Demand information generation method, demand data prediction method, device and equipment

Abstract

The embodiment of the invention discloses a demand information generation method, a demand data prediction method, a demand information generation device and demand data prediction equipment. A specific embodiment of the method comprises the steps of obtaining a demand data sequence; for each piece of demand data in the demand data sequence, executing the following updating steps: generating first user real demand data under the time corresponding to the demand data by using the first initial event demand influence parameter; generating real demand data of a second user by using the initial demand trend parameter; using the second initial event demand influence parameter to generate demand prediction data under the time corresponding to the target demand data; and according to the demand prediction data and the target demand data, performing parameter gradient updating on the initial demand trend parameter, the first initial event demand influence parameter and the second initial event demand influence parameter to generate a demand parameter information set. The implementation mode is related to the intelligent supply chain, and the demand data in the preset time can be accurately generated by utilizing the obtained demand parameter information set.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a demand information generating method, a demand data forecasting method, a device, and a device. Background Art

[0002] At present, in various fields and industries, the prediction of user demand has become an important concern. The obtained user demand prediction data can realize the precise regulation of traffic to improve the user experience. The method usually adopted for generating user demand prediction data is: through the historical user demand data sequence, the future demand prediction neural network model is used to generate user demand prediction data in the future time.

[0003] However, the inventors have found that when the above method is used to generate user demand forecast data, the following technical problems often occur:

[0004] Over-reliance on the demand change trends of historical user demand data series over the past period of time makes it difficult to cope with the explosive growth in demand during special events, resulting in inaccurate user demand forecast data.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. 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 demand information generation methods, demand data prediction methods, devices and equipment to solve 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 generating demand information, comprising: obtaining a demand data sequence for a predefined event sequence; for each demand data in the above demand data sequence, performing the following update steps: using the first initial event demand influence parameter for the above demand data to generate the first user real demand data at the corresponding time of the above demand data; based on the above first user real demand data, using the initial demand trend parameter for the target demand data to generate the second user real demand data at the corresponding time of the target demand data, wherein the corresponding time of the above target demand data is the next time of the corresponding time of the above demand data; based on the above second user real demand data, using the second initial event demand influence parameter for the above target demand data to generate the demand forecast data at the corresponding time of the above target demand data; based on the above demand forecast data and the above target demand data, performing parameter gradient update on the above initial demand trend parameter, the above first initial event demand influence parameter and the above second initial event demand influence parameter to generate a demand parameter information set.

[0009] Optionally, the predefined events in the above-mentioned predefined event sequence have a corresponding event demand impact time range; and the above-mentioned use of the first initial event demand impact parameter for the above-mentioned demand data to generate the first user real demand data at the corresponding time of the above-mentioned demand data includes: in response to determining that the corresponding time of the above-mentioned demand data is within the event demand impact time range corresponding to the target predefined event, the addition result of the above-mentioned first initial event demand impact parameter and the target numerical value is determined as the first addition information; and the division result of the above-mentioned demand data and the above-mentioned first addition information is determined as the first user real demand data.

[0010] Optionally, the method further includes: in response to determining that the time corresponding to the demand data is not within the event demand impact time range corresponding to the target predefined event, determining the demand data as the real demand data of the first user.

[0011] Optionally, the above-mentioned demand forecast data for the time corresponding to the target demand data is generated based on the above-mentioned second user's actual demand data and using the second initial event demand impact parameter for the above-mentioned target demand data, including: in response to determining that the time corresponding to the above-mentioned demand data is within the event demand impact time range corresponding to the target predefined event, the addition result of the above-mentioned second initial event demand impact parameter and the target numerical value is determined as the second addition information; and the multiplication result of the above-mentioned second addition information and the above-mentioned second user's actual demand data is determined as the demand forecast data.

[0012] Optionally, based on the above-mentioned first user's real demand data and utilizing the initial demand trend parameters for the above-mentioned target demand data, the above-mentioned real demand data of the second user at the time corresponding to the above-mentioned target demand data is generated, including: multiplying the above-mentioned initial demand trend parameters by the above-mentioned target demand data to determine the real demand data of the second user.

[0013] Optionally, the predefined events in the above-mentioned predefined event sequence have corresponding event demand impact range mask parameters; and the above-mentioned use of the first initial event demand impact parameters for the above-mentioned demand data to generate the first user real demand data at the corresponding time of the above-mentioned demand data includes: multiplying the above-mentioned event demand impact range mask parameters with the above-mentioned first initial event demand impact parameters to determine the first multiplication result; adding the first multiplication result and the target numerical value to obtain third addition information; and determining the division result of the above-mentioned demand data and the above-mentioned third addition information as the first user real demand data.

[0014] Optionally, the above-mentioned demand forecast data for the time corresponding to the above-mentioned target demand data is generated based on the above-mentioned second user's actual demand data and using the second initial event demand impact parameter for the above-mentioned target demand data, including: obtaining a second multiplication result by multiplying the above-mentioned event demand impact range mask parameter with the above-mentioned second initial event demand impact parameter; obtaining fourth addition information by adding the above-mentioned second multiplication result and the target numerical value; and determining the multiplication result of the above-mentioned fourth addition information and the above-mentioned second user's actual demand data as the demand forecast data.

