Equipment checking method and device based on artificial intelligence, equipment and medium

Abstract

The invention discloses an artificial intelligence-based equipment checking method and device, equipment and a medium, and the method comprises the steps: evaluating the checking probability of each piece of equipment based on the basic information, historical use conditions, checking loss records and maintenance records of the equipment, and determining to-be-checked equipment based on the checking probability of each piece of equipment; determining a checking task according to the employee information and the to-be-checked equipment; an inventory task is issued to the inventory personnel, task information uploaded by the inventory personnel is acquired, and the task information comprises the equipment identifier, the equipment position and the equipment photo; identifying and predicting the equipment picture to obtain a current state evaluation result of the equipment; and taking the equipment position corresponding to the equipment identifier and the current equipment state evaluation result as current equipment information, comparing the current equipment information with historical equipment information corresponding to the equipment identifier stored in a database, and determining an inventory result. According to the invention, the efficiency and the intelligent level of equipment checking are improved.

Description

Technical Field

[0001] The present invention relates to the field of equipment management, and in particular to an equipment inventory method, device, equipment and medium based on artificial intelligence. Background Art

[0002] Equipment inventory refers to an important equipment management procedure for counting, recording and checking equipment assets. For manufacturing companies, regular equipment inventory is crucial. It helps to ensure the accuracy and completeness of equipment asset management, timely identify and solve potential problems of equipment, avoid sudden failures, and improve equipment reliability and stability. In addition, accurate equipment inventory data can also increase asset transparency and provide an important basis for corporate decision-making. This data can be used to optimize equipment configuration, formulate reasonable maintenance plans and procurement decisions, thereby helping companies achieve long-term development goals. Traditional equipment inventory is usually conducted manually. This process requires the equipment manager to physically count, record and check the equipment one by one, and then manually update the inventory results to the company's asset management system. Equipment managers must personally ensure that each equipment is counted and recorded every year to ensure the accuracy and completeness of the equipment list.

[0003] However, manufacturing enterprises often face complex scenarios in equipment management. At present, the equipment management of manufacturing enterprises mainly focuses on large, immovable and expensive equipment, and pays less attention to portable equipment. They usually adopt the same inventory management mode and lack personalized management for different types of equipment. This traditional inventory can no longer meet the needs of today's digital and lean management. The main reasons are as follows: First, mobile devices often need to operate in different production or R&D sites, and their location and usage status change frequently, which requires inventory personnel to spend a lot of time and energy to locate these mobile devices, resulting in low inventory efficiency and time-consuming and labor-intensive. Secondly, manual inventory may affect the normal use of equipment, causing production line shutdown or production plan disruption, thereby affecting the company's production efficiency and customer delivery time. In addition, since manual inventory requires manual recording and verification of a large amount of data, the accuracy of the data is easily affected by human factors. In this case, there is a risk of data input errors, omissions, tampering and fraud, which in turn causes potential damage to the company's equipment management and operations. With the continuous development of information technology, many equipment inventory systems that integrate barcode / QR code scanning technology, RFID technology and mobile applications have emerged on the market. These systems provide enterprises with more convenient operation methods and greatly improve the efficiency of equipment inventory. However, although the application of these technologies makes inventory operations more convenient, manual intervention is still required. Therefore, further improvement and innovation are urgently needed to overcome the current limitations of relying on manual intervention and realize the comprehensive automation and intelligence of equipment inventory work. Summary of the invention

[0004] The embodiments of the present invention provide an artificial intelligence-based device inventory method, apparatus, computer equipment and storage medium to improve the efficiency and intelligence level of device inventory.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a device inventory method based on artificial intelligence, including:

[0006] Based on the basic information, historical usage, inventory shortage records and maintenance records of the equipment, the probability of inventory shortage for each equipment is evaluated, and based on the probability of inventory shortage for each equipment, the equipment to be counted is determined;

[0007] Determine an inventory task according to the employee information and the equipment to be counted, wherein the inventory task includes an inventory person and the equipment to be counted corresponding to the inventory person, and the inventory person is an employee selected according to the employee information and the equipment to be counted;

[0008] issuing the inventory task to the inventory personnel, and obtaining the task information uploaded by the inventory personnel, wherein the task information includes the equipment identification, equipment location and equipment photo;

[0009] Performing identification and prediction on the equipment photo to obtain an evaluation result of the current state of the equipment;

[0010] The device location corresponding to the device identification and the device current status evaluation result are used as current device information, and the current device information is compared with the historical device information corresponding to the device identification stored in the database to determine the inventory result.

