Information display method, device, electronic device and computer readable medium

Abstract

The embodiments of the present disclosure disclose information display methods, devices, electronic devices and computer-readable media. A specific implementation of the method includes: obtaining an input order information set, an input promotion information set, and an employee information set; inputting the input order information set and the input promotion information set into a pre-trained prediction model to generate a target order information set; based on the employee information set, generating a target capability information set; determining an unfinished result information set; based on the target order information set, the target capability information set and the unfinished result information set, generating fulfillment result information; pushing the fulfillment result information to a target device with a display function, and controlling the target device to display the fulfillment result information. This implementation can adjust the fulfillment result information in real time according to the target order information set, the target capability information set and the unfinished result information set, thereby improving the prediction level of the fulfillment result information, improving the employee fulfillment capability, and improving the fulfillment service level.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to an information display method, device, electronic device, and computer-readable medium. Background Art

[0002] With the development of new retail, Online To Offline (O2O for short) has become a trend. More and more physical merchants use the Internet to expand their customer base, and more people choose to place orders online. Compared with other commodities, fresh products are prone to rot and spoilage, which puts higher requirements on delivery time. When users place orders online, they can choose the delivery (fulfillment) time period according to their needs. The existing technology obtains the delivery capacity of each deliveryman based on the historical daily delivery situation, and pushes the delivery capacity as the fulfillment result information.

[0003] However, when using the above method to push information, the following technical problems often occur:

[0004] First, the daily delivery task requirements are preset in advance, and there are situations where delivery personnel are vacant, which limits the potential order volume. The fulfillment result information is determined based on historical delivery conditions, and the fulfillment result information cannot be adjusted in real time.

[0005] Second, since historical delivery conditions are affected by many different factors, directly predicting the fulfillment results based on historical delivery conditions will result in a low prediction level, which will lead to the inability to complete the delivery task in a timely manner, or a large amount of human resources will be wasted due to fewer delivery orders. Summary of the invention

[0006] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0007] Some embodiments of the present disclosure propose information display methods, devices, electronic devices, and computer-readable media to solve one or more of the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide a method for information display, the method comprising: obtaining an input order information set, an input promotion information set, and an employee information set; inputting the input order information set and the input promotion information set into a pre-trained prediction model to generate a target order information set; generating a target capability information set based on the employee information set; determining an unfinished result information set; generating fulfillment result information based on the target order information set, the target capability information set, and the unfinished result information set; pushing the fulfillment result information to a target device with a display function, and controlling the target device to display the fulfillment result information.

[0009] In a second aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any method as described in the first aspect.

[0010] In a third aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, any method in the first aspect is implemented.

[0011] The above-mentioned embodiments of the present disclosure have the following beneficial effects: the information display method of some embodiments of the present disclosure can adjust the fulfillment result information in real time according to the target order information set, the target capability information set and the unfinished result information set, improve the prediction level of the fulfillment result information, improve the employee's fulfillment capability, and improve the fulfillment service level. Specifically, the inventor found that the reason why the prediction level of the fulfillment result information is not high enough is that the historical delivery situation is affected by many different factors. The prediction level of the fulfillment result information is low directly based on the historical delivery situation, which leads to the inability to complete the delivery task in time, or a large amount of human resources is wasted due to the small number of delivery orders. In addition, the fulfillment result information cannot be adjusted in real time according to the actual workload of the delivery staff, which limits the potential order volume. Based on this, first, some embodiments of the present disclosure input the input order information set and the input promotion information set into the pre-trained prediction model to generate the target order information set. Among them, the pre-trained prediction model is trained based on the sample input information set and the sample order information set corresponding to the sample input information set. A large amount of data collected based on different weather conditions, date conditions, store locations, staffing conditions and other factors constructs a sample input information set and a sample order information set corresponding to the sample input information set. The sample input information set includes a large number of historical delivery situations, and these situations are structured, which can consider the influence of various different factors and improve the prediction level of the trained prediction model. Relying on the structured sample data and prediction model, the prediction level can be improved. Secondly, some embodiments of the present disclosure generate fulfillment result information based on the target order information set, the target capability information set and the unfinished result information set using a Markov random field model. The method can adjust the fulfillment result information in real time according to the unfinished result information set at the current moment, and can adjust the fulfillment result information in real time according to the actual workload of the delivery staff at the current moment, so as to fully meet the demand for potential orders. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0013] Figure 1 is an architectural diagram of an exemplary system in which some embodiments of the present disclosure may be applied;

[0014] Figure 2 is a flow chart of some embodiments of the information display method according to the present disclosure;

[0015] Figure 3 is a flow chart of training steps for training a prediction model according to the present disclosure;

[0016] Figure 4 It is a structural diagram of a terminal device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0019] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0021] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0022] Figure 1 An exemplary system architecture 100 is shown to which an embodiment of the information display method of the present disclosure may be applied.

[0023] 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.

[0024] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications, such as data processing applications, information display applications, data analysis applications, etc., can be installed on terminal devices 101, 102, 103.

[0025] Terminal devices 101, 102, 103 can be hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various terminal devices with display screens, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, etc. When terminal devices 101, 102, 103 are software, they can be installed in the terminal devices listed above. They can be implemented as multiple software or software modules (for example, to provide order information set input, etc.), or they can be implemented as a single software or software module. No specific limitation is made here.

[0026] The server 105 may be a server that provides various services, such as a server that stores target data input by the terminal devices 101, 102, and 103. The server may process the received order information set and feed back the processing result (such as fulfillment result information) to the terminal device.

