target enterprise information, industry information of the target enterprise, and funding information of the target enterprise.

[0022] In one implementation, the target enterprise information includes the following: Enterprise name: XX Manufacturing Co., Ltd. Enterprise scale: 500 employees, annual turnover of 150 million yuan, organizational structure: production department, R&D department, sales department, finance department, human resources department and other departments, of which the R&D department has 50 professional R&D personnel, accounting for 10% of the total number of employees. Years of operation: Founded in 2005, it has been operating in the industry for 18 years.

[0023] Details of the current status of enterprise digitalization are as follows: Equipment system: 30 automated production equipment, 20 of which are connected to the Internet and can be remotely monitored. The average version of equipment automation software is 3.5, and 60% of the equipment can achieve automatic adjustment of production parameters. Data resources: The internal data storage capacity reaches 5TB, and the data types include production data (such as output, quality parameters, equipment operation data), sales data (customer orders, sales, customer geographical distribution), financial data (cost, profit, balance sheet data), etc. Professional data analysis software is used for data mining and visualization analysis, and 5 data analysis reports are generated every month. Network security: Enterprise-level firewalls are installed, intrusion detection and prevention systems are equipped, network security training is conducted regularly, and the coverage rate of employee network security training reaches 90%. The number of cyber attacks in the past year is 3, and none of them caused major data leakage or business interruption. R&D design: CAD / CAM software is used for product design and manufacturing process planning, and the digital storage rate of design drawings reaches 100%. The average new product R&D cycle is 6 months, which is 1 month shorter than last year. Production control: The production management system is used for production planning and scheduling, with an accuracy rate of 95%. 50 sensors are installed on the production line for real-time quality inspection and production progress monitoring, and the product qualification rate is 98%. Procurement and supply: Raw materials are purchased through the electronic procurement platform, and digital partnerships have been established with 50 suppliers. Supplier inventory information can be obtained in real time, and the electronic processing rate of purchase orders reaches 90%. Marketing management: It has an official corporate website and mobile application, a total of 100,000 social media fans, 10 online marketing activities are carried out each year, and customer information is managed through the customer relationship management system, with a completeness rate of 80%. Product service: It provides an online after-sales service platform, through which customers can submit product after-sales problems. The average time for solving after-sales problems is 24 hours. The product is equipped with a digital user manual and remote fault diagnosis function.

[0024] Target event information: The company developed a new manufacturing process this year, using artificial intelligence algorithms to optimize the production process and improve production efficiency by 30%. The technology has been patented and is being gradually applied to the production line. It is expected to cover 80% of production tasks in the next year. From the perspective of technological advancement, the process is at the leading level in the industry, which can significantly reduce production costs and improve product quality. It has greatly improved the production links in the digital transformation of the company and is expected to bring an additional annual profit of 5 million yuan. The competitor launched a similar product, which is 10% lower than the company's product. The company has stabilized its market share by optimizing its marketing strategy, increasing its online marketing investment, carrying out a series of promotional activities, and signing long-term cooperation agreements with some customers. The market share has only dropped by 3%. Although facing competitive pressure, the company has effectively responded through digital marketing means and customer relationship management strategies. The brand awareness remains in the top 30% in the industry, and the customer satisfaction survey results show that it has increased by 5 percentage points compared with last year. The company has reached a strategic cooperation with a well-known technology company to jointly develop a smart product. The two parties will share technical resources and R&D results. The technology company will provide advanced artificial intelligence algorithms and big data analysis technology, and the company will be responsible for product manufacturing and marketing. The cooperation will enhance the company's R&D capabilities and market competitiveness in the field of smart products. It is expected that the new products will occupy 10% of the market share within one year after their launch, bringing the company an additional annual revenue of 30 million yuan and promoting the in-depth application of the company's digital technology in its products.

[0025] The enterprise belongs to the machinery manufacturing industry. The main characteristics of this industry include: capital intensive, high equipment acquisition and update costs. High technical content, and increasing requirements for the digitalization of R&D design and production processes. The supply chain is complex, involving many parts suppliers and sales channels. The product production cycle is long, and it generally takes 3-6 months from design to finished product delivery. The industry is highly competitive, and enterprises need to continuously improve product quality and production efficiency and reduce costs through digital innovation to gain competitive advantages. For example, the equipment automation rate of advanced enterprises in the industry generally reaches more than 80%, the utilization rate of data resources is high, and accurate production and marketing decisions can be made through data analysis.

[0026] The total investment in digital projects in the past three years was 20 million yuan, of which 10 million yuan was invested in equipment digital transformation, 5 million yuan was invested in software development and purchase, 3 million yuan was invested in personnel digital training, and 2 million yuan was invested in other digital-related investments (such as network security construction, etc.). This year, the company plans to invest 8 million yuan in digitalization, mainly for the development of smart products and the upgrade of production management systems. Own funds account for 60% of the investment in digital projects, bank loans account for 30%, and the remaining 10% is government subsidies and equity financing. Own funds mainly come from the company's profit accumulation over the years. The bank loan period is 3 years and the annual interest rate is 5%. In the past, the input-output ratio of digital projects was 1:3, that is, every 1 yuan of digital funds invested can bring 3 yuan of new income or cost savings. For example, by upgrading the production management system, 5 million yuan of production costs can be saved each year; through digital marketing promotion, 10 million yuan of new sales can be added.