[0015] Optionally, the above-mentioned initial demand trend parameters, the above-mentioned first initial event demand impact parameters and the above-mentioned second initial event demand impact parameters are updated with parameter gradients according to the above-mentioned demand forecast data and the above-mentioned target demand data to obtain a demand parameter information set, including: according to the above-mentioned demand forecast data and the above-mentioned target demand data, the above-mentioned initial demand trend parameters, the above-mentioned first initial event demand impact parameters, the above-mentioned event demand impact range mask parameters and the above-mentioned second initial event demand impact parameters are updated with parameter gradients to obtain first updated event demand impact parameter information, second updated event demand impact parameter information, demand trend parameter information and event demand impact range mask parameter information.

[0016] In a second aspect, some embodiments of the present disclosure provide a demand information generating device, comprising: a first acquisition unit, configured to acquire a demand data sequence for a predefined event sequence; an execution unit, configured to perform the following update steps for each demand data in the above demand data sequence: using the first initial event demand influence parameter for the above demand data to generate the first user real demand data at the corresponding time of the above demand data; based on the above first user real demand data, using the initial demand trend parameter for the target demand data to generate the second user real demand data at the corresponding time of the above target demand data, wherein the corresponding time of the above target demand data is the next time of the corresponding time of the above demand data; based on the above second user real demand data, using the second initial event demand influence parameter for the above target demand data to generate the demand forecast data at the corresponding time of the above target demand data; based on the above demand forecast data and the above target demand data, performing parameter gradient update on the above initial demand trend parameter, the above first initial event demand influence parameter and the above second initial event demand influence parameter to generate a demand parameter information set.

[0017] Optionally, the predefined events in the above-mentioned predefined event sequence have a corresponding event demand impact time range; and the execution unit can be configured to: in response to determining that the time corresponding to the above-mentioned demand data is within the event demand impact time range corresponding to the target predefined event, determine the addition result of the above-mentioned first initial event demand impact parameter and the target numerical value as the first addition information; and determine the division result of the above-mentioned demand data and the above-mentioned first addition information as the first user's actual demand data.

[0018] Optionally, the execution unit may be configured to: in response to determining that the time corresponding to the demand data is not within the event demand impact time range corresponding to the target predefined event, determine the demand data as the real demand data of the first user.

[0019] Optionally, the execution unit can be configured to: in response to determining that the time corresponding to the above-mentioned demand data is within the event demand impact time range corresponding to the target predefined event, determine the addition result of the above-mentioned second initial event demand impact parameter and the target numerical value as the second addition information; and determine the multiplication result of the above-mentioned second addition information and the above-mentioned second user actual demand data as the demand forecast data.

[0020] Optionally, the execution unit may be configured to: determine the result of multiplying the above initial demand trend parameter and the above target demand data as the real demand data of the second user.

[0021] Optionally, the predefined events in the above-mentioned predefined event sequence have corresponding event demand impact range mask parameters; and the execution unit can be configured to: determine the multiplication result of the above-mentioned event demand impact range mask parameter and the above-mentioned first initial event demand impact parameter as the first multiplication result; add the first multiplication result and the target numerical value to obtain third addition information; and determine the division result of the above-mentioned demand data and the above-mentioned third addition information as the first user's actual demand data.

[0022] Optionally, the execution unit can be configured to: multiply the above-mentioned event demand impact range mask parameter with the above-mentioned second initial event demand impact parameter to obtain a second multiplication result; add the above-mentioned second multiplication result and the target value to obtain fourth addition information; and multiply the above-mentioned fourth addition information with the above-mentioned second user actual demand data to determine the demand forecast data.

[0023] Optionally, the execution unit can be configured to: perform parameter gradient update on the above-mentioned initial demand trend parameters, the above-mentioned first initial event demand impact parameters, the above-mentioned event demand impact range mask parameters and the above-mentioned second initial event demand impact parameters according to the above-mentioned demand forecast data and the above-mentioned target demand data, and obtain the first updated event demand impact parameter information, the second updated event demand impact parameter information, the demand trend parameter information and the event demand impact range mask parameter information.

[0024] In a third aspect, some embodiments of the present disclosure provide a demand data forecasting method, including: obtaining historical demand data and a demand parameter information set sequence corresponding to a target time, wherein the demand parameter information set sequence is generated based on a demand information generation method; and generating demand forecasting data for a target future time based on the historical demand data and the demand parameter information set sequence.

[0025] In a fourth aspect, some embodiments of the present disclosure provide a demand data prediction device, comprising: a second acquisition unit, configured to acquire historical demand data and a demand parameter information set sequence corresponding to a target time, wherein the above-mentioned demand parameter information set sequence is generated based on a demand information generation method; and a generation unit, configured to generate demand prediction data for a target future time based on the above-mentioned historical demand data and the above-mentioned demand parameter information set sequence.

[0026] In a fifth aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any one of the implementation methods in the first and third aspects.

[0027] In a sixth 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, the method described in any one of the implementation modes of the first aspect and the third aspect is implemented.

[0028] In a seventh aspect, some embodiments of the present disclosure provide a computer program product, including a computer program, which, when executed by a processor, implements the method described in any one of the implementation modes of the first and third aspects above.

