Part change task time prediction method and device

Abstract

The invention provides a part change task time prediction method and device, and the method comprises the steps: receiving a prediction request of a target part change task, and enabling the prediction request to carry target change starting time; according to a distribution function obtained through fitting, the prediction time interval of the target part change task is determined, and the distribution function is obtained through fitting based on the sample change starting time of the sample part change task and the sample part library-to-library time; and according to the prediction time interval and the target change starting time, predicting the target part library arrival time of the target part change task. Therefore, the distribution function obtained by fitting the sample data is utilized, the prediction of the time of the target part to the library is automatically realized, the prediction efficiency and accuracy are improved, the data volume required for fitting the distribution function is relatively small, the requirement on the sample data volume is reduced, the time prediction can be quickly realized, and the usability in industrial production is improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle manufacturing technology, and more particularly to a method for predicting the time of a part change task. The present invention also relates to a device for predicting the time of a part change task, a computing device, and a computer-readable storage medium. Background Art

[0002] The production and manufacturing process of vehicles involves a large number of parts change tasks. For parts change tasks, it is necessary to predict the arrival time of parts in order to receive parts or arrange vehicle production and manufacturing plans. At present, experts often predict the time of parts change tasks based on production line engineering personnel and business requirements. Experts need to spend a lot of time analyzing parts change tasks and make time predictions based on their own experience. They rely heavily on their own experience and cannot make differentiated predictions for different change tasks. This is inefficient and inaccurate, and extremely labor-intensive. Summary of the invention

[0003] In view of this, the embodiment of this specification provides a method for predicting the time of a part change task. This specification also relates to a time prediction device for a part change task, a computing device, and a computer-readable storage medium to solve the technical defects existing in the prior art.

[0004] According to a first aspect of an embodiment of this specification, a time prediction method for a part change task is provided, comprising:

[0005] Receiving a prediction request for a target part change task, wherein the prediction request carries a target change start time;

[0006] Determine the predicted time interval of the target part change task according to the distribution function obtained by fitting, wherein the distribution function is obtained by fitting based on the sample change start time of the sample part change task and the sample part arrival time;

[0007] The target part arrival time of the target part change task is predicted according to the predicted time interval and the target change start time.

[0008] According to a second aspect of an embodiment of this specification, a time prediction device for a part change task is provided, comprising:

[0009] A receiving module is configured to receive a prediction request for a target part change task, wherein the prediction request carries a target change start time;

[0010] A determination module is configured to determine the predicted time interval of the target part change task according to a distribution function obtained by fitting, wherein the distribution function is obtained by fitting based on a sample change start time and a sample part arrival time of the sample part change task;

[0011] The prediction module is configured to predict the target part arrival time of the target part change task according to the prediction time interval and the target change start time.

[0012] According to a third aspect of an embodiment of this specification, a computing device is provided, including:

[0013] Memory and processor;

[0014] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement the steps of the time prediction method for the part change task.

[0015] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the time prediction method for the part change task are implemented.

[0016] The time prediction method for a part change task provided in an embodiment of the present specification receives a prediction request for a target part change task, wherein the prediction request carries a target change start time; determines a prediction time interval for the target part change task based on a fitted distribution function, wherein the distribution function is fitted based on a sample change start time and a sample part arrival time of a sample part change task; and predicts a target part arrival time for the target part change task based on the prediction time interval and the target change start time.

[0017] An embodiment of the present specification realizes the pre-fitting of the distribution function based on the sample change start time and the sample part arrival time of the sample part change task. When receiving the prediction request of the target part change task, the prediction time interval of the target part change task is determined according to the distribution function obtained by fitting, and then the target part arrival time of the target part change task is predicted according to the prediction time interval and the target change start time carried by the prediction request. In this way, the distribution function is fitted based on the sample change start time and the sample part arrival time of the sample part change task, and the prediction time interval is obtained through the distribution function to predict the target part arrival time of the target part change task. The distribution function obtained by fitting based on the sample data is used to automatically realize the prediction of the target part arrival time of the target part change task, thereby improving the prediction efficiency and accuracy. Moreover, the amount of data required for fitting the distribution function is small, which reduces the requirement for the amount of sample data, and can quickly realize time prediction, thereby increasing the usability in industrial production. In addition, any change task can fit the distribution function to realize time prediction, and differentiated predictions can be made for different change tasks, which is suitable for different change tasks and has strong adaptability to business. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flow chart of a method for predicting the time of a part change task provided in an embodiment of this specification;

[0019] Figure 2 It is a parts to library summary diagram provided in an embodiment of this specification;

[0020] Figure 3 It is a processing flow chart of a time prediction method for a parts change task applied to a vehicle production scenario provided in an embodiment of this specification;

[0021] Figure 4 It is a structural schematic diagram of a time prediction device for a part change task provided in an embodiment of this specification;

[0022] Figure 5 It is a structural block diagram of a computing device provided in one embodiment of this specification. DETAILED DESCRIPTION

[0023] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0024] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0025] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0026] First, the terms involved in one or more embodiments of this specification are explained.

