CN113077277A

CN113077277A - Information processing apparatus and method

Info

Publication number: CN113077277A
Application number: CN202010010537.1A
Authority: CN
Inventors: 刘仁敏
Original assignee: Beijing Jingbangda Trade Co Ltd; Beijing Jingdong Zhenshi Information Technology Co Ltd
Current assignee: Beijing Jingbangda Trade Co Ltd; Beijing Jingdong Zhenshi Information Technology Co Ltd
Priority date: 2020-01-06
Filing date: 2020-01-06
Publication date: 2021-07-06

Abstract

The invention discloses an information processing device and method, and relates to the technical field of computers. One embodiment of the apparatus comprises: the memory is used for storing at least two processing models and at least two information processing modes; the processor is used for determining processing requirements for the order reference information, configuring calling information for the order reference information according to the order reference information and the processing requirements, and indicating at least one target processing model, a target information processing mode and a calling relation matched for the order reference information by the calling information; and according to the calling relation, calling at least one target processing model and a target information processing mode stored in the memory to process the order reference information through a calling interface, generating expected order quantity for processing requirements, and outputting the expected order quantity. This embodiment enables flexibility in information processing.

Description

Information processing apparatus and method

Technical Field

The present invention relates to the field of computer technologies, and in particular, to an information processing apparatus and method.

Background

The order quantity of the product can be used for measuring the sales condition of the product, the operation condition of the company on the product and the like. Then, prior to a sale or promotion event, the product may be pre-deployed, such as to determine product inventory for a promotion period, by pre-evaluating the expected order quantity of the product, such as a predicted sales volume.

The existing sales prediction system mainly adopts a configured fixed processing model to predict a certain product sales scene such as sales promotion activities or a certain class of products such as household appliances, dairy products and the like. In addition, because different product sales scenarios are based on different characteristic attributes and processing models, it is often necessary to use several different sales prediction systems to predict sales of different product sales scenarios.

In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:

the existing sales forecasting system adopts a fixed processing model to forecast sales, and cannot be flexibly configured according to order characteristics.

Disclosure of Invention

In view of this, embodiments of the present invention provide an information processing apparatus and method, which can flexibly configure a processing model according to order reference information, so as to accurately evaluate expected order quantities corresponding to different scenarios.

To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided an information processing apparatus including: a memory, a processor, and a call interface, wherein,

the memory is used for storing at least two processing models and at least two information processing modes;

the processor is used for determining a processing requirement for order reference information, and configuring calling information for the order reference information according to the order reference information and the processing requirement, wherein the calling information indicates at least one target processing model, a target information processing mode and a calling relation matched for the order reference information; and according to the calling relation, calling the at least one target processing model and the target information processing mode stored in the memory to process the order reference information through the calling interface, generating expected order quantity for the processing requirement, and outputting the expected order quantity.

Preferably, the first and second electrodes are formed of a metal,

the memory is further used for storing at least one preset calling message;

the processor is further configured to receive a processing request for the order reference information, where the processing request indicates a selected type of call information stored in the memory, and configure the call information indicated by the processing request for the order reference information.

Preferably, the calling interface includes: a model calling sub-interface corresponding to each processing model and a processing mode calling sub-interface corresponding to each information processing mode;

the processor is used for calling the target processing model through the model calling sub-interface corresponding to the target processing model, calling the sub-interface through the processing mode corresponding to the target information processing mode, and calling the target information processing mode.

Preferably, the first and second electrodes are formed of a metal,

the processor is further configured to configure a model modification policy for the order reference information, and modify the at least one target processing model according to the model modification policy.

Preferably, the first and second electrodes are formed of a metal,

the processor is further configured to configure a cross validation mechanism for the order reference information, and validate the generated expected order quantity through the cross validation mechanism.

Preferably, the processor comprises: a pre-processing sub-module and a feature processing sub-module, wherein,

the preprocessing submodule is used for determining a data specification and a basic check, and correcting the data included in the order reference information according to the data specification and the basic check so as to enable the corrected data to meet the data specification;

the feature processing submodule is used for determining a feature extraction interface and features to be extracted, extracting data corresponding to the features to be extracted from the corrected data by calling the feature extraction interface, and processing the data corresponding to the features to be extracted by calling the at least one target processing model stored in the memory and the target information processing mode.