[0029] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the demand information generation method of some embodiments of the present disclosure, the demand data at the preset time can be accurately generated by using the obtained demand parameter information set. Specifically, the reason why the demand data at the relevant preset time is not accurate is that it is overly dependent on the demand change trend of the historical user demand data sequence in the past period of time, which is difficult to cope with the explosive growth of demand during special events, resulting in the obtained user demand forecast data (i.e., the demand data at the preset time) is not accurate enough. Based on this, the demand information generation method of some embodiments of the present disclosure, first, obtains the demand data sequence for the predefined event sequence for subsequent parameter update of related demand parameters. Then, for each demand data in the above demand data sequence, the following update steps are performed: the first step is to use the first initial event demand impact parameter for the above demand data to accurately generate the first user real demand data at the corresponding time of the above demand data. The obtained first user real demand data is used for the subsequent update of related demand parameters. The second step is to use the initial demand trend parameter for the target demand data according to the above first user real demand data, and accurately generate the second user real demand data at the corresponding time of the above target demand data. Among them, the time corresponding to the above-mentioned target demand data is the next time of the time corresponding to the above-mentioned demand data. The obtained real demand data of the second user is used for the subsequent update of relevant demand parameters. The third step is to accurately generate the demand forecast data at the corresponding time of the above-mentioned target demand data based on the real demand data of the second user and the second initial event demand impact parameter for the above-mentioned target demand data. The difference between the obtained demand forecast data and the target demand data is compared for the subsequent update of relevant demand parameters. The fourth step is to update the parameter gradient of the above-mentioned initial demand trend parameters, the above-mentioned first initial event demand impact parameters and the above-mentioned second initial event demand impact parameters according to the above-mentioned demand forecast data and the above-mentioned target demand data to generate a demand parameter information set. The obtained demand parameter information set can be used to accurately generate demand data at a preset time. In summary, through the parameter update of the relevant demand parameters, not only can the solution of the demand be explicitly displayed, but also the prediction of the explosive growth of demand during special events can be accurately realized, which greatly improves the accuracy of demand forecasting. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] 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 that components and elements are not necessarily drawn to scale.

[0031] Figure 1 is a schematic diagram of an application scenario of a method for generating demand information according to some embodiments of the present disclosure;

[0032] Figure 2 is a flow chart of some embodiments of the method for generating demand information according to the present disclosure;

[0033] Figure 3 are flow charts of other embodiments of the method for generating demand information according to the present disclosure;

[0034] Figure 4 is a flow chart of some embodiments of the demand data forecasting method according to the present disclosure;

[0035] Figure 5 is a schematic diagram of the structure of some embodiments of the demand information generating device according to the present disclosure;

[0036] Figure 6 is a schematic diagram of the structure of some embodiments of the demand data prediction device according to the present disclosure;

[0037] Figure 7 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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".

[0042] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0043] With regard to the collection, storage, and use of data (such as demand data) involved in this disclosure, before performing corresponding operations, relevant organizations or individuals shall fulfill obligations including conducting data security impact assessments, fulfilling the obligation to inform the data subject, and obtaining the authorization and consent of the data subject in advance.

[0044] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0045] Figure 1 It is a schematic diagram of an application scenario of the method for generating demand information according to some embodiments of the present disclosure.

[0046] exist Figure 1In the application scenario, first, the electronic device 101 can obtain a demand data sequence 102 for a predefined event sequence. In this application scenario, the demand data sequence 102 includes: demand data 1021 and demand data 1022. Then, for each demand data in the above demand data sequence 102, the electronic device 101 can perform the following update steps: First, using the first initial event demand impact parameter 103 for the above demand data 1021, generate the first user real demand data 104 at the corresponding time of the above demand data 1021. Second, based on the above first user real demand data 104, using the initial demand trend parameter 105 for the target demand data 1022, generate the second user real demand data 106 at the corresponding time of the above target demand data 1022. Among them, the corresponding time of the above target demand data 1022 is the next time of the corresponding time of the above demand data 1021. The third step is to generate the demand forecast data 108 at the time corresponding to the target demand data 1022 according to the second user real demand data 106 and the second initial event demand impact parameter 107 for the target demand data 1022. The fourth step is to perform parameter gradient update on the initial demand trend parameter 105, the first initial event demand impact parameter 103 and the second initial event demand impact parameter 107 according to the demand forecast data 108 and the target demand data 1022 to generate a demand parameter information set 109.

[0047] It should be noted that the electronic device 101 can be hardware or software. When the electronic device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the electronic device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.

[0048] It should be understood that Figure 1 The number of electronic devices in the embodiment is only for illustration. Any number of electronic devices may be provided according to implementation requirements.

[0049] Continue to refer Figure 2 , shows a process 200 of some embodiments of the method for generating demand information according to the present disclosure. The method for generating demand information comprises the following steps:

[0050] Step 201: Obtain a demand data sequence for a predefined event sequence.

[0051] In some embodiments, the execution subject of the above demand information generation method (for example Figure 1The electronic device 101 shown) can obtain a demand data sequence for a predefined event sequence through a wired connection or a wireless connection. Among them, the predefined event sequence may include multiple predefined events that exist in a chronological order. The predefined event may be an event that affects user demand. Specifically, the predefined event may be a holiday event or a promotional event. For example, the predefined event sequence may include: Spring Festival events, Qingming Festival events, New Year's Day events, Labor Day events, National Day events, and Mid-Autumn Festival events. The demand data sequence may be a historical demand data set for the target item. The demand data sequence contains a demand data subsequence corresponding to the predetermined event sequence. That is, the time period corresponding to the predefined event sequence is a sub-time period of the time period corresponding to the demand data sequence. In practice, the demand data sequence may be each demand data for each day of the year (including holidays).