[0027] S102: Process the target enterprise information to generate digital indicator information of the target enterprise.

[0028] In one implementation, the target enterprise information is processed to generate the target enterprise's equipment list information, production data information, sales data information, employee data information, and network communication information. Assume that the target enterprise is an electronic manufacturing enterprise. Extract the equipment list from the enterprise's asset management system, including the equipment name, model, purchase time, supplier, and other information. For example, there are 50 main production equipment, including SMT placement machine (model: XX-1000, purchased in 2018, supplier: ABC Company), wave soldering machine (model: YY-200, purchased in 2016, supplier: DEF Company), and automatic testing equipment (model: ZZ-500, purchased in 2020, supplier: GHI Company). Obtain production data from the production management system, such as daily production records, the total output in the past month is 100,000 products; production yield data, the average yield is 95%; the capacity utilization of different production lines, production line A utilization is 80%, production line B utilization is 75%, etc. It also includes raw material consumption data, such as 500,000 electronic components of model X and 300,000 electronic components of model Y consumed per month. Sales data is obtained from the customer relationship management system (CRM) and sales database. Including sales of 120 million yuan in the past year, the types and quantity distribution of sales products, such as 500,000 smartphone motherboards and 300,000 computer motherboards; customer geographical distribution, of which customers in East China account for 40% and customers in South China account for 30%; sales channel data, online e-commerce platform sales account for 30%, offline dealer sales account for 70%, etc.

[0029] Employee data is extracted from the human resources management system, such as the total number of employees is 800, including 150 R&D personnel, 400 production personnel, 150 sales personnel, and 100 management personnel. Employee education distribution, 30% of them have a bachelor's degree or above, and 40% have a college degree. Employee training records, 300 employees participated in digital skills training in the past year, and the total training time was 6,000 hours. Check the enterprise network architecture, including the network topology diagram, and find that the company adopts a star network structure, the core switch is XX brand, and the bandwidth is 10Gbps. Network security equipment information, including firewalls (brand: YY, model: ZZ, rule base update date is October 2024), intrusion detection system (IDS), etc. Network usage, such as monthly network traffic peak of 10TB, average network latency of 10ms, etc.

[0030] The target enterprise's equipment list information is processed to generate the target equipment's index information, where the target equipment's index is used to characterize whether the target equipment has digital control functions. For SMT placement machines (XX-1000 model): With digital control functions, the placement speed, accuracy and other parameters can be set through computer software, and it can be connected to the production management system to upload equipment operation status data in real time, such as equipment startup time, operating time, fault alarm information, etc. Its digital control function index score is 9 (out of 10 points, based on functional completeness and advancement). Wave soldering machine (YY-200 model): Partial digital control function, can set basic parameters such as welding temperature and speed, but cannot be connected to other systems, and the digital control function index score is 5. Automated testing equipment (ZZ-500 model): With highly digital control functions, it can automatically identify product defect types and classify and count them, can remotely monitor and adjust detection parameters, and integrate with the quality control system. The digital control function index score is 10.

[0031] Process production data and sales data to generate production control indicator information. By comparing the planned production output with the actual output, the production plan accuracy rate in the past month was 90% (the percentage of days with a deviation of ±10% between the actual output and the planned output). Calculate the raw material and finished product inventory turnover rates. The raw material inventory turnover rate is 6 times / year (the ratio of annual raw material cost to average raw material inventory value), and the finished product inventory turnover rate is 8 times / year (the ratio of annual sales to average finished product inventory value). Combined with the output and equipment operating time, it is calculated that the average output per hour of each device is 100 pieces (production efficiency = total output ÷ (total number of equipment × total equipment operating time)).

[0032] Process employee data information to generate R&D progress information. Assume that there are currently three major R&D projects. Project A is the R&D of a new smartphone motherboard. It has completed the design phase and entered the sample trial production phase. It is expected to take another three months to complete testing and put into mass production; Project B is the R&D of computer motherboard performance improvement. It is in the design optimization phase and has completed 60% of the design tasks; Project C is the R&D of a new production process. It has just started and is in the conceptual design phase. According to the project completion ratio and estimated time, the overall R&D progress is calculated to be 40% ((Project A progress × Project A weight + Project B progress × Project B weight + Project C progress × Project C weight) ÷ total project weight, assuming that the weights of each project are equal).

[0033] Process network communication information and generate network security indicator information. Through simulated network attack tests, the firewall can effectively block 95% of common network attack types, such as port scanning, malware intrusion, etc., and the score is 9 (out of 10 points, based on the success rate of blocking attacks). The SSL / TLS encryption protocol is used for sensitive data transmission within the enterprise. The encryption algorithm strength meets industry standards. The AES encryption algorithm is used for data storage. The encryption coverage rate is 90% (the proportion of encrypted data to the total data volume), and the score is 8. Network security vulnerability scans are conducted regularly every month. In the past year, an average of 5 vulnerabilities were found per month, and the average repair time was 48 hours. The vulnerability repair timeliness rate was 90% (the number of vulnerabilities repaired within the specified time was the proportion of the total number of vulnerabilities), and the score was 7.