In a second aspect, an embodiment of the present invention provides an information processing method, including:

storing at least two processing models and at least two information processing modes;

further comprising:

determining processing requirements for the order reference information;

configuring calling information for the order reference information according to the order reference information and the processing requirement, wherein the calling information indicates at least one target processing model, a target information processing mode and a calling relation matched for the order reference information;

according to the calling relation, calling the at least one target processing model and the target information processing mode from the at least two stored processing models and the at least two stored information processing modes through a preset calling interface to process the order reference information;

generating a prospective order quantity for the processing demand, and outputting the prospective order quantity.

Preferably, the information processing method further includes:

storing at least one preset calling information;

the configuring of the calling information for the order reference information includes:

receiving a processing request aiming at the order reference information, wherein the processing request indicates one kind of calling information selected from the at least one preset calling information, and configuring the calling information indicated by the processing request for the order reference information.

Preferably, the information processing method further includes: and configuring a model correction strategy for the order reference information, and correcting the at least one target processing model according to the model correction strategy.

Preferably, the information processing method further includes: configuring a cross validation mechanism for the order reference information, and validating the generated expected order quantity through the cross validation mechanism.

Preferably, the information processing method further includes:

determining data specification, basic verification, a feature extraction interface and features to be extracted;

correcting the data included in the order reference information according to the data specification and the basic verification so that the corrected data meet the data specification;

and extracting data corresponding to the features to be extracted from the corrected data by calling the feature extraction interface so as to call the at least one target processing model stored in the memory and the target information processing mode to process the data corresponding to the features to be extracted.

One embodiment of the above invention has the following advantages or benefits: aiming at least two processing models and at least two information processing modes stored in the memory, the processor can determine processing requirements for the order reference information, and at least one target processing model, a target information processing mode and a calling relation are matched according to the processing requirements and the order reference information, so that the flexible configuration of the processing models according to the order reference information is realized. In addition, since the processing model directly affects the accuracy of the generated expected order quantity, and the target processing model, the target information processing method and the call relation obtained according to the processing requirement and the order reference information are used in the embodiment of the present invention, the information processing apparatus provided in the embodiment of the present invention can ensure the accuracy of the generated expected order quantity.

Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.

Drawings

The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:

fig. 1 is a schematic diagram of main units of an information processing apparatus according to an embodiment of the present invention;

fig. 2 is a schematic diagram of main units of an information processing apparatus according to an embodiment of the present invention;

fig. 3 is a schematic diagram of main units of an information processing apparatus according to an embodiment of the present invention;

fig. 4 is a schematic diagram of main units of an information processing apparatus according to an embodiment of the present invention;

FIG. 5 is a flow chart illustrating the main steps of an information processing method according to an embodiment of the present invention;

FIG. 6 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;

FIG. 7 is a schematic block diagram of a computer system suitable for use with a server implementing an embodiment of the invention.

Detailed Description

Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

It should be noted that the embodiments of the present invention and the technical features of the embodiments may be combined with each other without conflict.

Order reference information refers to reference-valued data associated with a product that can be used to generally measure the condition of the product. For example, the order quantity in a certain period of time, the inventory corresponding to the order product, the attribute of the order product, the order quantity grade to which the order in a certain period of time belongs, the industry characteristic to which the product corresponding to the order belongs, and the like. Then, based on the order reference information, the expected order quantity of the product corresponding to the order reference information is obtained, and the product sales plan, the product inventory and the like can be guided or suggested.

As shown in fig. 1, an embodiment of the present invention provides an information processing apparatus, where the information processing apparatus 100 may include: memory 101, processor 102, and call interface 103, wherein,

a memory 101 for storing at least two processing models and at least two information processing methods;

the processor 102 is configured to determine a processing requirement for order reference information, configure calling information for the order reference information according to the order reference information and the processing requirement, where the calling information indicates at least one target processing model, a target information processing mode, and a calling relationship matched for the order reference information, call, through the calling interface 103, the at least one target processing model and the target information processing mode stored in the memory 101 to process the order reference information according to the calling relationship, generate an expected order quantity for the processing requirement, and output the expected order quantity.