[0027] It should be noted that the production and manufacturing process of vehicles involves a large number of parts change tasks. For the parts change tasks, it is necessary to predict the arrival time of the parts in order to receive the parts or arrange the production and manufacturing plan of the vehicle.

[0028] At present, experts often predict the time for part change tasks based on production line engineering personnel and business requirements. Experts need to spend a lot of time analyzing part change tasks and make time predictions based on their own experience. They rely heavily on the experts' own experience and cannot make differentiated predictions for different change tasks. This results in low efficiency and accuracy, and is extremely labor-intensive.

[0029] Alternatively, it is also possible to train a machine learning / deep learning time prediction model based on the industrial production time from a large-scale data source of the vehicle production process, and use the trained time prediction model to predict the arrival time of the part change task.

[0030] However, the time prediction model of machine learning / deep learning often requires a large amount of training data and has high requirements for training data. It is a big data model and is more suitable for time prediction in the Internet big data scenario. In the vehicle production and manufacturing scenario, the time information is relatively simple and the amount of data is small, which makes it difficult to meet the data requirements for model training. Complex time prediction models such as machine learning / deep learning often have high requirements for data volume and data items, require long-term, large-scale industrial production data, have a slow training process, low efficiency and high cost, are difficult to use directly in industry, and have poor scalability.

[0031] Therefore, the embodiment of the specification provides a method for predicting the time of a part change task, which realizes the distribution function obtained by fitting the sample change start time and the sample part arrival time of the sample part change task in advance, and when receiving the prediction request of the target part change task, the prediction time interval of the target part change task is determined according to the distribution function obtained by fitting, and then the target part arrival time of the target part change task is predicted according to the prediction time interval and the target change start time carried by the prediction request. In this way, the distribution function is fitted based on the sample change start time and the sample part arrival time of the sample part change task, and the prediction time interval is obtained by the distribution function to predict the target part arrival time of the target part change task. The distribution function obtained by fitting based on the sample data is used to automatically predict the target part arrival time of the target part change task, thereby improving the prediction efficiency and accuracy, and the amount of data required for fitting the distribution function is small, which reduces the requirement for the amount of sample data, can quickly realize time prediction, and increase the usability in industrial production; in addition, any change task can fit the distribution function to realize time prediction, and can achieve differentiated prediction for different change tasks, which is suitable for different change tasks and has strong adaptability to business.

[0032] In this specification, a time prediction method for a part change task is provided. This specification also relates to a time prediction device for a part change task, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0033] Figure 1 102 is a flowchart of a method for predicting the time of a part change task provided by an embodiment of the present specification, which specifically includes the following steps 102-106:

[0034] Step 102: Receive a prediction request for a target part change task, wherein the prediction request carries a target change start time.

[0035] Specifically, a part change task refers to a task of obtaining and changing vehicle-related parts, which are parts required for the production process of the vehicle. A target part change task is any part change task initiated by a staff member, such as a task to obtain part A of a vehicle. A prediction request refers to a request to predict the arrival time of the parts of the target part change task, and the target change start time refers to the start time of the target part change task, that is, the application trigger time of the target part change task.

[0036] It should be noted that when making a part change, you need to first submit a request for the part change task. After approval, the corresponding parts will be issued. There is often a certain interval between the change start time and the final part arrival time. In order to receive parts or arrange vehicle production and manufacturing plans, etc., it is necessary to predict the part arrival time of the part change task.

[0037] For example, a staff member needs to obtain part A. After submitting it for approval, part A arrives at the warehouse on October 5th. However, the staff is on vacation on October 5th, so part A cannot be put into the warehouse. Or, part A needs to be installed first and then task B is performed. Without knowing the arrival time of part A, it is impossible to prepare the labor, equipment and other materials required to perform task B. The staff can only wait until part A arrives at the warehouse before preparing the labor, equipment and other materials required to perform task B. This will seriously affect the production efficiency of the vehicle. Therefore, when applying for part A, it is necessary to predict its arrival time in order to receive the parts or arrange the vehicle's production and manufacturing plan, etc., to ensure the normal production and manufacturing of the vehicle.

[0038] In actual applications, when a staff member initiates a part change task, the part change task is the target part change task, and a prediction request can be automatically initiated to the prediction platform. At this time, the prediction platform receives the prediction request for the target part change task, which carries the target change start time. Subsequently, the target part arrival time can be predicted based on the target change start time carried in the prediction request.