[0034] The target equipment's indicator information, production control indicator information, R&D progress information, and network security indicator information are processed to generate the target enterprise's digital indicator information. According to the weighted average of the digital control function indicators of each device (assuming that the weight of the SMT placement machine is 0.4, the weight of the wave soldering machine is 0.3, and the weight of the automated testing equipment is 0.3), the equipment digital level score is 8 (0.4×9+0.3×5+0.3×10). According to the weighted average of indicators such as production plan accuracy, inventory turnover rate, and production efficiency (assuming that the weights are 0.3, 0.3, and 0.4 respectively), the production control digital score is 8.2 (0.3×90%+0.3×(6+8)÷2+0.4×100) (here, the inventory turnover rate is simply averaged for example calculation). The R&D progress information is 40%, and the score is 4 (relative scoring can be performed based on the industry's average R&D progress level. Assuming that the industry's average R&D progress is 50%, the score is obtained based on the proportion). Based on the weighted average of indicators such as firewall effectiveness, network data encryption, and network security vulnerability management (assuming the weights are 0.4, 0.3, and 0.3 respectively), the network security digitalization score is 8 (0.4×9+0.3×8+0.3×7).

[0035] The digital indicator information of the final target enterprise can be a comprehensive score or indicator set, for example, a comprehensive score of 7 (obtained by weighting the above indicators, and the weights can be determined based on the enterprise's digital strategy focus and industry characteristics), and also include the scores of each detailed indicator, so as to comprehensively evaluate the enterprise's digital level and conduct comparative analysis with other enterprises.

[0036] S103, obtaining an initial enterprise evaluation model that matches the digital indicator information of the target enterprise and a training data set that matches the initial enterprise evaluation model.

[0037] In one implementation, the initial enterprise evaluation model takes a multilayer perceptron neural network model as an example, and the model includes an input layer, a hidden layer, and an output layer. Specifically, input layer: determine the number of input layer nodes based on the digital indicator information of the target enterprise. For example, if there are 10 digital indicator information such as equipment digital level indicators, production control digital indicators, R&D digital progress indicators, and network security digital indicators, then the number of input layer nodes is 10. Each node receives a digital indicator data. Hidden layer: set two hidden layers. The first hidden layer has 20 neurons, and the second hidden layer has 10 neurons. The activation function of the hidden layer neurons uses the ReLU (RectifiedLinearUnit) function, and its expression is The ReLU function can speed up the training of the neural network and effectively deal with the gradient vanishing problem. Output layer: The output layer has 1 node, which is used to output the initial digital value of the target enterprise (for example, a value between 0 and 1, indicating the relative degree of digitalization of the enterprise). The activation function of the output layer uses the Sigmoid function, which is expressed as , the Sigmoid function can map the output value to between 0 and 1, which is suitable for expressing output results such as probability or relative degree.

[0038] The model training process is as follows: collect a large amount of digital indicator information from different companies and the corresponding digital level assessment results (which can be expert assessments or level results determined based on other mature assessment standards). For example, data from 1,000 companies are collected, and the digital indicator information of each company is used as input features, and the corresponding digital level assessment results are processed as output labels. Divide these data into training sets and validation sets according to a certain ratio (such as 80% for training and 20% for validation). The mean square error (MSE) is used as the loss function, and its expression is , where n is the number of samples, is the real digital grade assessment result (the processed value), It is the digital grade evaluation result of the model prediction. The mean square error can measure the average error between the model prediction value and the true value, and the model is trained by minimizing the mean square error. Optimization algorithm: Use the stochastic gradient descent (SGD) algorithm and its variants, such as stochastic gradient descent with momentum (SGDwithMomentum). The momentum term can accelerate the convergence of SGD in the relevant direction and reduce the oscillation at the local minimum. The learning rate is set to 0.01 and the momentum parameter is set to 0.9. During the training process, the learning rate is dynamically adjusted according to the loss value of the validation set. For example, when the loss of the validation set no longer decreases for several consecutive epochs (training rounds), the learning rate is multiplied by a decay factor (such as 0.5). The training set data is input into the multilayer perceptron neural network model and trained according to the selected loss function and optimization algorithm. In each epoch, all samples of the training set are traversed, the loss value is calculated and the parameters of the model are updated. After multiple epochs of training, the loss value of the model on the validation set converges or reaches the predetermined training round (such as 500 epochs).

[0039] Use the test set (the part separated from the original data and not involved in training and validation) to evaluate the trained model. Evaluation indicators can be accuracy, root mean square error (RMSE), etc. For example, the accuracy is calculated as the ratio of the digital level predicted by the calculation model to the actual digital level in the test set, and the RMSE is obtained by calculating the root mean square of the error between the predicted value and the true value. According to the evaluation results, the model with the best performance is selected as the initial enterprise evaluation model, which will be used to process the digital indicator information of the target enterprise and generate the initial digital value of the target enterprise. Such an initial enterprise evaluation model structure and training process example can be adjusted and optimized according to the characteristics of the digital indicator information of the target enterprise and the evaluation needs to improve the accuracy and reliability of the model.