The calling information configured for the order reference information may include identification information corresponding to the target processing model, identification information corresponding to the target information processing mode, parameters required by the target processing model, and the like, and when the number of the target processing models is at least two, the calling information may further include a calling relationship between at least two target processing models, where the calling relationship may be a calling order of the processing models or a calling logic of the processing models, and the like, for example, an output of the processing model 1 is used as an input of the processing model 2.

The at least two processing models include, but are not limited to, time series models such as exponential smoothing, ARIMA, Holt-Winter, etc., regression analysis models such as linear regression, nonlinear regression, tree regression, neural network, etc. basic data processing models; and open source models such as Fb-prophet and the like.

The processing requirement may be a requirement for the expected order quantity or a condition that the set expected order quantity needs to meet, such as a date granularity (day, week, month), an expected length, etc. of the expected order quantity. Such as evaluating the sales of products during a promotional program, which can be used as the expected order quantity for an embodiment of the present invention. Accordingly, the granularity of the dates for the expected number of orders may be one day/one week/one month of the promotional campaign, with the expected length being the promotional campaign. The processing requirements can also be inventory requirements, inter-bin allocation requirements, product layout requirements, and the like.

The at least two information processing modes include, but are not limited to, single-machine batch concurrency, spark market concurrency, Docker concurrency, and the like.

In the technical solution provided by the embodiment shown in fig. 1, for at least two processing models and at least two information processing methods stored in the memory, the processor may determine a processing requirement for the order reference information, and match at least one target processing model, target information processing method, and call relationship according to the processing requirement and the order reference information, thereby implementing flexible configuration of the processing models according to the order reference information. In addition, since the processing model directly affects the accuracy of the generated expected order quantity, and the target processing model, the target information processing method and the call relation obtained according to the processing requirement and the order reference information are used in the embodiment of the present invention, the information processing apparatus provided in the embodiment of the present invention can ensure the accuracy of the generated expected order quantity.

In addition, the processing requirement may further define attributes of the order reference information, for example, attributes of products corresponding to the order reference information, such as categories, for example, new products, sales promotion products, long-tailed products, and the like, sales levels to which the product order quantities belong, and industry characteristics to which the products belong.

Additionally, in one embodiment of the invention, the processor may be further configured to define a pre-processing policy that dictates the feature extraction, data cleansing, and data transformation of the order reference information.

In an embodiment of the present invention, the memory is further configured to store at least one preset call information;

the processor is further used for receiving a processing request aiming at the order reference information, the processing request indicates one kind of call information stored in the selected memory, and the call information indicated by the processing request is configured for the order reference information.

The preset calling information may be calling information which is stored in the memory before formal use of the information processing device and is well defined by a user for a certain type of products or a certain type of scenes, or may be calling information which is configured by the processor for certain order reference information before in the use process of the information processing device.

The information processing device provided by the embodiment of the invention can store preset calling information, accordingly, the stored calling information can be directly selected, and corresponding calling information can also be configured for the current order reference information so as to process the current order reference information and generate expected order quantity to meet different requirements of users. Flexibility in application of the information processing apparatus is further improved.

In one embodiment of the present invention, as shown in fig. 2, the call interface 103 includes: a model calling sub-interface 1031 corresponding to each processing model and a processing mode calling sub-interface 1032 corresponding to each information processing mode;

the processor 102 is configured to invoke the sub-interface 1031 through a model corresponding to the target processing model, invoke the sub-interface 1032 through a processing method corresponding to the target information processing method, and invoke the target information processing method.

The model calling sub-interfaces and the processing models and the processing mode calling sub-interfaces and the information processing modes can be in one-to-one correspondence, namely, one model calling sub-interface can only call one processing model, and correspondingly, one processing model can only be called by one model calling sub-interface; one processing mode calling sub-interface can only call one information processing mode, and correspondingly, one information processing mode can only be called by one processing mode calling sub-interface. After the target model calling sub-interface is determined, a processing model called by the target model calling sub-interface can be called; after the target processing mode calling sub-interface is determined, the information processing mode called by the target processing mode calling sub-interface can be called, and the calling accuracy can be guaranteed.