[0011] Optionally, the evaluating the probability of inventory shortage of each device based on the basic information, historical usage, inventory shortage record and maintenance record of the device includes:

[0012] The Bayesian statistical model is established by taking the equipment's historical usage and inventory records as prior probabilities and the most recent inventory results and equipment usage, maintenance and other information as new evidence.

[0013] According to the Bayesian statistical model, the posterior probability of each device being out of stock is calculated using the prior probability and new evidence as the probability of the device being out of stock.

[0014] Optionally, the determining of the equipment to be counted based on the probability of shortage of each equipment during the inventory counting includes:

[0015] Generate a risky equipment list according to the probability of equipment shortage and a preset probability threshold;

[0016] Based on the risk equipment list and business rules, the equipment to be counted is determined.

[0017] Optionally, determining the inventory task according to the employee information and the equipment to be inventoried includes:

[0018] For a device to be counted, according to the employee current location in the employee information, an employee corresponding to the employee current location whose distance between the employee current location and the device location is less than a preset distance threshold is selected as a candidate employee;

[0019] An inventory checker for the equipment to be checked is determined based on the skills and experience levels of the candidate employees recorded in the employee information.

[0020] Optionally, the performing identification and prediction on the device photo to obtain a device current status evaluation result includes:

[0021] The input image is X, and the convolutional neural network model f-rows processing and feature extraction are used to obtain the feature representation h = f(X);

[0022] Use the fully connected layer to classify the features and obtain the current status evaluation result y of the equipment pred ,Right now:

[0023] y pred＝softmax(W · h+b)

[0024] Among them, W and b are the weight and bias of the fully connected layer, and the softmax function is used to convert the prediction results into a probability distribution so that the sum of the probabilities of each category is 1.

[0025] In order to solve the above technical problems, the embodiment of the present application further provides an artificial intelligence-based device inventory device, including:

[0026] The equipment determination module is used to evaluate the probability of each equipment being lost based on the basic information, historical usage, loss records and maintenance records of the equipment, and determine the equipment to be counted based on the probability of each equipment being lost;

[0027] A task generation module is used to determine the inventory task according to the employee information and the equipment to be counted. The inventory task includes the inventory personnel and the equipment to be counted corresponding to the inventory personnel. The inventory personnel are employees selected according to the employee information and the equipment to be counted.

[0028] The task execution module is used to issue inventory tasks to inventory personnel and obtain task information uploaded by inventory personnel. The task information includes equipment identification, equipment location and equipment photos;

[0029] Image recognition module, used to identify and predict equipment photos and obtain the equipment's current status assessment results;

[0030] The result evaluation module is used to take the device location corresponding to the device identification and the device current status evaluation result as the current device information, and compare the current device information with the historical device information corresponding to the device identification stored in the database to determine the inventory result.

[0031] Optionally, the device determination module includes:

[0032] A priori probability determination unit is used to establish a Bayesian statistical model by taking the equipment's historical use and inventory records as prior probabilities and the most recent inventory results and equipment use, maintenance and other information as new evidence;

[0033] The posterior probability calculation unit is used to calculate the posterior probability of each device being out of stock according to the Bayesian statistical model using the prior probability and new evidence as the probability of the device being out of stock.

[0034] Optionally, the device determination module further includes:

[0035] A risk equipment list generating unit, used for generating a risk equipment list according to the probability of equipment inventory shortage and a preset probability threshold;

[0036] The equipment to be counted determining unit is used to determine the equipment to be counted based on the risk equipment list and business rules.