[0040] S104, processing the initial enterprise evaluation model based on the training data set to generate a target enterprise evaluation model.

[0041] In one implementation, feature extraction is performed on the training data set to determine the original feature library. Assume that we are building a model to evaluate the digitalization level of manufacturing enterprises, and have collected a large amount of enterprise data as a training data set. These data contain various information about the enterprises, such as enterprise scale, equipment digitalization level, employee digital skills level, network security investment, data management efficiency and many other features. First, each enterprise data in the training data set is analyzed in detail to extract features that may be related to enterprise digitalization. For example, sub-features such as the number of employees and annual turnover are extracted from enterprise scale data; the proportion of automated equipment and the rate of equipment networking are extracted from equipment digitalization level data; the proportion of employees who have received digital training and the number of employees with digital-related professional qualifications are extracted from employee digital skills level data; the proportion of security equipment purchase amount and the proportion of security personnel cost are extracted from network security investment data; the data update frequency and data error rate are extracted from data management efficiency data. All these extracted features form the original feature library. Assume that 30 different features are extracted, and these features constitute the original feature library. The original feature library is divided according to a certain ratio (for example, 70% is the training set and 30% is the validation set). Randomly distribute the enterprise data into two data sets: training set and validation set. Assuming that the original data set contains data from 500 enterprises, the training set will contain data from 350 enterprises and the validation set will contain data from 150 enterprises.

[0042] The original feature library is divided into various feature data sets to generate training sets and validation sets. Based on the classifier, each validation set divided by the original feature library is predicted and processed to generate prediction results. Based on the preset algorithm, each training set divided by the original feature library is trained and processed to generate validation set prediction results. Select a suitable classifier, such as a decision tree classifier. The decision tree classifier builds a tree model based on the characteristics of the data and classifies the data by judging the characteristics. Input the validation set data into the decision tree classifier. The decision tree will start from the root node and branch down gradually according to the different values ​​of the characteristics based on the various feature values ​​of the enterprises in the validation set. Finally, each enterprise is divided into different categories (here, it can be high, medium, low, etc.), thereby generating prediction results. For example, for an enterprise in the validation set, the decision tree predicts it as a low-level digitalization category based on its low equipment networking rate and low proportion of employee digital training. Select a preset algorithm, such as the stochastic gradient descent (SGD) algorithm, to train the training set. For each enterprise data in the training set, the SGD algorithm calculates the loss value under the current model parameters according to the preset loss function (such as the cross entropy loss function, which is used to measure the difference between the predicted result and the actual result), and updates the model parameters by gradient descent to reduce the loss value. During the training process, the model parameters (such as the node splitting rules and thresholds in the decision tree classifier) ​​are continuously adjusted so that the model's prediction results on the training set gradually approach the actual results, thereby generating a validation set prediction result. The validation set prediction result here refers to the result similar to the prediction of the validation set obtained after the model processes the training set data during the training process, which is used for subsequent comparative analysis.

[0043] The prediction results and the prediction results of the validation set are processed to generate target feature data. The target feature data is used to characterize the risk factors that affect the digitalization of enterprises. The preset enterprise evaluation model is processed based on the training data set with the target feature data to generate the target enterprise evaluation model. The prediction results of the validation set are compared with the prediction results of the training set. For example, the accuracy, recall and other indicators between the prediction results and the actual results are calculated. For those features with large differences between the prediction results and the actual results, they are regarded as risk factor features that may affect the digitalization of enterprises. Assuming that the feature of the device networking rate is found to have outliers in many enterprises with incorrect predictions, the device networking rate may be a risk factor feature that affects the digitalization of enterprises. These determined risk factor features are used as target feature data.

[0044] The training data set with target feature data (i.e., highlighting the risk factor characteristics) is input again into the preset enterprise assessment model (e.g., a multi-layer perceptron neural network model) for training. The neural network model will adjust the connection weights and thresholds between its neurons based on these data to better adapt to the risk factor characteristics in the data. After multiple rounds of training, a target enterprise assessment model is generated. This model can pay more attention to the risk factors that affect the digitalization of enterprises when assessing the digitalization level of enterprises, thereby improving the accuracy and reliability of the assessment. For example, when the target enterprise assessment model assesses a new enterprise, if the enterprise's equipment networking rate is low, the model will assess its digitalization level more cautiously due to previous training, and may give a relatively low digitalization grade score, and highlight the digitalization risks that may be caused by the low equipment networking rate in the assessment report.

[0045] S105: Process the digital indicator information of the target enterprise and the industry information of the target enterprise based on the target enterprise evaluation model to generate an initial digital value of the target enterprise.