[0027] It should be noted that the information display method provided in the embodiment of the present disclosure can be executed by the server 105 or by a terminal device.

[0028] It should be pointed out that the server 105 can also directly store the order information set locally, and the server 105 can directly extract the local data and obtain the fulfillment result information after processing. At this time, the exemplary system architecture 100 may not include the terminal devices 101, 102, 103 and the network 104.

[0029] It should also be noted that the terminal devices 101, 102, 103 may also be installed with information display applications, and in this case, the processing method may also be executed by the terminal devices 101, 102, 103. In this case, the exemplary system architecture 100 may also not include the server 105 and the network 104.

[0030] It should be noted that the server 105 can be hardware or software. When the server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, for providing information display services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0031] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of electronic devices, networks and servers may be provided as required.

[0032] Continue to refer Figure 2 , shows a process 200 of some embodiments of the information display method according to the present disclosure. The information display method comprises the following steps:

[0033] Step 201, obtaining an input order information set, an input promotion information set, and an employee information set.

[0034] In some embodiments, the execution subject of the information display method (eg Figure 1 The server shown in the figure) can obtain the input order information set, the input promotion information set, and the employee information set through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0035] Optionally, the input order information set includes a first number of input order information. Specifically, the first number may be 48. The input order information in the input order information set may be counted as a time period of half an hour. The input order information set includes 48 input order information. The input order information may be the number of orders generated by a store in a time period within a day input by a user or an external device. Specifically, the input order information may be the number of orders. The input order information set includes input order information within a second number of hours before the current moment. Specifically, the second number may be 24. The input order information in the input order information set is input order information within 24 hours before the current moment.

[0036] Optionally, the input promotion information in the input promotion information set includes inputting a planned sales order quantity and a promotion type. The promotion type includes a first promotion type and a second promotion type. Specifically, the first promotion type may be a holiday promotion, and the second promotion type may be a normal promotion. The input planned sales order quantity may be a total number of orders that are planned to be sold within a certain time period and input by a user or an external device.

[0037] Optionally, the employee information in the employee information set includes four categories: full-time pickers, part-time pickers, full-time delivery staff, and part-time delivery staff. The number of employee information in the employee information set is the number of employees in the retail store.

[0038] Step 202: input the input order information set and the input promotion information set into a pre-trained prediction model to generate a target order information set.

[0039] In some embodiments, the execution entity inputs the input order information set and the input promotion information set into a pre-trained prediction model to generate a target order information set.

[0040] Optionally, the target order information set includes a first number of target order information. The target order information set includes 48 target order information. The target order information in the target order information set is counted with half an hour as a time period. The target order information corresponds to the number of orders in a time period within one day. The target order information in the target order information set is the target order information within a second number of hours after the current moment. Specifically, the second number may be 24.

[0041] Specifically, the pre-trained prediction model can be a long short-term memory network (LSTM). The pre-trained prediction model includes a recurrent neural network, a dropout layer, and a fully connected layer. The output of the LSTM is the predicted order volume after the prediction moment. Taking 48 time periods per day as an example, the output corresponding to each set of inputs is the target order information, and the target order information is a vector of length 48.

[0042] As an inventive point of an embodiment of the present disclosure, the above method solves the second technical problem mentioned in the background technology, "Since the historical delivery situation is affected by many different factors, the prediction level of the fulfillment result information is low if it is predicted directly based on the historical delivery situation". The factors that lead to the low level of predicted fulfillment result information are often as follows: the historical delivery situation is affected by many different factors, such as abnormal weather, sick leave of personnel, etc. Predicting the fulfillment result information only based on historical data of a certain day or a shorter period will lead to a low prediction level due to the inaccuracy of historical data. If the above factors are solved, the effect of improving the prediction level can be achieved. In order to achieve this effect, the present disclosure introduces a pre-trained prediction model to predict the fulfillment results. The pre-trained prediction model takes the input order information set and the input promotion information set within one day before the current moment as input content, and outputs the target order information set within one day after the current moment. The pre-trained prediction model is trained based on actual order information and actual promotion information over a period of time, which can improve the prediction level.

[0043] Step 203: Generate a target capability information set based on the employee information set.

[0044] In some embodiments, the execution subject of the information display method determines the equivalent person value corresponding to each employee information in the employee information set using the following formula to obtain an equivalent person value set:

[0045] S=(Ap+Ad)+λ*(Bp+Bd),

[0046] Among them, Ap represents the number of full-time pickers, Ad represents the number of full-time delivery staff, Bp represents the number of part-time pickers, and Bd represents the number of part-time delivery staff. λ is the weight coefficient, and the value range of λ is 0<λ≤1. S is the equivalent person value.

[0047] Optionally, for each equivalent human value in the equivalent human value set, the equivalent human value is input into a predetermined regression model using the following formula to generate a capability upper limit value, so as to obtain a capability upper limit value set:

[0048] Fout=α*S(λ)+β,

[0049] Among them, α and β are regression model coefficients. α and β are obtained by setting λ = 0.1, 0.2, …, 1, performing least squares regression to obtain α and β respectively, and selecting the λ that minimizes the residual and the corresponding α and β as the final model parameters. S(λ) represents the equivalent human value with parameter λ. Fout represents the upper limit of the ability.

[0050] In an optional implementation of some embodiments, the execution subject determines a set of capacity fluctuation values. Obtain a combination of historical data sets. The combination of historical data sets includes a third number of historical data sets, and the historical data sets include a first number of historical data. The historical data in the historical data sets use half an hour as a time period, and the historical data corresponds to the number of orders in a time period within one day. The historical data in the historical data sets is the amount of order data within a second number of hours in one day.