[0037] In order to solve the above technical problems, an embodiment of the present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned artificial intelligence-based device inventory method when executing the computer program.

[0038] In order to solve the above technical problems, an embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned artificial intelligence-based device inventory method are implemented.

[0039] The artificial intelligence-based equipment inventory method, device, computer equipment and storage medium provided in the embodiment of the present invention evaluate the probability of inventory shortage of each equipment through the basic information, historical usage, inventory shortage record and maintenance record of the equipment, and determine the equipment to be inventoried based on the probability of inventory shortage of each equipment; determine the inventory task according to the employee information and the equipment to be inventoried, the inventory task includes the inventory personnel and the equipment to be inventoried corresponding to the inventory personnel, and the inventory personnel are employees selected according to the employee information and the equipment to be inventoried; issue the inventory task to the inventory personnel, and obtain the task information uploaded by the inventory personnel, and the task information includes the equipment identification, equipment location and equipment photos; identify and predict the equipment photos to obtain the current status evaluation result of the equipment; use the equipment location corresponding to the equipment identification and the current status evaluation result of the equipment as the current equipment information, and compare the current equipment information with the historical equipment information corresponding to the equipment identification stored in the database to determine the inventory result. A centralized management mode of mobile devices is realized, and intelligent means such as computer vision technology, machine learning, and deep learning are used to improve the automation, efficiency and intelligence level of equipment inventory. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0041] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0042] Figure 2 It is a flow chart of an embodiment of the artificial intelligence-based device inventory method of the present application;

[0043] Figure 3 It is a structural schematic diagram of an embodiment of an artificial intelligence-based device inventory device according to the present application;

[0044] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0046] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] See also Figure 1 ,like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0049] Users can use terminal devices 101 , 102 , 103 to interact with server 105 via network 104 to receive or send messages, etc.

[0050] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0051] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0052] It should be noted that the artificial intelligence-based device inventory method provided in the embodiment of the present application is executed by a server, and accordingly, the artificial intelligence-based device inventory device is arranged in the server.

[0053] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. According to the implementation requirements, there may be any number of terminal devices, networks and servers. The terminal devices 101, 102, 103 in the embodiment of the present application may specifically correspond to application systems in actual production.

[0054] See also Figure 2 , Figure 2 An artificial intelligence-based device inventory method provided by an embodiment of the present invention is shown. The method is applied in Figure 1 The server in is used as an example to illustrate the details as follows:

[0055] S201: Based on the basic information, historical usage, inventory shortage records and maintenance records of the equipment, the probability of inventory shortage for each equipment is evaluated, and based on the probability of inventory shortage for each equipment, the equipment to be inventoried is determined.

[0056] Specifically, in this embodiment, the basic information of the equipment, such as equipment name, specification model, purchase time, purchase price, equipment code, asset code, maintenance record, etc., is entered into the barcode / QR code / RFID tag of the inventory and affixed to the equipment. The equipment can be quickly and accurately identified and located, and detailed information of the equipment can be easily obtained. When the equipment information changes, only the basic information in the system needs to be changed, and there is no need to re-post the label. As a preferred method, a centralized management warehouse for mobile devices of the group company is established to collect all mobile devices of the subordinate business units and store and manage them in a standardized manner. If a technician needs to use the equipment, he must first submit the corresponding mobile device use application, and only after approval by relevant personnel can he go to the physical centralized management warehouse to collect the required equipment. The holder of the mobile device that is loaned out is the borrowed technician, and the holder of the fixed equipment and the mobile device that is not loaned out is the centralized warehouse keeper. The person who takes inventory of the equipment shall be the equipment holder.

[0057] In a specific optional implementation, based on the basic information, historical usage, inventory shortage records and maintenance records of the equipment, evaluating the probability of inventory shortage of each equipment includes:

[0058] The Bayesian statistical model is established by taking the equipment's historical usage and inventory records as prior probabilities and the most recent inventory results and equipment usage, maintenance and other information as new evidence.