[0046] In one implementation, the target enterprise's industry information is processed based on the target enterprise evaluation model to generate industry characteristic information; the target enterprise's digital indicator information is processed based on the target enterprise evaluation model to generate a data resource indicator set. The food processing industry information to which the enterprise belongs is processed through the target enterprise evaluation model. Industry characteristics may include the industry's average automation level, the degree of emphasis on food safety data management, the intensity of market competition, etc. For example, for the feature of the industry's average automation level, if the overall equipment automation level of the food processing industry is at a medium level, the numerical value may be 0.6 (assuming quantification from 0 to 1, 0 means no automation at all, and 1 means high automation); the degree of emphasis on food safety data management is high, which can be set to 0.8, because the food industry has strict requirements on quality and safety, and data management is more important; the intensity of market competition is assumed to be 0.5, which means that there is a certain amount of competition in the market but it is not particularly fierce. In this way, the industry characteristic information vector . Similarly, the target enterprise evaluation model is used to process the digital indicator information of the target enterprise to obtain the data resource indicator set. Data resource indicators may include data accuracy, data update frequency, data storage capacity, etc. If the data accuracy of the food processing enterprise is high, it is set to 0.7; the data update frequency is once a week, which is at a medium level, set to 0.5; the data storage capacity is large and can meet the enterprise's data storage needs for a period of time, set to 0.8. Then the data resource indicator set vector .

[0047] The industry characteristic information and the data resource indicator set are processed to generate an initial digital value of the target enterprise. The method also includes a calculation formula for obtaining the initial digital value of the target enterprise, which is:

[0048] ;

[0049] Among them, D represents the initial digitalization value of the target enterprise, which is the final result to be obtained and is used to measure the initial level of digitalization of the enterprise. In etc. represent different industry characteristics, such as the average automation level of the industry mentioned above, the importance attached to food safety data management, etc. is the number of industry characteristics. For example, if there are three industry characteristics, then m=3. The vector In etc. represent different data resource indicators, such as data accuracy, data update frequency, etc. is the number of data resource indicators. Here, assuming there are also three data resource indicators, then n=3. and is a weight coefficient used to balance the contribution of industry characteristic information and data resource indicator set to the initial digital value. Assuming that the industry characteristics and data resource indicators are equally important after analysis, you can set, , .

[0050] It is an industry characteristic The weights of reflect the relative importance of different industry characteristics in determining the initial digital value. For example, if it is believed that the importance of food safety data management is more critical in the food industry, this feature can be given a higher weight. (corresponding to the average automation level of the industry), (corresponding to the importance of food safety data management), (Corresponding to the intensity of market competition). It is a data resource indicator The weights of also reflect the importance of different data resource indicators to the initial digitized value. For example, if data accuracy is considered relatively important, (corresponding to data accuracy), 3 (corresponding to data update frequency), (corresponding to data storage capacity).

[0051] According to the parameter values ​​set above, substitute them into the calculation formula Calculate the initial digital value of the target enterprise. First calculate the industry characteristics: . Then calculate the data resource indicator set part: . Finally calculate the initial digitized value Through such a calculation process, the initial digital value of the target enterprise can be obtained. This value comprehensively considers the characteristics of the industry to which the enterprise belongs and the data resource indicators of the enterprise itself, providing basic data for further evaluation of the digital level of the enterprise.

[0052] S106, processing the target event information that matches the target enterprise information and the capital information of the target enterprise to generate a digital adjustment factor.

[0053] In one implementation, the target event information matching the target enterprise information is processed to generate event classification information and event key factor features corresponding to the event classification information. The target event information matching the target enterprise information is analyzed. Event classification can be divided into technology innovation events, market competition events, policy and regulatory events, etc. Technology innovation event: The enterprise has developed a new chip packaging technology, which has improved production efficiency and product quality. Key factor features include the advancement of innovative technology (for example, it is at the leading level in the industry and can improve production efficiency by 30%), application scope (expected to cover 80% of the enterprise's product lines in the next year), etc. Market competition event: A competitor launched a product with a lower price and similar performance, and the enterprise responded by increasing marketing investment and optimizing product services. Key factor features include competition objects (clear competitor enterprises), competition strategies (increasing marketing investment, improving service quality), and competition results (changes in market share, changes in brand awareness, etc.). Policy and regulatory events: The government has introduced environmental protection policies requiring enterprises to reduce energy consumption. The enterprise actively responded and invested funds to upgrade equipment. Key factor characteristics include specific requirements of policies and regulations (specific indicators for reducing energy consumption), impact on the digitalization process of enterprises (promoting enterprises to adopt digital energy management systems), etc.

[0054] A quantitative evaluation index system is set for each type of event. For example, for technological innovation events, a score of 1-10 is given according to the advancement of the innovative technology. Here, it is assumed that the advancement score of the new chip packaging technology is 8 points; a weight coefficient of 0-1 is given according to the proportion of the application scope to the company's business. Assuming that the application scope accounts for 80%, the weight coefficient is 0.8. Then the quantitative score of the technological innovation event is 8×0.8=6.4 points. Similarly, a quantitative evaluation is conducted on market competition events and policy and regulatory events. Assume that the quantitative score of market competition events is 4 points, and the quantitative score of policy and regulatory events is 5 points. Combining the quantitative scores of various types of events, assuming that the weight of technological innovation events is 0.4, the weight of market competition events is 0.3, and the weight of policy and regulatory events is 0.3, then the quantitative score of the target event information E=0.4×6.4+0.3×4+0.3×5=2.56+1.2+1.5=5.26 points.