[0051] Optionally, the historical performance capacity matrix can be generated based on the combination of historical data sets using the following formula:

[0052]

[0053] Among them, p i,j is the result of normalization of historical data of the jth period on the i-th day in the historical data set combination. 1，1 is the result of normalization of the historical data of the first period of the first day in the historical data set combination. The historical performance capacity matrix includes a third number of rows, and d represents the third number. The historical performance capacity matrix includes a first number of columns, t represents the first number, and P represents the historical performance capacity matrix.

[0054] Optionally, the execution entity determines the percentile value. Specifically, the percentile value can be determined based on the average backlog order rate and average fulfillment capability in the historical data set. The backlog order rate can represent the backlog of orders that have not been delivered within a certain period of time. For the relevant data of each time period in the historical data set, the percentile value of the time period is calculated using the following formula to obtain a percentile value set:

[0055] q j =0.7+0.2*(w1*exp(-k1*r 1j )+w2*(1 / (1+exp(-k2*(0.6-r 2j )))),

[0056] Where j represents the jth period in the historical data set, r 1j represents the average retention rate of orders in the jth period, r 2j represents the average performance capacity after peak normalization in the jth period, k1=24, k2=6, w1=0.6, w2=0.4, k1, k2, w1, w2 control the influence trend of retention rate in the jth period on percentile selection. j represents the percentile value of the jth period. Specifically, the percentile value can be 70% or 90%. 1j With r 2j Close to 0, q j Close to 90%. 1j With r 2j Close to 1, q j Close to 70%.

[0057] For each column in the historical performance capacity matrix, the element closest to the percentile value in the column is determined as the capacity fluctuation value corresponding to the column to obtain a capacity fluctuation value set. Specifically, the capacity fluctuation value set can be recorded as The capacity fluctuation value set includes t elements, where t is a first number. represents the set of capability fluctuation values, Represents the first element in the ability fluctuation value set. Represents the second element in the ability fluctuation value set. Represents the tth element in the ability fluctuation value set.

[0058] Optionally, for each capability upper limit value in the capability upper limit value set and each capability fluctuation value in the capability fluctuation value set, the product of the capability upper limit value and the capability fluctuation value is determined as the target capability information using the following formula to obtain the target capability information set:

[0059]

[0060] Among them, Fout represents the upper limit of capacity, represents a set of capacity fluctuation values, and R represents target capacity information. The promotion type includes a first promotion type and a second promotion type. Specifically, the first promotion type may be a holiday promotion, and the second promotion type may be a normal promotion. Specifically, in response to the promotion type being a holiday promotion, Can be recorded as Wherein, A represents the first promotion type. In response to the promotion type being a common promotion, Can be recorded as Among them, B represents the second promotion type.

[0061] Step 204, determining the unfinished result information set.

[0062] In some embodiments, the execution subject determines an unfinished result information set. The unfinished result information set includes 48 unfinished result information, and the unfinished result information in the unfinished result information set uses half an hour as a time period. The unfinished result information corresponds to the number of orders placed in a time period within a day, and the unfinished result information in the unfinished result information set is the unfinished result information within 24 hours before the current time.

[0063] Specifically, the unfinished result information refers to the number of orders that have not been completed in a specific time period within 24 hours before the current moment. Specifically, the unfinished result information can be the number of orders. The 24 hours before the current moment include a total of 48 time periods. The unfinished result information set is the set of the number of unfinished orders within the 48 time periods.

[0064] Step 205, generating fulfillment result information based on the target order information set, the target capability information set and the unfinished result information set.

[0065] In some embodiments, the above-mentioned execution entity generates fulfillment result information based on the target order information set, the target capability information set and the unfinished result information set.

[0066] In an optional implementation of some embodiments, the execution subject determines a set of random variables. Specifically, the random process y1, y2, y3, ..., y 48 represents the set of random variables corresponding to the number of orders that the store needs to fulfill but has not completed delivery in the 48 time periods before the current moment. Among them, y1 is the random variable corresponding to the number of orders that the store needs to fulfill but has not completed delivery in the first time period of the 48 time periods before the current moment. 48 It is a random variable corresponding to the number of orders that the store needs to fulfill but has not completed delivery in the 48th time period of the 48 time periods within the previous 24 hours calculated from the current moment.

[0067] For each of the 48 time periods, execute steps 1 to 3 below to generate a random variable corresponding to the number of orders that the store needs to fulfill but has not delivered in that period, so as to obtain a set of random variables corresponding to the number of orders that the store needs to fulfill but has not delivered in the 48 time periods within the 24 hours before the current moment.

[0068] Step 1: Calculate the random variable y corresponding to the number of undelivered orders in the store at the next moment from the current moment t+1 The random variable corresponding to the number of undelivered orders in the store at the current time t is y t, then the random variable y corresponding to the number of undelivered orders in the store at the next moment is t+1 At the same time, y t , the random variable r corresponding to the number of orders delivered within half an hour from time t to time (t+1) t And the random variable s corresponding to the number of orders that need to be fulfilled on the same day when users place orders in the store within half an hour from time t to time (t+1) t Determine jointly. Use the following formula to express y t+1 The calculation process:

[0069] y t+1 =max{y t -r t ,0}+s t ,,

[0070] Among them, y t+1 is the random variable corresponding to the number of undelivered orders in the store at the next moment from the current moment, y t is the random variable corresponding to the number of undelivered orders in the store at the current time t, r t is the random variable corresponding to the number of orders delivered within half an hour from time t to time (t+1), s t is the random variable corresponding to the number of orders that need to be fulfilled on the same day when users place orders in the store within half an hour from time t to time (t+1).