[0059] According to the Bayesian statistical model, the posterior probability of each device being short in inventory is calculated using the prior probability and new evidence as the probability of the device being short in inventory.

[0060] In a specific optional implementation manner, based on the probability of shortage of each device during inventory counting, determining the devices to be counted includes:

[0061] Generate a risky equipment list based on the probability of equipment shortage and the preset probability threshold;

[0062] Based on the risk equipment list and business rules, determine the equipment to be counted.

[0063] Specifically, this embodiment uses a Bayesian statistical model to estimate the probability of inventory shortages, combining the basic information of the equipment, historical usage, inventory shortage records, and maintenance records, and intelligently determines the equipment to be counted based on these probabilities. This module uses the equipment's historical usage and inventory records as prior probabilities, and uses the most recent inventory results and information such as equipment usage and maintenance as new evidence. By integrating this information, the probability of inventory shortages for each device is calculated. By using the Bayesian statistical method, the possibility of inventory shortages can be intelligently predicted based on the equipment's historical usage and inventory records, and a corresponding inventory plan can be generated, thereby improving the efficiency and accuracy of the inventory. The specific steps are as follows:

[0064] Establish a model - calculate the probability of inventory shortage: take the equipment's historical use and inventory records as the prior probability, and take the latest inventory results and equipment use, maintenance and other information as new evidence to establish a Bayesian statistical model. According to Bayes' theorem, use the prior probability and new evidence to calculate the posterior probability of each equipment inventory shortage. The calculation formula is as follows:

[0065] P(Deficiency|Evidence)=P(Eviendce|Deficiency)×P(Deficiency) / P(Evidence)

[0066] Among them, P(Deficiency|Evidence) represents the probability of a device shortage given the evidence; P(Eviendce|Deficiency) is the probability of observing specific evidence given the device shortage; P(Deficiency) is the prior probability of a device shortage; P(Evidence) is the prior probability of the observed evidence.

[0067] Set thresholds - determine which devices to count: Based on the posterior probability, set a threshold to determine which devices are considered likely to have inventory shortages. The threshold can be set based on actual needs and business rules. Based on the calculated posterior probability and the set threshold, an inventory plan is intelligently generated. Devices with a higher probability can be prioritized to reduce the risk of inventory shortages.

[0068] Furthermore, before evaluating the probability of inventory shortage of each device based on the basic information, historical usage, inventory shortage record and maintenance record of the device, and determining the device to be inventoried based on the probability of inventory shortage of each device, the device inventory counting method based on artificial intelligence provided in this embodiment also includes:

[0069] Establish equipment database, personnel database and inventory system database. Specifically include basic information of equipment (name, code, attribute, value, specification model, purchase time), basic information of inventory personnel (name, employee ID, job responsibilities) and inventory system (inventory work handover mechanism, inventory difference report form). And establish a cross-reference relationship between mobile equipment and fixed assets, and each equipment code corresponds to the asset code to unify equipment inventory and financial asset inventory. Lay a good data foundation for the smooth progress of subsequent inventory work;

[0070] Establishing a role-based, multi-level permission control system is a key measure to ensure the security of equipment inventory tasks and data confidentiality. Perform fine-grained permission management on system functions and data according to different user roles. Only authorized users can access system functions and data at different levels, effectively preventing unauthorized access. For example, only personnel with inventory permissions can access and modify equipment information, which ensures the integrity and accuracy of the data. At the same time, users at different levels are restricted to access only equipment information within their work scope, avoiding unnecessary information leakage and misoperation;

[0071] Encryption technology is used to encrypt the transmitted data, including sensitive device information such as serial number, model, location, etc., to prevent unauthorized access or tampering. To ensure the security of data transmission, specify the use of encrypted transmission protocols such as HTTPS, and determine the data format such as JSON or XML to ensure consistency. At the same time, technologies such as hash algorithms are used to ensure the integrity of the data transmission process and prevent potential security threats such as man-in-the-middle attacks or data tampering. With the introduction of elastic cloud services, the system can automatically adjust resources according to changes in data transmission load to ensure the stability and efficiency of transmission.