[0039] In an optional implementation of this embodiment, in order to facilitate the prediction of the arrival time of the target part in the warehouse, a distribution function may be fitted based on sample data in advance, that is, before receiving the prediction request for the target part change task, the following may be included:

[0040] Acquire sample data of multiple sample part change tasks, wherein the sample data includes a sample change start time and a sample part arrival time;

[0041] Determine the time difference between the sample change start time of the first sample data and the sample part arrival time, and use the time difference as the first sample change time difference corresponding to the first sample part change task, wherein the first sample data is the sample data of the first sample part change task, and the first sample part change task is any one of the multiple sample part change tasks;

[0042] According to the sample change time difference corresponding to each sample part change task, a distribution function is fitted.

[0043] Specifically, a sample part change task refers to a task that can be used as a sample for fitting a distribution function. The sample data of the sample part change task may include a sample change start time and a sample part arrival time in the warehouse, wherein the sample change start time refers to the application time for the sample part change task, and the sample part arrival time in the warehouse refers to the actual arrival time of the target part corresponding to the sample part change task.

[0044] In addition, the distribution function is an important function in probability statistics. Through the distribution function, the random variable can be studied by mathematical analysis. The distribution function is the most important probability feature of the random variable. The distribution function can fully describe the statistical law of the random variable and determine all other probability features of the random variable. The distribution function can be a Poisson distribution, a binomial distribution, a normal distribution, etc. The distribution function obtained by fitting in the embodiment of this specification can be used to represent the probability of the time interval between the change opening time and the time when the parts arrive at the warehouse.

[0045] It should be noted that the more sample part change tasks there are, the more accurate the distribution function obtained by fitting will be and the closer it will be to the actual scenario. However, the amount of calculation will also increase accordingly. In specific implementation, the required number of sample part change tasks can be set based on actual needs.

[0046] In practical applications, one can be randomly selected from multiple sample part change tasks as the first sample part change task, and the first task data of the first sample part change task can be obtained. The task data may include multiple data items, such as task attributes, time, remarks and other data items. The time item is obtained from the first task data, and the time item is used as the sample data, that is, the sample data includes the sample change start time and the sample part arrival time. Then, the time difference between the sample change start time and the sample part arrival time of the first sample data is determined, and the time difference is used as the first sample change time difference corresponding to the first sample part change task. By analogy, any sample part change task among multiple sample part change tasks can be used as the first sample part change task, and the corresponding first sample change time difference is obtained based on its corresponding first sample data. In this way, the sample change time difference corresponding to each sample part change task can be obtained, and the distribution function can be fitted based on the sample change time difference corresponding to each sample part change task.

[0047] For example, assuming that there are 5 sample part change tasks, the sample data of sample part change task 1 includes the sample change start time January 1, and the sample part arrival time February 5; the sample data of sample part change task 2 includes the sample change start time January 7, and the sample part arrival time February 26; the sample data of sample part change task 3 includes the sample change start time March 1, and the sample part arrival time April 9; the sample data of sample part change task 4 includes the sample change start time March 1, and the sample part arrival time April 5; the sample data of sample part change task 5 includes the sample change start time April 7, and the sample part arrival time May 1. The sample change time difference corresponding to sample part change task 1 is 36 days, the sample change time difference corresponding to sample part change task 2 is 40 days, the sample change time difference corresponding to sample part change task 3 is 40 days, the sample change time difference corresponding to sample part change task 4 is 36 days, and the sample change time difference corresponding to sample part change task 5 is 24 days.

[0048] In the specific implementation, it is assumed that the sample change time difference corresponding to each sample part change task follows the corresponding distribution, and the sample change time difference is used as the only variable to fit the distribution function.

[0049] In the embodiment of this specification, sample data of multiple sample part change tasks can be obtained, and the sample change time difference corresponding to each sample part change task can be obtained based on the sample data, and then a distribution function can be obtained based on the fitting of each sample change time difference. The distribution function can represent the probability of the time interval between the change start time and the part arrival time, so as to facilitate the subsequent prediction of the part arrival time of the part change task based on the distribution function obtained by fitting. In addition, the amount of data required for fitting the distribution function is small, which reduces the requirement for the amount of sample data, can quickly realize time prediction, and increases the usability in industrial production; in addition, any change task can fit the distribution function to realize time prediction, and can achieve differentiated prediction for different change tasks, which is suitable for different change tasks and has strong adaptability to business.

[0050] In an optional implementation of this embodiment, a set proportion of tasks may be obtained from historical part change tasks as sample part change tasks, that is, sample data of multiple sample part change tasks may be obtained, including:

[0051] Obtain historical part change tasks, and select multiple sample part change tasks from the historical part change tasks;

[0052] Task data corresponding to multiple sample part change tasks are obtained, and time items in the task data are used as sample data.