In an embodiment of the present invention, the processor 102 is further configured to configure a model modification policy for the order reference information, and modify the at least one target process model according to the model modification policy. So as to effectively improve the accuracy of the model. The model modification strategy can be that the target processing model is utilized to carry out iterative processing on the order reference information so as to adjust the parameters of the target processing model and determine the parameters corresponding to iterative convergence as final target processing model parameters.

In one embodiment of the invention, the processor configures a cross validation mechanism for the order reference information, and validates the generated expected order quantity through the cross validation mechanism. Through cross validation, the accuracy of the information processing result is effectively improved.

The Cross-Validation mechanism may be any one of simple Cross-Validation, S-fold Cross-Validation (S-Folder Cross Validation), and Leave-one-out Cross Validation. Wherein the content of the first and second substances,

simple cross-validation is to randomly divide the order reference information into two parts (e.g., 80% training set and 20% testing set), then train the target processing model with the training set, and validate the processing model and parameters on the testing set. Then, the order reference information is disturbed, the training set and the test set are reselected, and the order reference information is continuously trained and the target processing model is continuously checked. And finally, selecting a loss function to evaluate the optimal target processing model and parameters.

And S-fold cross validation is to randomly divide order reference information into S parts, randomly select S-1 parts as a training set each time, and make the rest 1 part as a test set. When this round is completed, S-1 shares are randomly selected again to train the data. After several rounds (less than S), a loss function is selected to evaluate the optimal process model and parameters.

And the step of leaving one order for cross validation refers to selecting orders in the N-1 order parameter information to train the processing model each time aiming at all the order numbers N in the order parameter information, and leaving one order to validate the quality of the processing model.

In one embodiment of the invention, as shown in FIG. 3, a processor 102 includes: a pre-processing sub-module 1021 and a feature processing sub-module 1022, wherein,

the preprocessing submodule 1021 is used for determining a data specification and a basic check, and correcting data included in the order reference information according to the data specification and the basic check so that the corrected data can meet the data specification;

the feature processing sub-module 1022 is configured to determine a feature extraction interface and a feature to be extracted, extract data corresponding to the feature to be extracted from the modified data by calling the feature extraction interface, and process the data corresponding to the feature to be extracted by calling at least one target processing model and a target information processing manner stored in the memory.

The determined data specification, the basic verification, the feature extraction interface and the feature to be extracted can be user-defined.

The data specification and the base check determined by the preprocessing submodule 1021 are described as an embodiment. For example, the order reference information includes historical orders, items, promotional data, inventory data. The specification of the time series data definition required for the time series model selected for information processing is shown in fig. 3, and the time series data includes order basic data, date dimension, start date, and expiration date. The historical orders, the promotion data and the stock data are inherited to the time sequence number data.

Table 1 and table 2 below illustrate one format specification for sales basis data such as historical orders and promotional data, respectively.

TABLE 1

TABLE 2

The basic check includes, but is not limited to, an integrity check and a correctness check. Integrity check is to check whether necessary fields are missing in the data, and correctness check is to check the data type, data specification, data loss, etc.

The characteristic extraction interface is a characteristic extraction standard interface.

It should be noted that the preprocessing submodule 1021 also needs to preprocess the data before the feature processing submodule 1022 performs feature extraction. The order reference information mentioned above may include the historical order data of table 1 and the promotion data of table 2, and accordingly, the preprocessing sub-module 102 may obtain different processing classes defined by the user for the historical order data and the promotion data, respectively, or the preprocessing sub-module 102 may directly call the processing classes stored in the memory for the historical order data and the promotion data. For example, for the pre-processing class of historical order data: inputs are order data, date granularity (day/week/month) in data, data start date, expiration date, data preprocessing logic: checking whether the fields and the input format of the input data are correct, and cleaning order data, such as character string spaces, null values, abnormal checking, field type conversion, date format processing, data aggregation and the like. And storing the cleaned data into an order object. For the promotion preprocessing class: the input is promotional data and the processing logic may be the same as the order data.