[0072] Connect with the financial system, human resources system, and supplier management system. The inventory system interacts with the financial system, and the corresponding asset inventory is completed after the corresponding equipment inventory is completed; the inventory system interacts with the centralized warehouse room in kind, and the mobile equipment that has been borrowed is counted by the equipment holding technicians, and the fixed equipment and non-borrowed mobile equipment are counted by the equipment warehouse management personnel;

[0073] When integrating with other systems, it is necessary to ensure the interoperability between systems, adopt standard data exchange formats such as XML and JSON, and provide APIs or other interfaces to facilitate system integration. During the physical delivery process, data should be automatically synchronized to the system to ensure data accuracy and real-time performance. At the same time, a real-time communication mechanism is introduced to ensure that each module in the system can work together in real time, reduce communication delays, and improve work efficiency. In addition, it is necessary to establish a distributed system architecture to ensure efficient collaboration between modules, while improving the scalability and stability of the system, so as to better support the smooth progress of equipment inventory tasks.

[0074] S202: Determine an inventory task according to the employee information and the equipment to be counted. The inventory task includes an inventory person and the equipment to be counted corresponding to the inventory person. The inventory person is an employee selected according to the employee information and the equipment to be counted.

[0075] In a specific optional implementation, determining the inventory task according to the employee information and the equipment to be inventory-checked includes:

[0076] For a device to be counted, according to the employee's current location in the employee information, an employee corresponding to the employee's current location whose distance to the device location is less than a preset distance threshold is selected as a candidate employee;

[0077] Determine the inventory personnel who will conduct the inventory of the equipment to be inventoried based on the skills and experience levels of the candidate employees recorded in the employee information.

[0078] S203: issuing an inventory task to the inventory personnel, and obtaining the task information uploaded by the inventory personnel, the task information including the equipment identification, equipment location and equipment photo.

[0079] Specifically, after the inventory notification is issued, the inventory personnel use the mobile terminal to scan the barcode label / QR code label / RFID label on the device, take photos of the device from multiple angles, and upload these photos to the system and submit them (during the inventory process, the mobile terminal determines the location of the inventory items at this time based on GPS positioning, and the inventory photos can only be taken by the camera and cannot be selected and uploaded from the album). The system uses deep learning-based object detection algorithms, such as YOLO, SSD, Faster R-CNN, etc. to detect devices in the captured images, determine the location and bounding box of the device in the image, and provide its location information in the image.

[0080] Among them, the inventory in this embodiment can be a spot inventory, or it can be based on the book inventory (mainly divided into: end-of-period inventory, regular inventory, cycle inventory, sampling inventory, temporary inventory), clarify the equipment list and the start and end time of the inventory; inventory personnel, verification personnel: determine the inventory personnel, monitoring personnel and sampling personnel, mainly composed of equipment managers, department heads, asset accountants, and auditors to form an inventory team, clarify the specific division of responsibilities and the coordination, reporting and handling mechanism of problems; inventory rules: conduct operational training for inventory personnel, establish inventory systems, inventory plans, work handover mechanisms, and inventory difference reporting forms, etc.

[0081] S204: Perform identification and prediction on the equipment photo to obtain an evaluation result of the current status of the equipment.

[0082] In a specific optional implementation, the device photo is identified and predicted to obtain the current status evaluation result of the device, including:

[0083] The input image is X, and the convolutional neural network model f-rows processing and feature extraction are used to obtain the feature representation h = f(X);

[0084] Use the fully connected layer to classify the features and obtain the current status evaluation result y of the equipment pred ,Right now:

[0085] y pred＝softmax(W ·h+b)

[0086] Among them, W and b are the weight and bias of the fully connected layer, and the softmax function is used to convert the prediction results into a probability distribution so that the sum of the probabilities of each category is 1.