[0053] Specifically, historical part change tasks refer to part change tasks that have been completed before the current time. For historical part change tasks, the change start time and the part arrival time can be accurately known. Therefore, a part of the historical part change tasks can be selected as sample part change tasks to fit the distribution function.

[0054] In practical applications, the proportion of sample part change tasks to historical part change tasks can be set in advance, and then tasks of the set proportion can be selected from the historical part change tasks as sample part change tasks, and task data corresponding to the sample part change tasks can be obtained. The time items in the task data can be used as sample data, and the time items include the change start time and the part arrival time, so as to fit the distribution function corresponding to the time difference between the change start time and the part arrival time. For example, if the set proportion is 80%, 80% of the tasks can be randomly selected from the historical part change tasks as sample part change tasks, and the distribution function can be fitted.

[0055] It should be noted that sample part change tasks can be screened from historical part change tasks, and based on the change start time and the actual part arrival time in the historical part change tasks that have been executed, a distribution function that follows the time difference between the change start time and the actual part arrival time can be fitted, thereby facilitating the subsequent prediction of the part arrival time of the part change task based on the fitted distribution function.

[0056] In an optional implementation of this embodiment, test data may be selected from historical part change tasks to perform regression testing on the distribution function obtained by fitting, that is, after selecting multiple sample part change tasks from historical part change tasks, the method further includes:

[0057] Other tasks in the historical part change tasks except the sample part change task are used as test tasks;

[0058] Accordingly, according to the sample change time difference corresponding to each sample part change task, after fitting the distribution function, it also includes:

[0059] The distribution function obtained by fitting is tested according to the test data of the test task, wherein the test data includes the test change start time and the test part arrival time;

[0060] If the test passes, the fitted distribution function is obtained.

[0061] It should be noted that a set proportion of tasks can be selected from the historical part change tasks as sample part change tasks, and then the remaining historical part change tasks can be used as test tasks. Based on the test data of the test tasks, the distribution function obtained by fitting is tested to verify the fitting result of the distribution function. For example, 80% of the historical part change tasks can be used as sample part change tasks, and the remaining 20% ​​can be used as test tasks.

[0062] In practical applications, the test data of the test task can be determined, and the test data includes the test change start time and the test part arrival time. For the first test data of the first test task, the time difference between the test change start time and the test part arrival time is determined, and the test change time difference corresponding to the first test task is obtained. By analogy, each test task can be used as the first test task, and the corresponding test change time difference is obtained. The average value of the test change time differences corresponding to each test task is determined, and the average value is used as the true value.

[0063] Then, based on the fitted distribution function, determine the initial time interval, which refers to the initial prediction time interval determined based on the distribution function, that is, the initial time interval is the prediction value. Based on the true value and the prediction value, determine the error value of the distribution function, and judge whether the error value meets the regression evaluation index MAE (mean absolute error). The regression evaluation index MAE can be set in advance, such as setting MAE to 3.9 days. If the error value of the calculated distribution function is greater than the regression evaluation index MAE, it means that the accuracy of the distribution function obtained by fitting is poor, and adjustment or refitting is required, and the test fails; if the error value of the calculated distribution function is not greater than the regression evaluation index MAE, it means that the accuracy of the distribution function obtained by fitting is good, and no adjustment or refitting is required. The test passes, and it can be determined that the final fitted distribution function is obtained.

[0064] In an embodiment of the present specification, other tasks in the historical part change tasks except the sample part change tasks can be used as test tasks. Based on the change start time and the actual part arrival time in the historical part change tasks that have been executed, the initially fitted distribution function is tested to verify the prediction accuracy of the distribution function. If the test fails, the distribution function can be adjusted or re-fitted. If the test passes, the final distribution function is obtained, which improves the accuracy of the fitted distribution function and thereby ensures the prediction accuracy of the part arrival time.

[0065] In an optional implementation of this embodiment, the distribution function is a Poisson distribution, and the distribution function is fitted according to the sample change time difference corresponding to each sample part change task, including:

[0066] Determine the variance of the sample change time difference corresponding to each sample part change task;

[0067] Fit a Poisson distribution to the variance.

[0068] It should be noted that it is assumed that the sample change time difference corresponding to each sample part change task follows a Poisson distribution. In specific implementation, the variance of the sample change time difference corresponding to each sample part change task can be determined, and the variance is used as the parameter λ of the Poisson distribution. The sample change time difference is used as the only variable to fit the Poisson distribution, and the sample change time difference is said to follow a Poisson distribution with parameter λ.

[0069] In addition, the mean and variance of the Poisson distribution are equal, and are both the parameter λ of the Poisson distribution. The variance is used as an example for explanation in the embodiments of this specification.