Correspondingly, the feature extraction mode defined by the user or the feature extraction mode stored in the memory selected by the user or the feature extraction mode stored in the memory automatically selected by the processor mainly extracts the features required by the training data for the preprocessed data. Such as: one specific example may be that the features that extract the order reference information may include historical sales features, date features, promotional features. For one processing class defined by the historical sales characteristics: the input is pre-processed sales data, and a special feature object is returned through a feature processing method, wherein the format of a feature data output field in the feature object can be shown in the following table 3:

TABLE 3

ds (date)	obj _ no (goods mark)	1 day in the past	Last 3 days	…	y (sales volume on the day)
						2019-01-01	s00001	1	2	…	3

As another example, for a process class defined by a date feature: the input is historical sales data, date characteristics are extracted, and the output format is shown in the following table 4:

TABLE 4

ds (date)	obj _ no (goods mark)	Whether it is over weekend	Week table	…	y (sales volume on the day)
						2019-01-01	s00001	0	2	…	3

One processing class defined for promotional features: the input is historical sales data, date features are extracted, and the output format is shown in the following table 5:

TABLE 5

ds (date)	obj _ no (goods mark)	Whether or not to promote sales	Type of promotion	…	y (sales volume on the day)
						2019-01-01	s00001	0	1 (full decrease)	…	3

And finally, combining the extracted features in a combining mode, and returning to all the finally combined features.

In summary, the processing requirements may include features to be extracted, granularity (days/weeks/months) corresponding to the expected number of orders, and a prediction length. In the calling information, logic, model fusion and the like of the expected order quantity can be designed and generated according to the actual scene. The invocation information may also define data length dependent logic such as using an exponential smoothed, simple average of the processing results when the data length is 3 months for an expected number of orders for a promotional campaign, using ARIMA, non-seasonal spatial state, simple exponential smoothed results average when the data length is greater than 3 months and less than 12 months, and using SARIMA, seasonal spatial state results average when the data length is greater than 12 months. The final output is the expected order quantity, which can be shown in table 6 below:

TABLE 6

ds (date)	obj _ no (goods mark)	True sales volume	Expected number of orders
				2019-01-01	s000001	0	1 (full decrease)

In order to clearly explain the information processing apparatus provided in the embodiment of the present invention, the information processing apparatus shown in fig. 4 is used to perform the expected number of orders, and the commodity layout, the inter-warehouse allocation, and the stock quantity derived based on the expected number of orders.

As shown in fig. 4, various basic models such as ETS, ARIMA, FBProphet, MLP, LSTM, RNN, linear/nonlinear regression, RF (immediate forest), GBDT (supervised promotion), various preset processing modes such as processing according to life cycle, processing according to new product, processing according to promotion exception, etc., product attributes such as new product, promoted product, large order, long-tailed product, industry feature, class, product sales level, etc. which can be selected by a user, and processing forms such as indirect processing, processing according to seasonality, etc. are stored in the memory 101, and a single-class product processing mode, a single-machine batch concurrence mode, a Spark market concurrence mode, a Docker concurrence mode, etc. may also be stored in the memory. The memory can also store packaged calling programs such as data cleaning, data conversion, feature extraction, feature combination, feature selection and the like. Various basic models, various preset processing modes, product attributes, processing forms and other various modes stored in the memory can be provided for a user through an interactive interface so as to be selected by the user. The processor 102 provides an interactive interface for a user, and the user implements any one or more of a custom model combination policy, an and processing policy for basic data, a pattern modification policy, a cross validation mechanism, a backtesting mechanism, a feature extraction mechanism, and the like through the interactive interface. The user-defined mode of each strategy can be that a user selects display modules of various models on an interactive interface, and sets corresponding calling logic or rules and the like for the selected modules. According to various policies defined by the user, the basic model stored in the memory can be called by calling each sub-interface in the interface 103, so as to realize information processing.

In addition, the information processing apparatus provided by the embodiment of the present invention may receive data related to order reference information manually imported by a user, and may also read the order reference information from other data sources, where the order reference information may include historical sales, product attributes, sales data, sales plans, new and old product relationships, and the like for a desired number of orders.