[0087] Furthermore, after identifying the object, the software needs to search for the corresponding device in the enterprise device library. This process is usually implemented using text-based or image-based retrieval technology. For text retrieval, you can search in the database based on the category and attributes of the device. For image retrieval, you can use image similarity matching technology, such as image feature-based retrieval methods, to find mobile devices in the database that are similar to the shooting device. The inventory operation is completed after the inventory results are reviewed and approved by the regulatory department (such as the finance department or the audit department).

[0088] S205: The device location corresponding to the device identification and the device current status evaluation result are used as current device information, and the current device information is compared with the historical device information corresponding to the device identification stored in the database to determine the inventory result.

[0089] Furthermore, after determining the inventory results, it also includes four parts: equipment change information processing, surplus and shortage equipment processing, equipment ledger information update and intelligent data analysis report.

[0090] Equipment change information processing: When the physical inventory information is inconsistent with the book information, the equipment holder can submit an information change application in the system to request correction of the equipment information. The equipment supervisor and the financial department will review the information change of the equipment based on the application submitted by the inventory person and information such as photo scanning.

[0091] Equipment surplus or shortage processing: When equipment surplus or shortage occurs, organize relevant equipment users and equipment management personnel to find out the reason. The responsible person will describe the difference information in detail and submit it in the system for review and processing by the equipment supervisor and the financial department.

[0092] Equipment ledger information update: Based on the above equipment information changes and inventory surplus and shortage processing review results, the corresponding equipment basic information in the system equipment database is updated.

[0093] Intelligent analysis of inventory results: The backend management system uses anomaly detection algorithms to conduct in-depth mining and analysis of abnormal inventory data, and uses predictive models to predict future equipment inventory situations, helping users to promptly identify potential risks, issue warnings in a timely manner, and provide solutions to take corresponding measures, providing a reference for the formulation of subsequent inventory plans.

[0094] Furthermore, an inventory report is automatically generated based on the above inventory information and the processing of inventory results. The report can be customized according to user needs, providing important reference for enterprise decision-making and providing improvement suggestions for the current status and deficiencies of mobile device management. Data visualization technology is used to convert data into intuitive and easy-to-understand graphics and charts, so as to more vividly display the inventory results and provide deeper insights.

[0095] Mobile display: Use interactive visualization tools such as Plotly, Tableau, Power BI, etc. to create interactive charts and dashboards. Users can explore data, adjust perspectives, and view detailed information as needed through interactive operations, making the inventory results more dynamic and flexible. For some complex data or device models, consider using 3D visualization technology to display inventory results. By presenting data in three dimensions, it can provide more vivid and intuitive visual effects, attract users' attention, and enhance communication effects.

[0096] Dashboard display: Establish an executive management cockpit and design a special dashboard to display the inventory results. The dashboard contains a variety of charts and indicators, such as bar charts, line charts, pie charts, etc., as well as key inventory result indicators and trend analysis. Through the dashboard, you can understand the inventory situation at a glance and make decisions in a timely manner. In terms of geographic location information, GIS technology is used to display the geographical distribution of inventory results. Through map visualization, you can intuitively display the location distribution of equipment, the spatial distribution of inventory results and other information to help users better understand the inventory situation.

[0097] In this embodiment, based on the basic information, historical usage, inventory shortage record and maintenance record of the equipment, the probability of inventory shortage of each equipment is evaluated, and based on the probability of inventory shortage of each equipment, the equipment to be inventoried is determined; based on the employee information and the equipment to be inventoried, the inventory task is determined, and the inventory task includes the inventory personnel and the equipment to be inventoried corresponding to the inventory personnel, and the inventory personnel are employees selected according to the employee information and the equipment to be inventoried; the inventory task is issued to the inventory personnel, and the task information uploaded by the inventory personnel is obtained, and the task information includes the equipment identification, equipment location and equipment photos; the equipment photos are identified and predicted to obtain the evaluation result of the current status of the equipment; the equipment location corresponding to the equipment identification and the evaluation result of the current status of the equipment are used as the current equipment information, and the current equipment information is compared with the historical equipment information corresponding to the equipment identification stored in the database to determine the inventory result. The centralized management mode of mobile devices is realized, and the automation, efficiency and intelligence level of equipment inventory are improved by using intelligent means such as computer vision technology, machine learning, and deep learning.