[0055] Process the target enterprise's funding information to generate a funding quantitative score, process the event classification information and the event key factor characteristics corresponding to the event classification information, and generate a target event information quantitative score. Analyze the target enterprise's funding information, including the amount of funding invested in the digital project, the stability of funding sources, and the efficiency of funding use. Amount of funding invested: In the past year, the company invested 5 million yuan in digital projects. Stability of funding sources: The company's funds mainly come from its own funds and bank loans, with own funds accounting for 70% and bank loans accounting for 30%. Own funds are relatively stable, and a higher stability score is given, assuming 0.8; bank loans have certain repayment pressure, and the stability score is slightly lower, assuming 0.6. The comprehensive funding source stability score is 0.7×0.8+0.3×0.6=0.56+0.18=0.74. Efficiency of funding use: By calculating the input-output ratio of digital projects, it is assumed that every 1 yuan of digital funds invested can bring 2 yuan of new income or cost savings. The funding efficiency score is 0.8 (scored based on the industry average and the company's own situation). Taking into account factors such as the amount of capital investment, the stability of the source of capital, and the efficiency of capital use, the calculation formula for the capital quantitative score is set as F = capital investment score × capital source stability score × capital use efficiency score. Assume that the capital investment score is scored based on the relative level of the enterprise's investment amount in the industry, which is assumed to be 0.7 here. Then the capital quantitative score F = 0.7 × 0.74 × 0.8 = 0.4144.

[0056] The quantitative score of funds and the quantitative score of target event information are processed to generate a digital adjustment factor. The method also includes a calculation formula for the user to obtain the digital adjustment factor, which is:

[0057] ; ; Among them, the target event information weight is , the weight of fund information is , represents the quantitative score of the target event information, and F represents the quantitative score of funds. Assume that the target event information weight is 0.6, the weight of fund information is 0.4. According to the calculation formula , where E=5.26 (quantitative score of target event information) and F=0.4144 (quantitative score of funds). Then the digital adjustment factor A=0.6×5.26+0.4×0.4144=3.156+0.16576=3.32176. Through the above steps, the target event information and fund information are processed to generate the digital adjustment factor, which can be used to adjust the initial digital value of the target enterprise to more accurately evaluate the digital level information of the enterprise.

[0058] S107: Processing the initial digital value of the target enterprise and the digital adjustment factor based on the target enterprise evaluation model to generate digital level information of the target enterprise.

[0059] In one implementation, the initial digital value and digital adjustment factor of the target enterprise are processed based on the target enterprise evaluation model to generate a comprehensive evaluation factor, wherein the comprehensive evaluation factor is used to characterize the comprehensive digitalization of the target enterprise under the influence of the basic digital level and various adjustment factors. First, determine the initial digital value and digital adjustment factor of the target enterprise. The initial digital value can be calculated by the previous method, assuming it is 70 (this is just an example value). The digital adjustment factor is generated by the quantitative score of the target event information (E) and the quantitative score of funds (F). Assume that E=4.5 (obtained through the processing of target event information, such as the quantitative score of events such as technological innovation, market competition, policies and regulations), and F=0.6 (obtained through the processing of corporate financial information, including quantitative scores of capital investment, source stability, and utilization efficiency). Then the digital adjustment factor can be calculated according to the formula (It is assumed that the target event information weight , fund information weight ) is calculated: The comprehensive evaluation factor is used to characterize the comprehensive digitalization of the target enterprise under the influence of the basic digitalization level and various adjustment factors. Assume that the target enterprise evaluation model is an algorithm or model that comprehensively considers multiple factors. It takes the initial digitalization value and the digitalization adjustment factor as input, and generates a comprehensive evaluation factor after a series of calculations and analyses. Here, it is assumed that the comprehensive evaluation factor is EF=70 3.33=233.1.

[0060] The comprehensive evaluation factors are processed to generate a digital score for the target enterprise. , , Represents coefficient parameters, which can be adjusted according to industry characteristics, enterprise type and evaluation purpose. , which mainly affects the linear contribution degree of the comprehensive evaluation factors; , used to adjust the quadratic contribution of the comprehensive evaluation factor; , is a constant term used to calibrate the overall score range. According to the calculation formula , the comprehensive evaluation factor And the coefficient parameters are substituted into the formula to calculate the digital score: .

[0061] The digital score of the target enterprise is processed to generate digital grade information of the target enterprise. The method includes a calculation formula for obtaining the digital score of the target enterprise, and the calculation formula is:

[0062] ;in, , , represents the coefficient parameter, represents the quantitative score of the target event information, and F represents the quantitative score of funds. The digitization level is determined according to the digitization score. Different digitization score intervals can be pre-set to correspond to different digitization levels. For example, a score of 0-1000 is primary digitization, 1001-5000 is intermediate digitization, and 5001 and above is advanced digitization. Based on the previously calculated digitization score , the target enterprise is at an advanced digital level. Through the above steps, using calculation formulas and a series of processing processes, starting from the initial digital value and digital adjustment factor of the target enterprise, the digital score and digital level information of the target enterprise are gradually generated, providing a specific method and basis for comprehensively evaluating the digital level of the enterprise.