[0070] In practical applications, the Poisson distribution is shown in the following formula (1):

[0071]

[0072] Wherein, k represents the value of the variable, i.e., the sample change time difference; λ is the parameter of the Poisson distribution, i.e., the variance of the sample change time difference corresponding to each sample part change task; P{X=k} represents the probability that X is equal to k.

[0073] In the embodiments of this specification, it is assumed that the sample change time difference corresponding to each sample part change task obeys the Poisson distribution, and the Poisson distribution is used to fit the probability of the time interval between the change start time and the part arrival time. The required amount of data is small, which reduces the requirement for the sample data volume, can quickly realize time prediction, and increases the usability in industrial production. In addition, any change task can be fitted with the Poisson distribution to realize time prediction, and differentiated predictions can be made for different change tasks, which is suitable for different change tasks and has strong adaptability to business.

[0074] Step 104: Determine the predicted time interval of the target part change task according to the distribution function obtained by fitting, wherein the distribution function is obtained by fitting based on the sample change start time and the sample part arrival time of the sample part change task.

[0075] It should be noted that a distribution function can be obtained by fitting the sample change start time and the sample part arrival time of the sample part change task. This distribution function can indicate the probability of occurrence of the time interval between the change start time and the part arrival time. Therefore, the predicted time interval of the target part change task can be determined based on the distribution function obtained by fitting.

[0076] In an optional implementation of this embodiment, determining the predicted time interval of the target part change task according to the distribution function obtained by fitting includes:

[0077] Determine the reference time from the distribution function obtained by fitting according to a set rule;

[0078] Based on the reference time, determine the predicted time interval for the part change task.

[0079] In practical applications, the setting rules may be selection rules pre-set based on actual business needs, and the setting rules are used to select a target point as a reference time from the distribution function obtained by fitting. For example, the distribution function is obtained by fitting the sample change start time and the sample part arrival time of the sample part change task. The distribution function has an extreme point, and the setting rule may be to select the extreme point as the reference time. At this time, the reference time determined refers to the time interval with the highest probability of occurrence; or, the setting rule may also be to determine the total probability before the extreme point, and select the target point as the reference time based on the total probability, such as selecting the point with the total probability closest to 0.5 near the extreme point on the distribution function as the reference time. Of course, in actual implementation, other selection rules may also be set based on actual business needs, and the embodiments of this specification do not limit this.

[0080] In specific implementation, after determining the reference time from the distribution function obtained by fitting, the reference time can be directly used as the predicted time interval determined based on the distribution function; or, the standard deviation corresponding to the distribution function can be determined, and the standard deviation can be added or subtracted from the reference time to obtain the final predicted time interval. Of course, in practical applications, other calculations can also be performed based on the determined reference time to determine the predicted time interval of the part change task, and this specification does not limit this.

[0081] In the embodiments of the present specification, the predicted time interval between the change start time and the part arrival time can be determined based on the distribution function obtained by fitting, so as to facilitate the subsequent prediction of the target part arrival time of the target part change task based on the predicted time interval, automatically realize the prediction of the arrival time, and improve the prediction efficiency and accuracy.

[0082] Step 106: According to the prediction time interval and the target change start time, the target part arrival time of the target part change task is predicted.

[0083] It should be noted that the predicted time interval refers to the time interval between the change start time and the part arrival time predicted based on the distribution function. Therefore, the predicted time interval can be added to the target change start time to obtain the predicted target part arrival time of the target part change task, and the arrival time can be automatically predicted, thereby improving the prediction efficiency and accuracy.

[0084] An optional implementation of this embodiment may also count the parts arriving at the warehouse at different times based on the predicted arrival time of the parts, that is, after predicting the arrival time of the target parts of the target part change task according to the predicted time interval and the target change start time, the method further includes:

[0085] Determine the part change tasks to be counted with the target time for the parts to arrive at the warehouse;

[0086] Count the number of parts change tasks to be counted;

[0087] Based on the number of part change tasks to be counted, draw and display the parts arrival summary diagram corresponding to the target time.

[0088] It should be noted that the target time is any time that needs to be counted, which can be any day. For the target time, the part change tasks to be counted whose part arrival time is the target time can be determined, and then the number of part change tasks to be counted can be counted. According to the number of part change tasks to be counted, a summary diagram of parts arrival corresponding to the target time can be drawn and displayed, so that users can view and manage each part change task conveniently.

[0089] In actual applications, in addition to counting the part change tasks whose arrival time is the target time, the number of part change tasks whose change start time is the target time and the number of parts that have actually arrived at the warehouse can also be counted for the target time. Of course, other parameters can also be counted for the target time and displayed to the user so that the user can understand the status of each part change task in a timely manner, and this manual does not limit this.