As shown in fig. 5, an embodiment of the present invention provides an information processing method, which may include the steps of:

s501: storing at least two processing models and at least two information processing modes;

s502: determining processing requirements for the order reference information;

s503: configuring calling information for the order reference information according to the order reference information and the processing requirements, wherein the calling information indicates at least one target processing model, a target information processing mode and a calling relation matched for the order reference information;

s504: according to the calling relation, calling at least one target processing model and at least one target information processing mode from at least two stored processing models and at least two stored information processing modes through a preset calling interface to process order reference information;

s505: a prospective order quantity is generated for processing the demand, and the prospective order quantity is output.

In an embodiment of the present invention, the information processing method may further include: storing at least one preset calling information; accordingly, the specific implementation of configuring and calling information for order reference information may include: receiving a processing request aiming at the order reference information, wherein the processing request indicates one kind of calling information selected from at least one preset calling information, and configuring the calling information indicated by the processing request for the order reference information.

In an embodiment of the present invention, the information processing method may further include: and configuring a model correction strategy for the order reference information, and correcting at least one target processing model according to the model correction strategy.

In an embodiment of the present invention, the information processing method may further include: and configuring a cross validation mechanism for the order reference information, and validating the generated expected order quantity through the cross validation mechanism.

In an embodiment of the present invention, the information processing method may further include: determining data specification, basic verification, a feature extraction interface and features to be extracted;

correcting data included in the order reference information according to the data specification and the basic verification so that the corrected data meet the data specification;

and extracting data corresponding to the features to be extracted from the corrected data by calling the feature extraction interface, and processing the data corresponding to the features to be extracted by calling at least one target processing model and a target information processing mode stored in the memory.

Fig. 6 shows an exemplary system architecture 600 to which an information processing apparatus or an information processing method of an embodiment of the present invention can be applied.

As shown in fig. 6, the system architecture 600 may include

terminal devices

601, 602, 603, a network 604, and a server 605. The network 604 serves to provide a medium for communication links between the

terminal devices

601, 602, 603 and the server 605. Network 604 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.

A user may use the

terminal devices

601, 602, 603 to interact with the server 605 via the network 604 to receive or send messages or the like. The

terminal devices

601, 602, 603 may have installed thereon various communication client applications, such as shopping applications, web browser applications, search applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).

The

terminal devices

601, 602, 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 605 may be a server providing various services, such as a background management server (for example only) providing support for pages browsed by a user using the

terminal devices

601, 602, 603. The backend management server may perform information processing according to various received policies and the like, and feed back a processing result (for example, a report showing an expected order quantity — just an example) to the terminal device.

It should be noted that the information processing method provided by the embodiment of the present invention is generally executed by the server 605, and accordingly, the information processing apparatus is generally provided in the server 605.

It should be understood that the number of terminal devices, networks, and servers in fig. 6 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Referring now to FIG. 7, a block diagram of a computer system 700 suitable for use with a server device implementing an embodiment of the invention is shown. The terminal device shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU)701, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data necessary for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

The following components are connected to the I/O interface 705: an input portion 706 including a keyboard, a mouse, and the like; an output section 707 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 708 including a hard disk and the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read out therefrom is mounted into the storage section 708 as necessary.

In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments disclosed herein include an information processing apparatus comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 709, and/or installed from the removable medium 711. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 701.

It should be noted that the computer readable medium involved in the present invention may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes a pre-processing sub-module and a feature processing sub-module. The names of these modules do not in some cases constitute a limitation to the module itself, and for example, the preprocessing sub-module may also be described as a "module that corrects data included in the order reference information".

As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: storing at least two processing models and at least two information processing modes; determining processing requirements for the order reference information; configuring calling information for the order reference information according to the order reference information and the processing requirement, wherein the calling information indicates at least one target processing model, a target information processing mode and a calling relation matched for the order reference information; according to the calling relation, calling the at least one target processing model and the target information processing mode from the at least two stored processing models and the at least two stored information processing modes through a preset calling interface to process the order reference information; generating a prospective order quantity for the processing demand, and outputting the prospective order quantity.