[0071] Step 2: In order to assist the calculation process, an intermediate variable z is introduced t :

[0072] z t =max{y t -r t ,0},

[0073] Among them, y t is a random variable representing the number of undelivered orders in the store at the current time t, r t is the random variable corresponding to the number of orders delivered within half an hour from time t to time (t+1). Specifically, the Markov random field model can be used to generate the random variable z t and t+1 The distribution of. Define an indicator variable z' t =y t -r t , then the indicator variable z' can be obtained using the following formula t The probability of value k is:

[0074]

[0075] Where P() represents the probability value, i and j are arbitrary integers, and k is an arbitrary integer. The intermediate variable z is calculated using the following formula: t Probability:

[0076]

[0077] Where P() represents the probability value, k is an arbitrary integer, z' t is the indicator variable, z t is an intermediate variable.

[0078] Step 3: Calculate the random variable y t+1 The probability of . Using the following formula, calculate y t+1 The probability of value k is:

[0079]

[0080] Among them, z t is an intermediate variable, i and j are arbitrary integers, k is an arbitrary integer, and P() represents the probability value.

[0081] Optionally, the difference between the unfinished result information set and the target capability information set is determined as the saturated indicator set. The saturated indicator set and the random variable set are input into a predetermined statistical model to obtain the saturated indicator distribution results and the upper limit distribution results. Specifically, the predetermined statistical model may be a Markov random field model. The Markov random field model refers to any random variable sequence in the model that is arranged in chronological order, and the distribution characteristics at the N+1th moment are independent of the values ​​of the random variables before the Nth moment. When a value is randomly assigned to the random variable at each moment, the set of random variables at all moments constitutes a Markov random field. The model that simulates the Markov random field is the Markov random field model.

[0082] Optionally, the execution entity determines a performance threshold. Specifically, the performance threshold may be any positive fraction in the range of 0 to 1.

[0083] In an optional implementation of some embodiments, in response to the saturation index distribution result being greater than the fulfillment threshold, an adjustment parameter is determined. Specifically, the adjustment parameter is any negative integer, and the adjustment parameter satisfies the following formula:

[0084] P(z' t <m)≤p<P(z' t <m+1),

[0085] Among them, z' t represents the indicator variable, m is the adjustment parameter, P() represents the probability value, and p represents the fulfillment threshold.

[0086] The following formula is used to determine the fulfillment result information by adding the adjustment parameter to the target capability information at the current moment in the target capability information set:

[0087] x' t+1 =x t+1 +(-m),

[0088] Among them, x t+1 is the target capability information at the current moment, m is the adjustment parameter, x' t+1 It is the performance result information.

[0089] In an optional implementation of some embodiments, in response to the fulfillment upper limit distribution result being not less than the fulfillment threshold, an adjustment parameter is determined. Specifically, the adjustment parameter is any negative integer. An estimated total value is determined. Specifically, the estimated total value may be the total number of orders that have been placed and need to be fulfilled on that day.

[0090] The sum of all elements in the saturation index set is determined as the first comparison value. In response to the sum of the first comparison value and the target order information at the next moment in the target order information set being greater than the difference between the estimated total value and the adjustment parameter, the fulfillment result information is determined as the difference between the estimated total value and the adjustment parameter minus the first comparison value using the following formula:

[0091]

[0092] Among them, n t+1 is the estimated total value, m is the adjustment parameter, represents the first comparison value, x' represents the element in the saturation index set, x' t+1 Indicates the fulfillment result information.

[0093] In response to the fact that the sum of the first comparison value and the target order information at the next moment in the target order information set at the current moment is not greater than the difference between the estimated total value and the adjustment parameter, the target order information at the next moment in the target order information set at the current moment is determined as the fulfillment result information using the following formula:

[0094] x' t+1 =x t+1 ,

[0095] Among them, x t+1 The target order information for the next moment from the current moment, x' t+1 Indicates the fulfillment result information.

[0096] In an optional implementation of some embodiments, the execution entity determines the total number of orders. Specifically, the total number of orders can be the number of orders that the store is expected to fulfill on the day. The difference between the total number of orders and the adjustment parameter is determined as the second comparison value. In response to the fulfillment upper limit distribution result being not less than the fulfillment threshold, the difference between the second comparison value and the first comparison value is determined as the fulfillment result information using the following formula:

[0097]

[0098] Wherein, Nm is the second comparison value, Represents the first comparison value, x' t+1 Indicates the fulfillment result information.