[0090] The parts-to-warehouse summary graph may be a line graph, a bar graph, a text graph, etc., or may be a combination of multiple shapes.

[0091] In addition, each time can be used as a target time for statistics. After the statistics are completed, each time can be drawn as a time series summary chart to obtain the statistical parameters corresponding to each time. After selecting a time, the detailed statistical parameters of the time will be displayed. The statistical parameters may include the number of part change tasks opened, the number of parts actually arriving at the warehouse, the number of parts predicted to arrive at the warehouse, etc.

[0092] As an example, Figure 2 This is a parts to library summary diagram provided in an embodiment of this specification, such as Figure 2As shown in the figure, the statistical parameters of each date form a line chart, which includes the corresponding lines of the number of parts change tasks opened, the number of parts actually arriving in the warehouse, and the number of parts predicted to arrive in the warehouse. After the staff clicks to select a date, the detailed arrival data of that date is displayed. For example, if 2023-01-01 is selected, the number of parts change tasks opened on that date is 406, the number of parts actually arriving in the warehouse is 22, and the number of parts predicted to arrive in the warehouse is 377.

[0093] The time prediction method for part change tasks provided in the embodiment of the present specification realizes the distribution function obtained by fitting the sample change start time and the sample part arrival time of the sample part change task in advance. When receiving the prediction request of the target part change task, the prediction time interval of the target part change task is determined according to the distribution function obtained by fitting, and then the target part arrival time of the target part change task is predicted according to the prediction time interval and the target change start time carried by the prediction request. In this way, the distribution function is fitted based on the sample change start time and the sample part arrival time of the sample part change task, and the prediction time interval is obtained through the distribution function to predict the target part arrival time of the target part change task. The distribution function obtained by fitting based on the sample data is used to automatically predict the target part arrival time of the target part change task, thereby improving the prediction efficiency and accuracy. Moreover, the amount of data required for fitting the distribution function is small, which reduces the requirement for the amount of sample data, and can quickly realize time prediction, thereby increasing the usability in industrial production. In addition, any change task can fit the distribution function to realize time prediction, and differentiated predictions can be made for different change tasks, which is suitable for different change tasks and has strong adaptability to business.

[0094] The following combination Figure 3 Taking the application of the time prediction method for part change tasks provided in this specification in the vehicle production scenario as an example, the time prediction method for part change tasks is further explained. Figure 3 This is a processing flow chart of a time prediction method for a part change task applied to a vehicle production scenario provided in an embodiment of this specification, which specifically includes the following steps:

[0095] Step 302: Obtain historical part change tasks of vehicle production, select a set proportion of sample part change tasks from the historical part change tasks, and use other tasks in the historical part change tasks except the sample part change tasks as test tasks.

[0096] Step 304: Obtain the task data corresponding to the sample part change task, and use the time item in the task data as sample data, where the sample data includes the sample change start time and the sample part arrival time.

[0097] Step 306: Determine the time difference between the sample change start time of the first sample data and the sample part arrival time, and use the time difference as the first sample change time difference corresponding to the first sample part change task.

[0098] Step 308: Obtain the sample change time difference corresponding to each sample part change task, determine the variance of the sample change time difference corresponding to each sample part change task, and fit a Poisson distribution according to the variance.

[0099] Step 310: Test the fitted Poisson distribution based on the test data of the test task, where the test data includes the test change start time and the test part arrival time; if the test passes, obtain the fitted Poisson distribution.

[0100] Step 312: Receive a prediction request for a target part change task during the production process of a target vehicle, where the prediction request carries a target change start time.

[0101] Step 314: Determine the reference time corresponding to the extreme point of the Poisson distribution obtained by fitting, and use the reference time as the predicted time interval of the part change task.

[0102] Step 316: Add a prediction time interval to the target change start time to predict the target part arrival time of the target part change task.

[0103] Step 318: Determine the statistical parameters of the target time, which include the number of part change tasks opened, the number of parts actually arriving at the warehouse, and the number of parts predicted to arrive at the warehouse.

[0104] Step 320: Generate and display a time series summary graph of the statistical parameters based on the statistical parameters at each time.

[0105] The time prediction method for part change tasks provided in the embodiment of the present specification realizes the pre-fitting of the sample change start time and the sample part arrival time of the sample part change task to obtain the Poisson distribution. When receiving the prediction request of the target part change task, the prediction time interval of the target part change task is determined according to the fitted Poisson distribution, and then the target part arrival time of the target part change task is predicted according to the predicted time interval and the target change start time carried by the prediction request. In this way, the Poisson distribution is fitted based on the sample change start time and the sample part arrival time of the sample part change task, and the prediction time interval is obtained through the Poisson distribution to predict the target part arrival time of the target part change task. The Poisson distribution obtained by fitting based on the sample data is used to automatically predict the target part arrival time of the target part change task, thereby improving the prediction efficiency and accuracy. The amount of data required for fitting the Poisson distribution is small, which reduces the requirement for the amount of sample data, can quickly realize time prediction, and increase the usability in industrial production. In addition, any change task can fit the Poisson distribution to realize time prediction, and differentiated predictions can be made for different change tasks, which is suitable for different change tasks and has strong adaptability to business.