[0052] Step 202: for each demand data in the demand data sequence, perform the following update steps:

[0053] Step 2021: Generate first user real demand data at a time corresponding to the above demand data by using the first initial event demand impact parameter for the above demand data.

[0054] In some embodiments, the execution entity may generate the first user real demand data at the time corresponding to the demand data using the first initial event demand impact parameter for the demand data. The first initial event demand impact parameter may be a demand parameter to be updated that characterizes the degree of influence of a predefined event on demand. In practice, the larger the first initial event demand impact parameter, the greater the degree of influence of the predefined event on demand. The time corresponding to the demand data may be the demand time corresponding to the demand item. For example, the demand time may be the order time of the demand item or the order time of the demand item. The demand item may be the required item corresponding to the demand data. For example, the demand item may be an ordered item. The first user real demand data may be the predicted demand for the user's item at the demand time corresponding to the demand item. In practice, the demand for the user's item may be the order quantity required by the user.

[0055] In some optional implementations of some embodiments, there is a corresponding event demand impact time range for the predefined events in the above-mentioned predefined event sequence. The event demand impact time range can represent the time range of the impact of the predefined event on the demand. The above-mentioned event demand impact time range can be a pre-set time range. For example, if the predefined event is New Year's Day, the event demand impact time range can be "7 days before New Year's Day - 7 days after New Year's Day".

[0056] Optionally, the step of using the first initial event demand impact parameter for the demand data to generate the first user real demand data at a time corresponding to the demand data may include the following steps:

[0057] In the first step, in response to determining that the time corresponding to the above-mentioned demand data is within the event demand impact time range corresponding to the target predefined event, the addition result of the above-mentioned first initial event demand impact parameter and the target value is determined as the first addition information. The target predefined event may be a predefined event corresponding to the demand data. For example, if the demand data is demand data during the New Year's Day, then the target predefined event is New Year's Day. The above-mentioned target value may be a pre-set value. For example, the target value may be "1".

[0058] In a second step, the execution entity may determine the result of dividing the demand data by the first added information as the real demand data of the first user.

[0059] As an example, the execution entity may divide the demand data by the first added information to determine the result as the real demand data of the first user.

[0060] Optionally, in response to determining that the time corresponding to the above-mentioned demand data is not within the event demand impact time range corresponding to the target predefined event, the above-mentioned execution entity may determine the above-mentioned demand data as the real demand data of the first user.

[0061] Step 2022: Based on the above-mentioned first user's real demand data, using the initial demand trend parameters for the target demand data, generate the second user's real demand data at the time corresponding to the above-mentioned target demand data.

[0062] In some embodiments, the execution subject may generate the real demand data of the second user at the time corresponding to the target demand data according to the real demand data of the first user and using the initial demand trend parameters for the target demand data. The time corresponding to the target demand data is the next time of the time corresponding to the demand data. The time corresponding to each demand data in the demand data sequence is continuous. The initial demand trend parameter may be a parameter to be updated at the time corresponding to the target demand data, used to characterize the changing trend of the demand at the time corresponding to the demand data and the time corresponding to the target demand data. The time corresponding to the real demand data of the second user is different from that corresponding to the real demand data of the first user.

[0063] For example, the demand data sequence includes: first demand data and second demand data. The time corresponding to the first demand data is January 1. The time corresponding to the second demand data is January 2. The first demand data is the demand data. The second demand data is the target demand data.

[0064] As an example, the execution subject may input the first user's real demand data and the initial demand trend parameter into the demand data prediction model to generate the second user's real demand data. In practice, the demand data prediction model may be a time series neural network model.

[0065] In some optional implementations of some embodiments, the execution entity may determine the result of multiplying the initial demand trend parameter by the target demand data as the real demand data of the second user.

[0066] Step 2023: Based on the second user's actual demand data, using the second initial event demand impact parameter for the target demand data, generate demand forecast data for the time corresponding to the target demand data.

[0067] In some embodiments, the execution subject may generate demand forecast data at a time corresponding to the target demand data based on the second user's real demand data and using the second initial event demand impact parameter for the target demand data. The second initial event demand impact parameter corresponds to a different time than the first initial event demand impact parameter. That is, it indicates that each demand data has a corresponding initial event demand impact parameter to be updated.

[0068] As an example, the execution entity may directly multiply the second initial event demand impact parameter by the second user's actual demand data to obtain demand forecast data at a time corresponding to the target demand data.

[0069] In some optional implementations of some embodiments, the generating of demand forecast data at a time corresponding to the target demand data according to the second user real demand data and using the second initial event demand impact parameter for the target demand data may include the following steps:

[0070] In the first step, in response to determining that the time corresponding to the demand data is within the event demand impact time range corresponding to the target predefined event, the execution entity may determine the sum of the second initial event demand impact parameter and the target value as the second added value. In practice, the target value may be "1".

[0071] In a second step, the execution entity may determine the product of the second added value and the second user's actual demand data as demand forecast data.

[0072] Step 2024, based on the above-mentioned demand forecast data and the above-mentioned target demand data, the above-mentioned initial demand trend parameters, the above-mentioned first initial event demand impact parameters and the above-mentioned second initial event demand impact parameters are updated with parameter gradients to generate a demand parameter information set.