[0098] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0099] Figure 3 The principle block diagram of the device inventory counting apparatus based on artificial intelligence is shown, which corresponds to the device inventory counting method based on artificial intelligence in the above embodiment. Figure 3 As shown, the artificial intelligence-based equipment inventory device includes an equipment determination module 31, a task generation module 32, a task execution module 33, an image recognition module 34 and a result evaluation module 35. The functional modules are described in detail as follows:

[0100] The equipment determination module 31 is used to evaluate the probability of each equipment being damaged by inventory based on the basic information, historical usage, inventory damage record and maintenance record of the equipment, and determine the equipment to be inventoried based on the probability of each equipment being damaged by inventory;

[0101] A task generation module 32 is used to determine an inventory task according to employee information and equipment to be inventoried, wherein the inventory task includes an inventory person and equipment to be inventoried corresponding to the inventory person, and the inventory person is an employee selected according to the employee information and equipment to be inventoried;

[0102] The task execution module 33 is used to issue the inventory task to the inventory personnel and obtain the task information uploaded by the inventory personnel. The task information includes the equipment identification, equipment location and equipment photo;

[0103] The image recognition module 34 is used to identify and predict the equipment photo to obtain the equipment current status assessment result;

[0104] The result evaluation module 35 is used to use the device location corresponding to the device identification and the device current status evaluation result as the current device information, and compare the current device information with the historical device information corresponding to the device identification stored in the database to determine the inventory result.

[0105] Optionally, the device determination module 31 includes:

[0106] A priori probability determination unit is used to establish a Bayesian statistical model by taking the equipment's historical use and inventory records as prior probabilities and the most recent inventory results and equipment use, maintenance and other information as new evidence;

[0107] The posterior probability calculation unit is used to calculate the posterior probability of each device being out of stock according to the Bayesian statistical model using the prior probability and new evidence as the probability of the device being out of stock.

[0108] Optionally, the device determination module 31 further includes:

[0109] A risk equipment list generating unit, used for generating a risk equipment list according to the probability of equipment inventory shortage and a preset probability threshold;

[0110] The equipment to be counted determining unit is used to determine the equipment to be counted based on the risk equipment list and business rules.

[0111] For the specific definition of the device inventory apparatus based on artificial intelligence, please refer to the definition of the device inventory method based on artificial intelligence above, which will not be repeated here. Each module in the above-mentioned device inventory apparatus based on artificial intelligence can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0112] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0113] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components connected to the memory 41, the processor 42, and the network interface 43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0114] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0115] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or D interface display memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as the program code of the device inventory method based on artificial intelligence, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0116] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run the program code stored in the memory 41 or process data, such as running the program code of the device inventory method based on artificial intelligence.

[0117] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0118] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores an interface display program, and the interface display program can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned artificial intelligence-based device inventory method.

[0119] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0120] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to replace some of the technical features therein with equivalents. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. An artificial intelligence-based equipment inventory method, characterized in that: include: Based on the basic information, historical usage, inventory shortage records and maintenance records of the equipment, the probability of inventory shortage for each equipment is evaluated, and based on the probability of inventory shortage for each equipment, the equipment to be counted is determined; Determine an inventory task according to the employee information and the equipment to be counted, wherein the inventory task includes an inventory person and the equipment to be counted corresponding to the inventory person, and the inventory person is an employee selected according to the employee information and the equipment to be counted; issuing the inventory task to the inventory personnel, and obtaining the task information uploaded by the inventory personnel, wherein the task information includes the equipment identification, equipment location and equipment photo; Performing identification and prediction on the equipment photo to obtain an evaluation result of the current state of the equipment; The device location corresponding to the device identification and the device current status evaluation result are used as current device information, and the current device information is compared with the historical device information corresponding to the device identification stored in the database to determine the inventory result.