[0106] Corresponding to the above method embodiment, this specification also provides an embodiment of a time prediction device for a part change task, Figure 4 1 is a schematic diagram of a time prediction device for a part change task provided in an embodiment of this specification. Figure 4 As shown, the device comprises:

[0107] The receiving module 402 is configured to receive a prediction request for a target part change task, wherein the prediction request carries a target change start time;

[0108] A determination module 404 is configured to determine a predicted time interval of a target part change task according to a distribution function obtained by fitting, wherein the distribution function is obtained by fitting based on a sample change start time and a sample part arrival time of a sample part change task;

[0109] The prediction module 406 is configured to predict the target part arrival time of the target part change task according to the prediction time interval and the target change start time.

[0110] Optionally, the device further comprises a fitting module configured to:

[0111] Acquire sample data of multiple sample part change tasks, wherein the sample data includes a sample change start time and a sample part arrival time;

[0112] Determine the time difference between the sample change start time of the first sample data and the sample part arrival time, and use the time difference as the first sample change time difference corresponding to the first sample part change task, wherein the first sample data is the sample data of the first sample part change task, and the first sample part change task is any one of the multiple sample part change tasks;

[0113] According to the sample change time difference corresponding to each sample part change task, a distribution function is fitted.

[0114] Optionally, the fitting module is further configured to:

[0115] Obtain historical part change tasks, and select multiple sample part change tasks from the historical part change tasks;

[0116] Task data corresponding to multiple sample part change tasks are obtained, and time items in the task data are used as sample data.

[0117] Optionally, the fitting module is further configured to:

[0118] Other tasks in the historical part change tasks except the sample part change task are used as test tasks;

[0119] Accordingly, the device further comprises a testing module configured to:

[0120] The distribution function obtained by fitting is tested according to the test data of the test task, wherein the test data includes the test change start time and the test part arrival time;

[0121] If the test passes, the fitted distribution function is obtained.

[0122] Optionally, the distribution function is Poisson distribution; the fitting module is further configured as follows:

[0123] Determine the variance of the sample change time difference corresponding to each sample part change task;

[0124] Fit a Poisson distribution to the variance.

[0125] Optionally, the determination module 404 is further configured to:

[0126] Determine the reference time from the distribution function obtained by fitting according to a set rule;

[0127] Based on the reference time, determine the predicted time interval for the part change task.

[0128] Optionally, the device further includes a statistical module configured to:

[0129] Determine the part change tasks to be counted with the target time for the parts to arrive at the warehouse;

[0130] Count the number of parts change tasks to be counted;

[0131] Based on the number of part change tasks to be counted, draw and display the parts arrival summary diagram corresponding to the target time.

[0132] The time prediction method for part change tasks provided in the embodiment of the present specification realizes the distribution function obtained by fitting the sample change start time and the sample part arrival time of the sample part change task in advance. When receiving the prediction request of the target part change task, the prediction time interval of the target part change task is determined according to the distribution function obtained by fitting, and then the target part arrival time of the target part change task is predicted according to the prediction time interval and the target change start time carried by the prediction request. In this way, the distribution function is fitted based on the sample change start time and the sample part arrival time of the sample part change task, and the prediction time interval is obtained through the distribution function to predict the target part arrival time of the target part change task. The distribution function obtained by fitting based on the sample data is used to automatically predict the target part arrival time of the target part change task, thereby improving the prediction efficiency and accuracy. Moreover, the amount of data required for fitting the distribution function is small, which reduces the requirement for the amount of sample data, and can quickly realize time prediction, thereby increasing the usability in industrial production. In addition, any change task can fit the distribution function to realize time prediction, and differentiated predictions can be made for different change tasks, which is suitable for different change tasks and has strong adaptability to business.

[0133] The above is a schematic scheme of a time prediction device for a part change task of this embodiment. It should be noted that the technical scheme of the time prediction device for a part change task and the technical scheme of the time prediction method for a part change task described above belong to the same concept. For details not described in detail in the technical scheme of the time prediction device for a part change task, please refer to the description of the technical scheme of the time prediction method for a part change task described above.

[0134] Figure 5 The structure block diagram of a computing device provided according to an embodiment of the present specification is shown. The components of the computing device 500 include but are not limited to a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and the database 550 is used to store data.