[0073] In some embodiments, the execution entity may perform parameter gradient update on the initial demand trend parameters, the first initial event demand impact parameters and the second initial event demand impact parameters according to the demand forecast data and the target demand data to generate a demand parameter information set.

[0074] As an example, first, the execution subject may use the target loss function to determine the data difference between the demand forecast data and the target demand data to obtain data difference information. Then, based on the data difference information, the initial demand trend parameter, the first initial event demand impact parameter, and the second initial event demand impact parameter are updated with parameter gradients using the solution process corresponding to the initial demand trend parameter, the solution process corresponding to the first initial event demand impact parameter, and the solution process corresponding to the second initial event demand impact parameter to generate a demand parameter information set.

[0075] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the demand information generation method of some embodiments of the present disclosure, the demand data at the preset time can be accurately generated by using the obtained demand parameter information set. Specifically, the reason why the demand data at the relevant preset time is not accurate is that it is overly dependent on the demand change trend of the historical user demand data sequence in the past period of time, which is difficult to cope with the explosive growth of demand during special events, resulting in the obtained user demand forecast data (i.e., the demand data at the preset time) is not accurate enough. Based on this, the demand information generation method of some embodiments of the present disclosure, first, obtains the demand data sequence for the predefined event sequence for subsequent parameter update of related demand parameters. Then, for each demand data in the above demand data sequence, the following update steps are performed: the first step is to use the first initial event demand impact parameter for the above demand data to accurately generate the first user real demand data at the corresponding time of the above demand data. The obtained first user real demand data is used for the subsequent update of related demand parameters. The second step is to use the initial demand trend parameter for the target demand data according to the above first user real demand data, and accurately generate the second user real demand data at the corresponding time of the above target demand data. Among them, the time corresponding to the above-mentioned target demand data is the next time of the time corresponding to the above-mentioned demand data. The obtained real demand data of the second user is used for the subsequent update of relevant demand parameters. The third step is to accurately generate the demand forecast data at the corresponding time of the above-mentioned target demand data based on the real demand data of the second user and the second initial event demand impact parameter for the above-mentioned target demand data. The difference between the obtained demand forecast data and the target demand data is compared for the subsequent update of relevant demand parameters. The fourth step is to update the parameter gradient of the above-mentioned initial demand trend parameters, the above-mentioned first initial event demand impact parameters and the above-mentioned second initial event demand impact parameters according to the above-mentioned demand forecast data and the above-mentioned target demand data to obtain a demand parameter information set. The obtained demand parameter information set can be used to accurately generate demand data at a preset time. In summary, through the parameter update of relevant demand parameters, not only can the solution of demand be explicitly displayed, but also the prediction of explosive growth of demand during special events can be accurately realized, which greatly improves the accuracy of demand forecasting.

[0076] Further references Figure 3 , shows a process 300 of another embodiment of the method for generating demand information according to the present disclosure. The method for generating demand information includes the following steps:

[0077] Step 301: Obtain a demand data sequence for a predefined event sequence.

[0078] Step 302: for each demand data in the demand data sequence, perform the following update steps:

[0079] Step 3021: determine the multiplication result of the event demand impact range mask parameter and the first initial event demand impact parameter as the first multiplication result.

[0080] In some embodiments, an execution entity (e.g. Figure 1 The electronic device 101 shown may determine the multiplication result of the event requirement impact range mask parameter and the first initial event requirement impact parameter as the first multiplication result. The predefined events in the predefined event sequence have corresponding event requirement impact range mask parameters.

[0081] Step 3022, determining the addition result of the first multiplication result and the target value as the third addition information.

[0082] In some embodiments, the execution subject may determine the addition result of the first multiplication result and the target value as the third addition information. In practice, the target value may be a preset value. For example, the target value may be "1".

[0083] Step 3023: determine the actual demand data of the first user as the result of dividing the demand data by the third added information.

[0084] In some embodiments, the execution entity may divide the demand data by the third added information to obtain the actual demand data of the first user.

[0085] Step 3024: Based on the above-mentioned first user's real demand data, using the initial demand trend parameters for the target demand data, generate the second user's real demand data at the time corresponding to the above-mentioned target demand data.

[0086] Step 3025: Multiply the event demand impact range mask parameter by the second initial event demand impact parameter to obtain a second multiplication result.

[0087] In some embodiments, the execution entity may obtain a second multiplication result by multiplying the event demand impact range mask parameter with the second initial event demand impact parameter.

[0088] Step 3026, adding the second multiplication result and the target value to obtain fourth addition information.

[0089] In some embodiments, the execution entity may obtain fourth addition information by adding the second multiplication result to the target value.

[0090] Step 3027: Determine the demand forecast data as the multiplication result of the fourth added information and the second user's actual demand data.

[0091] In some embodiments, the execution entity may determine the demand forecast data as a result of multiplying the fourth addition information by the second user's actual demand data.

[0092] Step 3028, based on the above-mentioned demand forecast data and the above-mentioned target demand data, the above-mentioned initial demand trend parameters, the above-mentioned first initial event demand impact parameters, the above-mentioned event demand impact range mask parameters and the above-mentioned second initial event demand impact parameters are updated with parameter gradients to obtain the first updated event demand impact parameter information, the second updated event demand impact parameter information, the demand trend parameter information and the event demand impact range mask parameter information.