[0099] The above-mentioned processing step of setting the fulfillment threshold, as an inventive point of an embodiment of the present disclosure, solves the technical problem mentioned in the background technology: "The daily delivery task requirements are preset in advance, and there are vacancies in the delivery personnel, which limits the potential order volume. However, the fulfillment result information is determined based on the historical delivery situation, and the fulfillment result information cannot be adjusted in real time.". The factors that lead to the limitation of potential orders and the inability to adjust the fulfillment result information are often as follows: the total number of orders that the store needs to fulfill is predetermined based on historical conditions, delivery task requirements, etc., and the fulfillment result information is determined based on the total number of orders. When the delivery capacity of the delivery personnel changes on the same day or the order situation on the same day changes, the fulfillment result information cannot be adjusted in real time. If the above factors are solved, the effect of adjusting the fulfillment result information in real time can be achieved. In order to achieve this effect, the present disclosure makes dynamic adjustments based on the fulfillment threshold. First, in response to the saturation index distribution result being less than the fulfillment threshold, the result of adding the adjustment parameter to the target capacity information at the current moment in the target capacity information set can be determined as the fulfillment result information. Secondly, the current performance situation is judged. In response to the performance upper limit distribution result being not less than the performance threshold, and in response to the sum of the first comparison value and the target order information at the next moment of the current moment in the target order information set being greater than the difference between the estimated total value and the performance threshold, the performance result information is determined as the difference between the estimated total value and the performance threshold minus the first comparison value. Thirdly, the current performance situation is judged. In response to the performance upper limit distribution result being not less than the performance threshold, and in response to the sum of the first comparison value and the target order information at the next moment of the current moment in the target order information set being not greater than the difference between the estimated total value and the performance threshold, the target order information at the next moment of the current moment in the target order information set is determined as the performance result information. Finally, the performance result information can also be determined based on the preset total order quantity. Through different determination methods, it is possible to achieve real-time determination of the performance result information based on the target order information set, target capacity information set, and unfinished result information set at the current moment.

[0100] Step 206: Push the fulfillment result information to a target device with a display function, and control the target device to display the fulfillment result information.

[0101] In some embodiments, the above-mentioned execution subject pushes the fulfillment result information to a target device with a display function, and controls the target device to display the fulfillment result information. Among them, the target device with a display function can be a device that is connected to the above-mentioned execution subject in communication, and can be displayed according to the received fulfillment result information. For example, when the above-mentioned execution subject outputs the fulfillment result information indicating that the current fulfillment task is inconsistent with the displayed fulfillment result information, the user can be prompted to change the fulfillment plan (for example, reduce the allocation of fulfillment tasks, or increase the allocation of fulfillment tasks), thereby improving the fulfillment level. This implementation method can be used for fresh food delivery in new retail physical stores, taking into full account the characteristics of user ordering behavior and employee fulfillment behavior, and systematically regulating, alarming and limiting the store order flow. So that while ensuring the timeliness rate, the store's revenue can be maximized at the same time.

[0102] Figure 2 An embodiment provided has the following beneficial effects: obtaining an input order information set, an input promotion information set, and an employee information set; inputting the input order information set and the input promotion information set into a pre-trained prediction model to generate a target order information set; generating a target capability information set based on the employee information set; determining an unfinished result information set; generating fulfillment result information based on the target order information set, the target capability information set, and the unfinished result information set; pushing the fulfillment result information to a target device with a display function, and controlling the target device to display the fulfillment result information. This implementation can adjust the fulfillment result information in real time according to the target order information set, the target capability information set, and the unfinished result information set, thereby improving the prediction level of the fulfillment result information, enhancing the employee fulfillment capability, and improving the fulfillment service level.

[0103] Continue to refer Figure 3 , shows a process 300 of an embodiment of a training step of a pre-trained prediction model according to the present disclosure. The training step may include the following steps:

[0104] Step 301, determining the network structure of the initial prediction model and initializing the network parameters of the initial prediction model.

[0105] In this embodiment, the execution subject of the training step can be the same as the execution subject of the information display method (for example Figure 1 The terminal device shown in the figure is the same or different. If they are the same, the execution subject of the training step can store the trained network structure information and the parameter values ​​of the network parameters locally after the prediction model is obtained through training. If they are different, the execution subject of the training step can send the trained network structure information and the parameter values ​​of the network parameters to the execution subject of the information display method after the prediction model is obtained through training.

[0106] In this embodiment, the execution subject of the training step may first determine the network structure of the initial prediction model. For example, it is necessary to determine which layers the initial prediction model includes, the connection order relationship between the layers, which neurons each layer includes, the weight and bias corresponding to each neuron, the activation function of each layer, etc. Optionally, the prediction model may include a recurrent neural network, a discard layer, and a fully connected layer.

[0107] Then, the execution subject of the training step can initialize the network parameters of the initial prediction model. In practice, the various network parameters of the initial prediction model (for example, weight parameters and bias parameters) can be initialized with some different small random numbers. "Small random numbers" are used to ensure that the network will not enter a saturated state due to excessive weights, thereby causing training failure, and "different" is used to ensure that the network can learn normally.

[0108] Step 302: Obtain a training sample set.

[0109] In this embodiment, the execution subject of the training step can obtain the training sample set locally or remotely from other terminal devices connected to the execution subject network. The training sample includes a sample input information set and a sample order information set corresponding to the sample input information set. The sample input information set includes the sample input planned sales order quantity, the sample input actual sales order quantity and the sample promotion type.

[0110] Specifically, the sample input information set consists of the actual sales volume, planned sales volume, and promotion type for half a year to a year. This information is divided into several time periods every day. The actual sales volume, planned sales volume, and promotion type are columns, and the time period is a row. Specifically, each day is divided into 48 time periods, and the input is a 96x2 matrix (filled with 0 after the prediction moment). The element corresponding to 96 is 2 days, and the information of 48 time periods every day. Promotion types include big promotion, medium promotion, and ordinary. Among them, big promotion and medium promotion have different promotion strengths, and big promotion has planned promotion volume, while medium promotion is uncertain (may or may not). The information of the reference day and the information of the day have a certain correspondence in time, and each level of promotion and the promotion of the same level in the past also correspond in date. For example, 8:00 on the reference day corresponds to 8:00 on the day, and the first day of a big promotion in the past corresponds to the first day of the current big promotion.