[0063] This method first obtains various types of information about the target enterprise, performs segmented processing on the enterprise information, generates different indicator information from the equipment list, production and sales data, employee data, and network communication information, and then obtains digital indicator information in a comprehensive manner. Next, the training data set is extracted for features, and the training set and validation set are divided. After classifier prediction and preset algorithm training, the target feature data is obtained by comparing the results to construct the target enterprise evaluation model. Then, the model processes the industry information and digital indicator information to generate the initial digital value, and processes the target event and capital information to obtain the digital adjustment factor. Finally, the model processes the initial digital value and the adjustment factor to generate a comprehensive evaluation factor, and further obtains the digital score, thereby determining the digital level information. This method fully considers various factors of the enterprise and provides a systematic and accurate approach and tool for the digital level evaluation of the enterprise.

[0064] In one embodiment, if Figure 2 As shown, the present application also provides an evaluation device for enterprise digitalization level, including:

[0065] The acquisition module 201 is used to acquire target enterprise information, target event information matching the target enterprise information, industry information of the target enterprise, and funding information of the target enterprise; acquire an initial enterprise evaluation model matching the digital indicator information of the target enterprise and a training data set matching the initial enterprise evaluation model;

[0066] Processing module 202 is used to process the target enterprise information to generate digital index information of the target enterprise; process the initial enterprise evaluation model based on the training data set to generate a target enterprise evaluation model; process the digital index information of the target enterprise and the industry information of the target enterprise based on the target enterprise evaluation model to generate an initial digital value of the target enterprise; process the target event information matching the target enterprise information and the funding information of the target enterprise to generate a digital adjustment factor; process the initial digital value of the target enterprise and the digital adjustment factor based on the target enterprise evaluation model to generate the digital level information of the target enterprise.

[0067] The present application embodiment provides an electronic device, such as Figure 3 As shown, the electronic device 3 includes a first processor 300, a memory 301, a bus 302 and a communication interface 303, and the first processor 300, the communication interface 303 and the memory 301 are connected via the bus 302; the memory 301 stores a computer program that can be run on the first processor 300, and when the first processor 300 runs the computer program, it executes the enterprise digitization level evaluation method provided in any of the aforementioned embodiments of the present application.

[0068] The memory 301 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 303 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0069] The bus 302 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 301 is used to store a program, and the first processor 300 executes the program after receiving an execution instruction. The enterprise digitalization level evaluation method disclosed in any implementation of the embodiment of the present application may be applied to the first processor 300, or implemented by the first processor 300.

[0070] The first processor 300 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the first processor 300. The above-mentioned first processor 300 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be embodied as being executed by a hardware decoding processor, or by a combination of hardware and software modules in a decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 301, and the first processor 300 reads the information in the memory 301 and completes the steps of the above method in combination with its hardware.

[0071] The electronic device provided by the above-mentioned embodiment of the present application and the enterprise digitalization level evaluation method provided by the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0072] The present application embodiment provides a computer-readable storage medium, such as Figure 4 As shown, the computer-readable storage medium 401 stores a computer program, and when the computer program is read and executed by the second processor 402, the aforementioned enterprise digitalization level evaluation method is implemented.

[0073] The technical solution of the embodiment of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling an electronic device (which may be an air conditioner, a refrigeration device, a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0074] Each embodiment in the present application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the evaluation method, electronic device, electronic device, and readable storage medium embodiment for evaluating the digital level of an enterprise, since they are basically similar to the above-mentioned evaluation method embodiment for the digital level of an enterprise, the description is relatively simple, and the relevant parts can be referred to the partial description of the above-mentioned evaluation method embodiment for the digital level of an enterprise.

[0075] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application shall be subject to the scope defined by the claims.

Claims

1. A method for evaluating the digitalization level of an enterprise, characterized in that: include: Obtain target enterprise information, target event information matching the target enterprise information, target enterprise industry information and target enterprise funding information; Processing the target enterprise information to generate digital indicator information of the target enterprise; Acquire an initial enterprise evaluation model that matches the digital indicator information of the target enterprise and a training data set that matches the initial enterprise evaluation model; Processing the initial enterprise evaluation model based on the training data set to generate a target enterprise evaluation model; Processing the digital indicator information of the target enterprise and the industry information of the target enterprise based on the target enterprise evaluation model to generate an initial digital value of the target enterprise; Processing target event information that matches target enterprise information and funding information of the target enterprise to generate a digital adjustment factor; The initial digital value of the target enterprise and the digital adjustment factor are processed based on the target enterprise evaluation model to generate digital level information of the target enterprise.