[0093] In some embodiments, the above-mentioned execution entity can perform parameter gradient update on the above-mentioned initial demand trend parameters, the above-mentioned first initial event demand impact parameters, the above-mentioned event demand impact range mask parameters and the above-mentioned second initial event demand impact parameters according to the above-mentioned demand forecast data and the above-mentioned target demand data, and obtain the first updated event demand impact parameter information, the second updated event demand impact parameter information, the demand trend parameter information and the event demand impact range mask parameter information.

[0094] As an example, first, the execution subject can use the target loss function to determine the data difference between the demand forecast data and the target demand data to obtain data difference information. Then, based on the data difference information, the initial demand trend parameter, the first initial event demand impact parameter, the event demand impact range mask parameter, the event demand impact range mask parameter, and the second initial event demand impact parameter are updated with parameter gradients using the solution process corresponding to the initial demand trend parameter, the first initial event demand impact parameter, the event demand impact range mask parameter, and the second initial event demand impact parameter to obtain a demand parameter information set.

[0095] In some embodiments, the specific implementation of steps 301 and 3024 and the technical effects thereof can be referred to in Figure 2 Steps 201 and 2022 in the corresponding embodiment are not described in detail here.

[0096] from Figure 3 It can be seen that Figure 2 Compared with the description of some corresponding embodiments, Figure 3In the corresponding process 300 of the demand information generation method in some embodiments, by updating the mask parameters of the event demand impact range, the accuracy of the event demand impact range is greatly improved, and the obtained demand parameter information set is more accurate, so that the demand data under the preset time can be generated more accurately.

[0097] Continue to refer Figure 4 , shows a process 400 of some embodiments of the demand data forecasting method according to the present disclosure. The demand data forecasting method comprises the following steps:

[0098] Step 401, obtaining historical demand data and demand parameter information set sequence corresponding to the target time.

[0099] In some embodiments, the execution entity of the above demand data prediction method (for example Figure 1 The electronic device 101 shown can obtain the historical demand data and demand parameter information set sequence corresponding to the target time by wired or wireless means. The above-mentioned demand parameter information set sequence is generated based on the demand information generation method. Specifically, the target time can be the current time. The historical demand data can be the demand data before the current time. For example, the current time is January 2. Then the historical demand data can be the demand data corresponding to January 1.

[0100] Step 402: Generate demand forecast data for a target future time based on the above historical demand data and the above demand parameter information set sequence.

[0101] In some embodiments, the execution entity may generate demand forecast data for a target future time based on the historical demand data and the demand parameter information set sequence. The target future time may be a time after the target time. For example, if the target time is January 2, the target future time may be January 3.

[0102] As an example, first, the execution subject may determine at least one demand parameter information set for the target future time and the target time. Then, based on the generation of demand forecast data in the demand information generation method, demand forecast data corresponding to each time from the target time to the target future time is generated in sequence. Among them, each time includes the target future time.

[0103] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the demand data prediction method of some embodiments of the present disclosure, demand prediction data for a target future time can be accurately generated.

[0104] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a demand information generating device, and these device embodiments are Figure 2 Corresponding to the method embodiments shown, the demand information generating device can be specifically applied to various electronic devices.

[0105] like Figure 5 As shown, a demand information generating device 500 includes: a first acquisition unit 501 and an execution unit 502. The first acquisition unit 501 is configured to acquire a demand data sequence for a predefined event sequence; the execution unit 502 is configured to perform the following update steps for each demand data in the demand data sequence: using the first initial event demand impact parameter for the demand data, generating the first user real demand data at the corresponding time of the demand data; based on the first user real demand data, using the initial demand trend parameter for the target demand data, generating the second user real demand data at the corresponding time of the target demand data, wherein the corresponding time of the target demand data is the next time of the corresponding time of the demand data; based on the second user real demand data, using the second initial event demand impact parameter for the target demand data, generating the demand forecast data at the corresponding time of the target demand data; based on the demand forecast data and the target demand data, performing parameter gradient update on the initial demand trend parameter, the first initial event demand impact parameter and the second initial event demand impact parameter to generate a demand parameter information set.

[0106] In some optional implementations of some embodiments, there is a corresponding event demand impact time range for the predefined events in the above-mentioned predefined event sequence; and the execution unit 502 can be further configured to: in response to determining that the time corresponding to the above-mentioned demand data is within the event demand impact time range corresponding to the target predefined event, the addition result of the above-mentioned first initial event demand impact parameter and the target numerical value is determined as the first addition information; and the division result of the above-mentioned demand data and the above-mentioned first addition information is determined as the first user's actual demand data.

[0107] In some optional implementations of some embodiments, the execution unit 502 may be further configured to: in response to determining that the time corresponding to the above-mentioned demand data is not within the event demand impact time range corresponding to the target predefined event, determine the above-mentioned demand data as the real demand data of the first user.

[0108] In some optional implementations of some embodiments, the execution unit 502 can be further configured to: in response to determining that the time corresponding to the above-mentioned demand data is within the event demand impact time range corresponding to the target predefined event, determine the addition result of the above-mentioned second initial event demand impact parameter and the target numerical value as the second addition information; and determine the multiplication result of the above-mentioned second addition information and the above-mentioned second user actual demand data as the demand forecast data.