[0111] Specifically, in response to the promotion type of the day being a big promotion, the number of orders in the non-promotion period of the reference day in the sample input information set (only on the first day of the big promotion) is the actual sales number of the corresponding period of the most recent big promotion (the first day), and the number of orders in the promotion period of the reference day is measured by the planned sales number of the big promotion of the day. In response to the promotion type of the day being a medium promotion, the number of orders on the first and second days of the reference day in the sample input information set can use the actual sales number of the first and second days of the date corresponding to the previous medium promotion type. The number of orders on the days after the reference day can use the actual sales number of the previous day. In response to the promotion type of the day being a normal day, the actual sales number of the corresponding day of last week can be used as the actual sales number in the sample input information set.

[0112] Specifically, the output sample order information set can be the predicted order volume after the prediction time. Specifically, taking 48 time periods per day as an example, the output is a vector of length 48. The data before the output prediction time is discarded and denormalized to obtain the final prediction result.

[0113] Specifically, the sample input information set and the output sample order information set are normalized respectively to obtain the final sample input information set and the output sample order information set.

[0114] Step 303, select a sample from the sample set, take the sample input information set included in the sample as input, take the corresponding pre-obtained sample order information set corresponding to the sample input information set as expected output, and train the prediction model.

[0115] In this embodiment, the execution subject of the training step can execute step 1 to train the prediction model.

[0116] Step 1: Prediction model training process.

[0117] First, a sample input information set included in the training samples in the selected training sample set is input into the initial prediction model to obtain an order information set of the selected samples.

[0118] Second, the selected sample order information set is compared with the corresponding sample order information set. Specifically, the difference between the selected sample order information set and the corresponding sample order information set can be first calculated using a preset loss function. For example, the difference between the selected sample order information and the corresponding sample order information can be calculated using the masked mean absolute error loss function using the following formula:

[0119]

[0120] Among them, m represents the total number of calculation cycles after the prediction time, i represents the current cycle corresponding to the current time, and x iis the sample selected at the current moment, y i It is the sample order information at the current moment. h(x i ) represents the order information of the selected sample at the current moment. loss represents the mean absolute error loss function value with mask.

[0121] Third, in response to determining that the initial prediction model has reached the optimization goal, the initial prediction model is used as a pre-trained prediction model that has completed training, and the training ends. Specifically, the preset optimization goal here may include but is not limited to at least one of the following: the training time exceeds the preset time; the number of training times exceeds the preset number of times; the calculated difference is less than the preset difference threshold.

[0122] Step 304, in response to determining that the initial prediction model has not been trained, adjusting relevant parameters in the initial prediction model, reselecting samples from the sample set, using the adjusted initial prediction model as the initial prediction model, and performing the training step again.

[0123] In this embodiment, the execution subject of the training step responds to determining that the initial prediction model has not been trained. Specifically, it can be in response to the initial prediction model not reaching the optimization target, and adjusts the relevant parameters in the initial prediction model. Specifically, various implementation methods can be used to adjust the network parameters of the initial prediction model based on the difference between the selected sample order information set and the corresponding sample order information set. For example, the Adam, BP (Back Propagation) algorithm or the SGD (Stochastic Gradient Descent) algorithm can be used to adjust the network parameters of the initial prediction model.

[0124] Optionally, the execution subject reselects a sample from the sample set, takes the sample input information set included in the sample as input, takes the corresponding pre-obtained sample order information set corresponding to the sample input information set as the expected output, uses the adjusted initial prediction model as the initial prediction model, executes the above step 1, and trains the prediction model again.

[0125] In this embodiment, the execution subject of the training step determines the initial prediction model obtained through training as the pre-trained prediction model.

[0126] Figure 3 An embodiment provided has the following beneficial effects: a prediction model is trained based on a sample input information set and a sample order information set corresponding to the sample input information set. The prediction model can be directly applied to determine the order information set that can be generated by the input sample input information set. The pre-trained prediction model is trained based on actual order information and actual promotion information within a period of time, which can improve the prediction level.

[0127] Reference below Figure 4 , which shows a schematic diagram of the structure of a computer system 400 suitable for implementing a server of an embodiment of the present disclosure. Figure 4 The server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0128] like Figure 4 As shown, the computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403. Various programs and data required for the operation of the system 400 are also stored in the RAM 403. The CPU 401, the ROM 402 and the RAM 403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0129] The following components are connected to the I / O interface 405: a storage section 406 including a hard disk, etc.; and a communication section 407 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 407 performs communication processing via a network such as the Internet. A drive 408 is also connected to the I / O interface 405 as needed. A removable medium 409, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 408 as needed, so that a computer program read therefrom is installed into the storage section 406 as needed.

[0130] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 407, and / or installed from the removable medium 409. When the computer program is executed by the central processing unit (CPU) 401, the above functions defined in the method of the present disclosure are executed. It should be noted that the computer-readable medium described in the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, device, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0131] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as C or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0132] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0133] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present disclosure is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other.