2. The method according to claim 1, characterized in that The target enterprise information is processed to generate digital indicator information of the target enterprise, including: Processing the target enterprise information to generate equipment inventory information, production data information, sales data information, employee data information and network communication information of the target enterprise; Processing the equipment list information of the target enterprise to generate index information of the target equipment, wherein the index of the target equipment is used to characterize whether the target equipment has a digital control function; Processing the production data information and the sales data information to generate production control indicator information; Processing the employee data information to generate R&D progress information; Processing the network communication information to generate network security indicator information; The index information of the target device, the production control index information, the research and development progress information and the network security index information are processed to generate digital index information of the target enterprise.

3. The method according to claim 1, characterized in that The initial enterprise evaluation model is processed based on the training data set to generate a target enterprise evaluation model, including: Extract features from the training data set and determine the original feature library; Dividing the original feature library into various feature data sets to generate a training set and a validation set; Based on the classifier, each verification set divided by the original feature library is predicted and processed to generate a prediction result; Based on the preset algorithm, each training set divided by the original feature library is trained and processed to generate the prediction results of the validation set class; Processing the prediction results and the prediction results of the validation set to generate target feature data, where the target feature data is used to characterize risk factors that affect enterprise digitalization; The initial enterprise evaluation model is processed based on a training data set with target feature data to generate a target enterprise evaluation model.

4. The method according to claim 1, characterized in that The digital indicator information of the target enterprise and the industry information of the target enterprise are processed based on the target enterprise evaluation model to generate an initial digital value of the target enterprise, including: Processing the industry information of the target enterprise based on the target enterprise evaluation model to generate industry characteristic information; Processing the digital indicator information of the target enterprise based on the target enterprise evaluation model to generate a data resource indicator set; The industry characteristic information and the data resource indicator set are processed to generate an initial digital value of the target enterprise.

5. The method according to claim 4, characterized in that Processing the digital indicator information of the target enterprise and the industry information of the target enterprise based on the target enterprise evaluation model to generate an initial digital value of the target enterprise, further comprising: The method also includes a calculation formula for obtaining the initial digital value of the target enterprise, and the calculation formula is: ； Among them, D represents the initial digital value of the target enterprise, and the industry characteristic information is represented by vector Indicated by, m represents the number of industry characteristic information, and the data resource indicator set is represented by vector Indicates that n represents the number of data resource indicators, and represents the weight coefficient, Representative industry characteristic information The weights are used to reflect the relative importance of different industry characteristics in determining the initial digital value. Representative data resource indicator set The weights are used to reflect the importance of different data resource indicators to the initial digitized value.

6. The method according to claim 4, characterized in that The target event information matching the target enterprise information and the capital information of the target enterprise are processed to generate a digital adjustment factor, including: Processing target event information that matches target enterprise information to generate event classification information and event key factor features corresponding to the event classification information; Processing the target enterprise's funding information to generate a funding quantitative score; Processing the event classification information and event key factor features corresponding to the event classification information to generate a quantitative score of target event information; Processing the quantitative score of the funds and the quantitative score of the target event information to generate a digital adjustment factor; The method further includes a user obtaining a calculation formula for a digitization adjustment factor, the calculation formula being: ； ； Among them, the target event information weight is , the weight of fund information is , represents the quantitative score of the target event information, and F represents the quantitative score of funds.

7. The method according to claim 6, characterized in that The initial digital value of the target enterprise and the digital adjustment factor are processed based on the target enterprise evaluation model to generate digital level information of the target enterprise, including: Based on the target enterprise evaluation model, the initial digitalization value of the target enterprise and the digitalization adjustment factor are processed to generate a comprehensive evaluation factor, wherein the comprehensive evaluation factor is used to characterize the comprehensive digitalization of the target enterprise under the influence of the basic digitalization level and various adjustment factors; Processing the comprehensive evaluation factors to generate a digital score for the target enterprise; Processing the digital score of the target enterprise to generate digital grade information of the target enterprise; The method includes a calculation formula for obtaining a digital score of a target enterprise, and the calculation formula is: ； in, , , represents the coefficient parameter, represents the quantitative score of the target event information, and F represents the quantitative score of funds.

8. An evaluation device for enterprise digitalization level, characterized in that: The device comprises: An acquisition module is used to acquire target enterprise information, target event information matching the target enterprise information, industry information of the target enterprise, and funding information of the target enterprise; acquire an initial enterprise evaluation model matching the digital indicator information of the target enterprise and a training data set matching the initial enterprise evaluation model; A processing module is used to process the target enterprise information to generate digital index information of the target enterprise; process the initial enterprise evaluation model based on the training data set to generate a target enterprise evaluation model; process the digital index information of the target enterprise and the industry information of the target enterprise based on the target enterprise evaluation model to generate an initial digital value of the target enterprise; process the target event information matching the target enterprise information and the funding information of the target enterprise to generate a digital adjustment factor; process the initial digital value of the target enterprise and the digital adjustment factor based on the target enterprise evaluation model to generate digital grade information of the target enterprise.

9. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; The first processor is configured to execute the enterprise digitization level evaluation method according to any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the method for evaluating the enterprise digitization level according to any one of claims 1 to 7 is implemented.

Images