[0109] In some optional implementations of some embodiments, the execution unit 502 may be further configured to: determine the result of multiplying the above-mentioned initial demand trend parameter and the above-mentioned target demand data as the second user's real demand data.

[0110] In some optional implementations of some embodiments, the predefined events in the above-mentioned predefined event sequence have corresponding event demand impact range mask parameters; and the execution unit 502 can be further configured to: determine the multiplication result of the above-mentioned event demand impact range mask parameter and the above-mentioned first initial event demand impact parameter as the first multiplication result; determine the addition result of the first multiplication result and the target numerical value as the third addition information; and determine the division result of the above-mentioned demand data and the above-mentioned third addition information as the first user's actual demand data.

[0111] In some optional implementations of some embodiments, the execution unit 502 can be further configured to: obtain a second multiplication result by multiplying the above-mentioned event demand impact range mask parameter with the above-mentioned second initial event demand impact parameter; obtain fourth addition information by adding the above-mentioned second multiplication result with the target value; and determine the multiplication result of the above-mentioned fourth addition information with the above-mentioned second user actual demand data as demand forecast data.

[0112] In some optional implementations of some embodiments, the execution unit 502 can be further configured to: perform parameter gradient update on the above-mentioned initial demand trend parameters, the above-mentioned first initial event demand impact parameters, the above-mentioned event demand impact range mask parameters and the above-mentioned second initial event demand impact parameters according to the above-mentioned demand forecast data and the above-mentioned target demand data, and obtain the first updated event demand impact parameter information, the second updated event demand impact parameter information, the demand trend parameter information and the event demand impact range mask parameter information.

[0113] It can be understood that the units recorded in the demand information generating device 500 are similar to those in the reference Figure 2 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the demand information generating device 500 and the units included therein, and will not be described in detail here.

[0114] Further references Figure 6 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a demand data forecasting device. These device embodiments are similar to Figure 4 Corresponding to the method embodiments shown, the demand data prediction device can be specifically applied to various electronic devices.

[0115] like Figure 6 As shown, a demand data prediction device 600 includes: a second acquisition unit 601 and a generation unit 602. The second acquisition unit 601 is configured to acquire historical demand data and a demand parameter information set sequence corresponding to a target time, wherein the demand parameter information set sequence is generated based on a demand information generation method; the generation unit 602 is configured to generate demand prediction data for a target future time according to the historical demand data and the demand parameter information set sequence.

[0116] It can be understood that the units recorded in the demand data prediction device 600 are similar to those in the reference Figure 4 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the demand data prediction device 600 and the units included therein, and will not be described in detail here.

[0117] Reference below Figure 7 , which shows an electronic device (eg, Figure 1 Schematic diagram of the structure of the electronic device 101)700. Figure 7 The electronic device 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.

[0118] like Figure 7 As shown, the electronic device 700 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory 702 or a program loaded from a storage device 708 into a random access memory 703. Various programs and data required for the operation of the electronic device 700 are also stored in the random access memory 703. The processing device 701, the read-only memory 702, and the random access memory 703 are connected to each other via a bus 704. An input / output interface 705 is also connected to the bus 704.

[0119] Typically, the following devices may be connected to the input / output interface 705: an input device 706 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 707 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 708 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 709. The communication device 709 may allow the electronic device 700 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The electronic device 700 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 7Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0120] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include 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 some such embodiments, the computer program can be downloaded and installed from a network through a communication device 709, or installed from a storage device 708, or installed from a read-only memory 702. When the computer program is executed by the processing device 701, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0121] It should be noted that the computer-readable medium in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may 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 wires, 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 some embodiments of the present disclosure, the 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 some embodiments of the present disclosure, the 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. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The 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 conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0122] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0123] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains a demand data sequence for a predefined event sequence; for each demand data in the demand data sequence, performs the following update steps: using the first initial event demand impact parameter for the demand data, generates the first user real demand data at the time corresponding to the demand data; based on the first user real demand data, using the initial demand trend parameter for the target demand data, generates the second user real demand data at the time corresponding to the target demand data, wherein the time corresponding to the target demand data is the next time of the time corresponding to the demand data; based on the second user real demand data, using the second initial event demand impact parameter for the target demand data, generates the demand forecast data at the time corresponding to the target demand data; based on the demand forecast data and the target demand data, performs parameter gradient update on the initial demand trend parameter, the first initial event demand impact parameter and the second initial event demand impact parameter to generate a demand parameter information set. Obtain historical demand data and a sequence of demand parameter information sets corresponding to a target time, wherein the above-mentioned sequence of demand parameter information sets is generated based on a demand information generation method; and generate demand forecast data for a target future time based on the above-mentioned historical demand data and the above-mentioned sequence of demand parameter information sets.

[0124] Computer program code for performing the operations of some embodiments 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 via 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., via the Internet using an Internet service provider).

[0125] 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.

[0126] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The units described may also be provided in a processor, for example, may be described as: a processor includes a first acquisition unit and a first execution unit. The names of these units do not, in some cases, constitute limitations on the units themselves, for example, the first acquisition unit may also be described as a "unit for acquiring a sequence of required data for a predefined sequence of events".

[0127] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0128] Some embodiments of the present disclosure further provide a computer program product, including a computer program, which implements any of the above-mentioned demand information generating methods or demand data prediction methods when executed by a processor.