Claims

1. An information display method, comprising: Acquire an input order information set, an input promotion information set, and an employee information set, wherein the input order information set includes a first number of input order information, the input order information in the input order information set uses half an hour as a time period, the input order information corresponds to the number of orders in a time period within a day, and the input order information in the input order information set is input order information within a second number of hours before the current time; Inputting the input order information set and the input promotion information set into a pre-trained prediction model to generate a target order information set, wherein the target order information set includes a first number of target order information, and the target order information in the target order information set is the target order information within a second number of hours after the current moment; Based on the employee information set, generating a target capability information set; Determine an unfinished result information set, wherein the unfinished result information set includes a first number of unfinished result information, the unfinished result information in the unfinished result information set uses half an hour as a time period, the unfinished result information corresponds to the number of orders placed in a time period within one day, and the unfinished result information in the unfinished result information set is the unfinished result information within a second number of hours before the current time; Generate fulfillment result information based on the target order information set, the target capability information set and the unfinished result information set; Pushing the fulfillment result information to a target device with a display function, and controlling the target device to display the fulfillment result information; wherein the pre-trained prediction model includes a recurrent neural network, a dropout layer, and a fully connected layer; and The pre-trained prediction model is obtained through the following steps: Determining a network structure of an initial prediction model and initializing network parameters of the initial prediction model; Acquire a training sample set, wherein the training sample includes a sample input information set and a sample order information set corresponding to the sample input information set, wherein the sample input information set includes a sample input planned sales order quantity, a sample input actual sales order quantity, and a sample promotion type; Select samples from the sample set and perform the following training steps: Inputting the sample input information set of the selected sample into the initial prediction model to obtain the order information set of the selected sample; Comparing the selected sample order information set with the corresponding sample order information set; Determining whether the initial prediction model reaches a preset optimization goal according to the comparison result; In response to determining that the initial prediction model achieves the optimization goal, using the initial prediction model as the pre-trained prediction model that has completed training; In response to determining that the initial prediction model has not been trained, adjusting relevant parameters in the initial prediction model, reselecting samples from the sample set, using the adjusted initial prediction model as the initial prediction model, and performing the training step again; Wherein, based on the employee information set, generating a target capability information set includes: For each employee information in the employee information set, the equivalent person value corresponding to the employee information is determined using the following formula to obtain an equivalent person value set: S=(Ap+Ad)+λ*(Bp+Bd), Among them, Ap represents the number of full-time pickers, Ad represents the number of full-time delivery staff, Bp represents the number of part-time pickers, Bd represents the number of part-time delivery staff, λ is the weight coefficient, the value range of λ is 0<λ≤1, and S is the equivalent person value; For each equivalent human value in the equivalent human value set, the equivalent human value is input into a predetermined regression model using the following formula to generate a capability upper limit value, thereby obtaining a capability upper limit value set: Fout=α*S(λ)+β, Among them, α and β are regression model coefficients. α and β are obtained by setting λ = 0.1, 0.2, …, 1, performing least squares regression to obtain α and β respectively, and selecting λ that minimizes the residual and the corresponding α and β as the final model parameters. S(λ) represents the equivalent human value with parameter λ, and Fout represents the upper limit of the ability. Determine the set of capability fluctuation values, including: Acquire a historical data set combination, wherein the historical data set combination includes a third number of historical data sets, the historical data set includes a first number of historical data, the historical data in the historical data set uses half an hour as a time period, the historical data corresponds to the number of orders in a time period within a day, and the historical data in the historical data set is the amount of order data within a second number of hours in a day; The historical performance capacity matrix is ​​generated based on the combination of the historical data sets using the following formula: Among them, p i,j is the result of normalization of historical data of the jth period on the i-th day in the historical data set combination, p 1,1 is the result of normalization processing of the historical data of the first period of the first day in the historical data set combination, taking the elements in each historical data set in the historical data set combination as a row of the historical performance capacity matrix, the historical performance capacity matrix includes a third number of rows, d represents the third number, the historical performance capacity matrix includes a first number of columns, t represents the first number, and P represents the historical performance capacity matrix; Determining the percentile value includes: determining the percentile value according to the average delayed order rate and the average fulfillment capability in the historical data set, the delayed order rate represents the backlog of orders that have not been delivered within a certain period of time, and for the relevant data of each period in the historical data set, using the following formula, calculating the percentile value of the period to obtain a percentile value set: q j =0.7+0.2*(w1*exp(-k1*r 1j )+w2*(1 / (1+exp(-k2*(0.6-r 2j )))), Where j represents the jth period in the historical data set, r 1j represents the average retention rate of orders in the jth period, r 2j represents the average performance capacity after peak normalization in the jth period, k1=24, k2=6, w1=0.6, w2=0.4, k1, k2, w1, w2 control the influence trend of the retention rate in the jth period on the percentile selection, q j represents the percentile value of the jth period; For each row in the historical performance capacity matrix, determine the element in the row that is equal to the percentile value as the capacity fluctuation value corresponding to the row, so as to obtain the capacity fluctuation value set, wherein the capacity fluctuation value set includes t elements, where t is a first number; For each capability upper limit value in the capability upper limit value set and each capability fluctuation value in the capability fluctuation value set, the product of the capability upper limit value and the capability fluctuation value is determined as the target capability information using the following formula to obtain the target capability information set: Among them, Fout represents the upper limit of capacity, represents a set of capability fluctuation values, R represents target capability information, and the promotion type includes a first promotion type and a second promotion type; Wherein, generating the fulfillment result information based on the target order information set, the target capability information set and the unfinished