2. The artificial intelligence-based device inventory method according to claim 1, characterized in that: The probability of inventory shortage of each device is evaluated based on the basic information, historical usage, inventory shortage record and maintenance record of the device, including: The Bayesian statistical model is established by taking the equipment's historical usage and inventory records as prior probabilities and the most recent inventory results and equipment usage, maintenance and other information as new evidence. According to the Bayesian statistical model, the posterior probability of each device being out of stock is calculated using the prior probability and new evidence as the probability of the device being out of stock.

3. The artificial intelligence-based device inventory method according to claim 1, characterized in that: The determining of the equipment to be counted based on the probability of shortage of each equipment includes: Generate a risky equipment list according to the probability of equipment shortage and a preset probability threshold; Based on the risk equipment list and business rules, the equipment to be counted is determined.

4. The artificial intelligence-based device inventory method according to claim 1, characterized in that: Determining the inventory task according to the employee information and the equipment to be inventory-checked includes: For a device to be counted, according to the employee current location in the employee information, an employee corresponding to the employee current location whose distance between the employee current location and the device location is less than a preset distance threshold is selected as a candidate employee; An inventory checker for the equipment to be checked is determined based on the skills and experience levels of the candidate employees recorded in the employee information.

5. The artificial intelligence-based device inventory method according to claim 1, characterized in that: The identification and prediction of the device photo to obtain the device current status evaluation result includes: The input image is X, and the convolutional neural network model f-rows processing and feature extraction are used to obtain the feature representation h = f(X); Use the fully connected layer to classify the features and obtain the current status evaluation result y of the equipment pred ,Right now: y pred＝softmax(W · h+b) Among them, W and b are the weight and bias of the fully connected layer, and the softmax function is used to convert the prediction results into a probability distribution so that the sum of the probabilities of each category is 1.

6. An artificial intelligence-based equipment inventory device, characterized in that: include: The equipment determination module is used to evaluate the probability of each equipment being lost based on the basic information, historical usage, loss records and maintenance records of the equipment, and determine the equipment to be counted based on the probability of each equipment being lost; A task generation module is used to determine the inventory task according to the employee information and the equipment to be counted. The inventory task includes the inventory personnel and the equipment to be counted corresponding to the inventory personnel. The inventory personnel are employees selected according to the employee information and the equipment to be counted. The task execution module is used to issue inventory tasks to inventory personnel and obtain task information uploaded by inventory personnel. The task information includes equipment identification, equipment location and equipment photos; Image recognition module, used to identify and predict equipment photos and obtain the equipment's current status assessment results; The result evaluation module is used to take the device location corresponding to the device identification and the device current status evaluation result as the current device information, and compare the current device information with the historical device information corresponding to the device identification stored in the database to determine the inventory result.

7. The artificial intelligence-based equipment inventory device according to claim 6, characterized in that: The device determination module includes: A priori probability determination unit is used to establish a Bayesian statistical model by taking the equipment's historical use and inventory records as prior probabilities and the most recent inventory results and equipment use, maintenance and other information as new evidence; The posterior probability calculation unit is used to calculate the posterior probability of each device being out of stock according to the Bayesian statistical model using the prior probability and new evidence as the probability of the device being out of stock.

8. The artificial intelligence-based equipment inventory device according to claim 6, characterized in that: The device determination module also includes: A risk equipment list generating unit, used for generating a risk equipment list according to the probability of equipment inventory shortage and a preset probability threshold; The equipment to be counted determining unit is used to determine the equipment to be counted based on the risk equipment list and business rules.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the artificial intelligence-based device inventory method as described in any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the artificial intelligence-based device inventory method as described in any one of claims 1 to 5 is implemented.

Images