[0129] The above descriptions are only some preferred embodiments 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 embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A method for generating demand information, comprising: Obtaining a sequence of required data for a predefined sequence of events; For each demand data in the demand data sequence, the following update steps are performed: Generate first user real demand data at a time corresponding to the demand data by using a first initial event demand impact parameter for the demand data; According to the first user real demand data, using the initial demand trend parameters for the target demand data, generating the second user real demand data at the time corresponding to the target demand data, wherein the time corresponding to the target demand data is the next time of the time corresponding to the demand data; According to the second user real demand data, using the second initial event demand impact parameter for the target demand data, generating demand forecast data at a time corresponding to the target demand data; According to the demand forecast data and the target demand data, the initial demand trend parameter, the first initial event demand impact parameter and the second initial event demand impact parameter are updated with a parameter gradient to generate a demand parameter information set.

2. The method according to claim 1, wherein: The predefined events in the predefined event sequence have corresponding event demand impact time ranges; as well as The step of using the first initial event demand impact parameter for the demand data to generate first user real demand data at a time corresponding to the demand data includes: In response to determining that the time corresponding to the demand data is within the event demand impact time range corresponding to the target predefined event, determining the result of adding the first initial event demand impact parameter and the target value as first added information; A result of dividing the demand data by the first added information is determined as the real demand data of the first user.

3. The method according to claim 2, wherein: The method further comprises: In response to determining that the time corresponding to the demand data is not within the event demand impact time range corresponding to the target predefined event, the demand data is determined as the real demand data of the first user.

4. The method according to claim 2, wherein: The step of generating demand forecast data at a time corresponding to the target demand data according to the second user real demand data and using the second initial event demand impact parameter for the target demand data includes: In response to determining that the time corresponding to the demand data is within the event demand impact time range corresponding to the target predefined event, determining the result of adding the second initial event demand impact parameter and the target value as second added information; The multiplication result of the second added information and the second user's actual demand data is determined as demand forecast data.

5. The method according to claim 1, wherein: The step of generating, according to the first user real demand data, the second user real demand data at a time corresponding to the target demand data by using the initial demand trend parameter for the target demand data includes: The result of multiplying the initial demand trend parameter and the target demand data is determined as the real demand data of the second user.

6. The method according to claim 1, wherein: There are corresponding event requirement impact range mask parameters for the predefined events in the predefined event sequence; as well as The step of using the first initial event demand impact parameter for the demand data to generate first user real demand data at a time corresponding to the demand data includes: Determine a first multiplication result of a multiplication result of the event demand impact range mask parameter and the first initial event demand impact parameter; Determine the addition result of the first multiplication result and the target value as the third addition information; A result of dividing the demand data by the third added information is determined as the real demand data of the first user.

7. The method according to claim 6, wherein: The step of generating demand forecast data at a time corresponding to the target demand data according to the second user real demand data and using the second initial event demand impact parameter for the target demand data includes: The event demand impact range mask parameter is multiplied by the second initial event demand impact parameter to obtain a second multiplication result; Add the second multiplication result and the target value to obtain fourth addition information; The product of the fourth added information and the second user's actual demand data is determined as demand forecast data.

8. The method according to claim 7, wherein: The step of performing parameter gradient updating on the initial demand trend parameter, the first initial event demand impact parameter, and the second initial event demand impact parameter according to the demand forecast data and the target demand data to obtain a demand parameter information set includes: According to the demand forecast data and the target demand data, the initial demand trend parameter, the first initial event demand impact parameter, the event demand impact range mask parameter and the second initial event demand impact parameter are updated with parameter gradients to obtain the first updated event demand impact parameter information, the second updated event demand impact parameter information, the demand trend parameter information and the event demand impact range mask parameter information.

9. A demand data forecasting method, comprising: Acquire historical demand data and a demand parameter information set sequence corresponding to a target time, wherein the demand parameter information set sequence is generated based on the method according to any one of claims 1 to 8; Demand forecast data for a target future time is generated based on the historical demand data and the demand parameter information set sequence.

10. A demand information generating device, comprising: A first acquisition unit is configured to acquire a demand data sequence for a predefined event sequence; The execution unit is configured to perform the following update steps for each demand data in the demand data sequence: using the first initial event demand impact parameter for the demand data to generate the first user real demand data at the time corresponding to the demand data; based on the first user real demand data, using the initial demand trend parameter for the target demand data to generate the second user real demand data at the time corresponding to the target demand data, wherein the time corresponding to the target demand data is the next time of the time corresponding to the demand data; According to the second user's actual demand data, using the second initial event demand impact parameters for the target demand data, generate demand forecast data for the time corresponding to the target demand data; based on the demand forecast data and the target demand data, perform parameter gradient update on the initial demand trend parameters, the first initial event demand impact parameters and the second initial event demand impact parameters to generate a demand parameter information set.

11. A demand data forecasting device, comprising: A second acquisition unit is configured to acquire historical demand data and a demand parameter information set sequence corresponding to a target time, wherein the demand parameter information set sequence is generated based on the method according to any one of claims 1 to 8; The generating unit is configured to generate demand forecast data for a target future time according to the historical demand data and the demand parameter information set sequence.

12. An electronic 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 9.

13. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

14. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 9.

Images