result information set includes: Determine the set of random variables, including: using the random process y1,y2,y3,...,y 48 represents the set of random variables corresponding to the number of orders that the store needs to fulfill but has not completed delivery in the 48 time periods within the 24 hours before the current moment, where y1 is the random variable corresponding to the number of orders that the store needs to fulfill but has not completed delivery in the first time period of the 48 time periods within the 24 hours before the current moment, and y 48 The random variable corresponding to the number of orders that the store needs to fulfill but has not delivered in the 48th time period of the 48 time periods within the previous 24 hours calculated from the current moment; For each of the 48 time periods, execute the following steps 1 to 3 to generate a random variable corresponding to the number of orders that the store needs to fulfill but has not completed delivery in that period, so as to obtain a set of random variables corresponding to the number of orders that the store needs to fulfill but has not completed delivery in a total of 48 time periods within 24 hours before the current moment; Step 1: Calculate the random variable y corresponding to the number of undelivered orders in the store at the next moment from the current moment t+1 , the random variable corresponding to the number of undelivered orders in the store at the current time t is y t , then the random variable y corresponding to the number of undelivered orders in the store at the next moment is t+1 At the same time, y t , the random variable r corresponding to the number of orders delivered within half an hour from time t to time (t+1) t And the random variable s corresponding to the number of orders that need to be fulfilled on the same day when users place orders in the store within half an hour from time t to time (t+1) t Let us jointly decide and express y using the following formula t+1 The calculation process: y t+1 =max{y t -r t ,0}+s t , Among them, y t+1 is the random variable corresponding to the number of undelivered orders in the store at the next moment from the current moment, y t is the random variable corresponding to the number of undelivered orders in the store at the current time t, r t is the random variable corresponding to the number of orders delivered within half an hour from time t to time (t+1), s t is the random variable corresponding to the number of orders that need to be fulfilled on the same day when users place orders in the store within half an hour from time t to time (t+1); Step 2: In order to assist the calculation process, an intermediate variable z is introduced t : z t =max{y t -r t ,0}, Among them, y t is a random variable representing the number of undelivered orders in the store at the current time t, r t is the random variable corresponding to the number of orders delivered within half an hour from time t to time (t+1). Specifically, the random variable z is generated using the Markov random field model. t and t+1 The distribution of, define an indicator variable z' t =y t -r t , then the indicator variable z' can be obtained using the following formula t The probability of value k is: Where P() represents the probability value, i and j are arbitrary integers, and k is an arbitrary integer. The intermediate variable z is calculated using the following formula: t Probability: P(z t = k) = P(z' t =k), when k>0 Where P() represents the probability value, k is an arbitrary integer, z' t is the indicator variable, z t is an intermediate variable; Step 3: Calculate the random variable y t+1 The probability of y is calculated using the following formula t+1 The probability of value k is: Among them, z t is an intermediate variable, i and j are arbitrary integers, k is an arbitrary integer, and P() represents the probability value; The difference between the unfinished result information set and the target capability information set is determined as a saturated indicator set, and the saturated indicator set and the random variable set are input into a predetermined statistical model to obtain a saturated indicator distribution result and a performance upper limit distribution result; Determine compliance thresholds; In response to the saturation index distribution result being greater than the fulfillment threshold, an adjustment parameter is determined. Specifically, the adjustment parameter is any negative integer, and the adjustment parameter satisfies the following formula: P(z t '<m)≤p<P(z t '<m+1), Among them, z' t represents the indicator variable, m is the adjustment parameter, P() represents the probability value, and p represents the fulfillment threshold; The following formula is used to determine the fulfillment result information by adding the adjustment parameter to the target capability information at the current moment in the target capability information set: x' t+1 =x t+1 +(-m), Among them, x t+1 is the target capability information at the current moment, m is the adjustment parameter, x' t+1 Information about performance results; In response to the performance upper limit distribution result being not less than the performance threshold, determining an adjustment parameter; The sum of all elements in the saturation index set is determined as the first comparison value. In response to the sum of the first comparison value and the target order information at the next moment in the target order information set being greater than the difference between the estimated total value and the adjustment parameter, the fulfillment result information is determined as the difference between the estimated total value and the adjustment parameter minus the first comparison value using the following formula: Among them, n t+1 is the estimated total value, m is the adjustment parameter, represents the first comparison value, x' represents the element in the saturation index set, x' t+1 Indicates the fulfillment result information; In response to the fact that the sum of the first comparison value and the target order information at the next moment in the target order information set at the current moment is not greater than the difference between the estimated total value and the adjustment parameter, the target order information at the next moment in the target order information set at the current moment is determined as the fulfillment result information using the following formula: x' t+1 =x t+1 , Among them, x t+1 The target order information for the next moment from the current moment, x' t+1 Indicates the fulfillment result information; Determine the total number of orders, which is the number of orders that the store needs to fulfill on the day, including: determining the difference between the total number of orders and the adjustment parameter as the second comparison value, and in response to the fulfillment upper limit distribution result being not less than the fulfillment threshold, determining the difference between the second comparison value and the first comparison value as the fulfillment result information using the following formula: Wherein, Nm is the second comparison value, Represents the first comparison value, x' t+1 Indicates the fulfillment result information.

2. The method according to claim 1, wherein: The input promotion information in the input promotion information set includes an input planned sales order quantity and a promotion type, and the promotion type includes a first promotion type and a second promotion type.

3. The method according to claim 2, wherein: The step of generating a target capability information set based on the employee information set includes: For each employee information in the employee information set, determining an equivalent person value corresponding to the employee information to obtain an equivalent person value set; Inputting the equivalent human value set into a predetermined regression model to obtain a set of upper capacity values; Determine the set of capability fluctuation values; The product of the capability upper limit value set and the capability fluctuation value set is determined as a target capability information set.

4. A first terminal device, comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 3.

5. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images