[0135] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface card (NIC)) of wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0136] In one embodiment of the present specification, the above components of the computing device 500 and Figure 5 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 5 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0137] The computing device 500 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. The computing device 500 may also be a mobile or stationary server.

[0138] The processor 520 is used to execute the following computer executable instructions to implement the steps of the time prediction method for the above-mentioned part change task.

[0139] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the time prediction method of the above-mentioned part change task belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the time prediction method of the above-mentioned part change task.

[0140] An embodiment of the present specification also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, are used to implement the steps of the time prediction method for the above-mentioned part change task.

[0141] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the time prediction method of the above-mentioned part change task belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the time prediction method of the above-mentioned part change task.

[0142] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0143] Computer instructions include computer program codes, which may be in source code form, object code form, executable files, or some intermediate form, etc. Computer readable media may include: any entity or device capable of carrying computer program codes, recording media, USB flash drives, mobile hard disks, magnetic disks, optical disks, computer memories, read-only memories (ROM), random access memories (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0144] It should be noted that, for the convenience of description, the aforementioned method embodiments are all described as a series of action combinations, but those skilled in the art should be aware that this specification is not limited by the order of the actions described, because according to this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this specification.

[0145] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0146] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A time prediction method for a part change task, characterized in that: The method comprises: Receiving a prediction request for a target part change task, wherein the prediction request carries a target change start time; Determine the predicted time interval of the target part change task according to the distribution function obtained by fitting, wherein the distribution function is obtained by fitting based on the sample change start time of the sample part change task and the sample part arrival time; The target part arrival time of the target part change task is predicted according to the predicted time interval and the target change start time.

2. The time prediction method for a part change task according to claim 1, characterized in that: Before receiving the prediction request for the target part change task, the method further includes: Acquire sample data of a plurality of sample part change tasks, wherein the sample data includes a sample change start time and a sample part arrival time; Determine a time difference between a sample change start time of the first sample data and a sample part arrival time, and use the time difference as a first sample change time difference corresponding to a first sample part change task, wherein the first sample data is sample data of the first sample part change task, and the first sample part change task is any one of the multiple sample part change tasks; According to the sample change time difference corresponding to each sample part change task, a distribution function is fitted.

3. The time prediction method for a part change task according to claim 2, characterized in that: The obtaining of sample data of a plurality of sample part change tasks includes: Acquire historical part change tasks, and select the plurality of sample part change tasks from the historical part change tasks; The task data corresponding to the plurality of sample part change tasks are acquired, and the time item in the task data is used as the sample data.

4. The time prediction method for a part change task according to claim 3 is characterized in that: After selecting the plurality of sample part change tasks from the historical part change tasks, the method further includes: Using other tasks in the historical part change tasks except the sample part change task as test tasks; Accordingly, after fitting the distribution function according to the sample change time difference corresponding to each sample part change task, the method further includes: Testing the distribution function obtained by fitting according to the test data of the test task, wherein the test data includes the test change start time and the test part arrival time; If the test passes, the fitted distribution function is obtained.

5. The time prediction method for a part change task according to claim 2, characterized in that: The distribution function is a Poisson distribution; the distribution function is fitted according to the sample change time difference corresponding to each sample part change task, including: Determining the variance of the sample change time difference corresponding to each sample part change task; A Poisson distribution is fit according to the variance.

6. The time prediction method for a part change task according to any one of claims 1 to 5, characterized in that: Determining the predicted time interval of the target part change task according to the distribution function obtained by fitting includes: Determine the reference time from the distribution function obtained by fitting according to a set rule; A predicted time interval of the part change task is determined according to the reference time.

7. The time prediction method for a part change task according to any one of claims 1 to 5, characterized in that: After predicting the target part arrival time of the target part change task according to the prediction time interval and the target change start time, the method further includes: Determine the part change tasks to be counted with the target time for the parts to arrive at the warehouse; Counting the number of the part change tasks to be counted; According to the number of the part change tasks to be counted, a parts arrival summary diagram corresponding to the target time is drawn and displayed.

8. A time prediction device for a part change task, characterized in that: The device comprises: A receiving module is configured to receive a prediction request for a target part change task, wherein the prediction request carries a target change start time; A determination module is configured to determine the predicted time interval of the target part change task according to a distribution function obtained by fitting, wherein the distribution function is obtained by fitting based on a sample change start time and a sample part arrival time of the sample part change task; The prediction module is configured to predict the target part arrival time of the target part change task according to the prediction time interval and the target change start time.

9. A computing device, characterized in that include: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement the steps of the time prediction method for a part change task as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: It stores computer instructions, which, when executed by a processor, implement the steps of the time prediction method for a part change task as described in any one of claims 1-7.

Images