In addition, the computer readable medium carries one or more programs which, when executed by a device, cause the device to further include: storing at least one preset calling information; correspondingly, the specific implementation of configuring the call information for the order reference information includes: receiving a processing request aiming at the order reference information, wherein the processing request indicates one kind of calling information selected from the at least one preset calling information, and configuring the calling information indicated by the processing request for the order reference information.

In addition, the computer readable medium carries one or more programs which, when executed by a device, cause the device to further include: and configuring a model correction strategy for the order reference information, and correcting the at least one target processing model according to the model correction strategy.

In addition, the computer readable medium carries one or more programs which, when executed by a device, cause the device to further include: configuring a cross validation mechanism for the order reference information, and validating the generated expected order quantity through the cross validation mechanism.

In addition, the computer readable medium carries one or more programs which, when executed by a device, cause the device to further include: determining data specification, basic verification, a feature extraction interface and features to be extracted;

According to the technical scheme of the embodiment of the invention, aiming at least two processing models and at least two information processing modes stored in the memory, the processor can determine the processing requirements for the order reference information, and at least one target processing model, a target information processing mode and a calling relation are matched according to the processing requirements and the order reference information, so that the flexible configuration of the processing models according to the order reference information is realized. In addition, since the processing model directly affects the accuracy of the generated expected order quantity, and the target processing model, the target information processing method and the call relation obtained according to the processing requirement and the order reference information are used in the embodiment of the present invention, the information processing apparatus provided in the embodiment of the present invention can ensure the accuracy of the generated expected order quantity.

In addition, according to the technical scheme of the embodiment of the invention, the processing model and the information processing mode can be configured according to the order reference information, so that the calling information is closer to the requirement of the expected order quantity, namely, the processing process is perfectly fused with the scene, and the accuracy of the processing result can be effectively improved. In addition, the memory can further store at least one preset calling message; the processor can directly process the order reference information according to the selected calling information to generate the corresponding expected order quantity, and the flexibility of information processing is further improved.

In the embodiment provided by the invention, the memory stores various processing models, and the calling information can select various models and calling sequences of the various models, so that the processing models have diversity and the defect of processing information by a single model is overcome.

In the embodiment of the invention, the preprocessing processes such as the feature extraction process, the data cleaning process and the like are modularized, and a user can call the modularized data preprocessing processes by setting corresponding configurations for the modularized data preprocessing processes, so that the modularized data preprocessing processes can be repeatedly used.

In addition, the embodiment of the invention standardizes the data, so that the input, the output, the parameters and the like of each model can be mutually called.

The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An information processing apparatus characterized by comprising: a memory, a processor, and a call interface, wherein,

the processor is configured to determine a processing requirement for order reference information, configure calling information for the order reference information according to the order reference information and the processing requirement, where the calling information indicates at least one target processing model, a target information processing mode, and a calling relationship matched for the order reference information, and according to the calling relationship, call the at least one target processing model and the target information processing mode stored in the memory through the calling interface to process the order reference information, generate an expected order quantity for the processing requirement, and output the expected order quantity.

2. The information processing apparatus according to claim 1,

the memory is further used for storing at least one preset calling message;

3. The information processing apparatus according to claim 1, wherein the call interface includes: a model calling sub-interface corresponding to each processing model and a processing mode calling sub-interface corresponding to each information processing mode;

4. The information processing apparatus according to claim 1,

5. The information processing apparatus according to claim 1 or 4,

6. The information processing apparatus according to any one of claims 1 to 4, wherein the processor includes: a pre-processing sub-module and a feature processing sub-module, wherein,

7. An information processing method characterized by comprising:

further comprising:

determining processing requirements for the order reference information;

8. The information processing method according to claim 7, further comprising:

storing at least one preset calling information;

9. The information processing method according to claim 7,

further comprising: configuring a model correction strategy for the order reference information, and correcting the at least one target processing model according to the model correction strategy;

and/or the presence of a gas in the gas,

further comprising: configuring a cross validation mechanism for the order reference information, and validating the generated expected order quantity through the cross validation mechanism.

10. The information processing method according to any one of claims 7 to 9, characterized by further comprising:

11. An information processing electronic device characterized by comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 7-10.

12. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 7-10.