Back to results
US 11,961,134 B2Granted
Proposal system, method, and computer-readable storage medium for storing program
AssigneeCanon Kabushiki Kaisha
InventorsMasataka Yoshida, Misato Furuya
Life of this patent
Estimating the term…
Abstract
In the proposal system, sales performance information that is related to a device is acquired and information that is related to a usage situation of a device is accepted from a customer. A device to be a purchase target is inferred by a learned model based on the information that is related to the usage situation of the device and the sales performance information, and then a proposal information is outputted as a result of that inference.
Claims12
A proposal system, comprising:
- a first processing circuit including at least one processor;
- and at least one memory;
- and
- a second processing circuit including at least one processor and at least one memory,
- the at least one memory of the first processing circuit storing instructions that, when executed by the at least one processor of the first processing circuit, cause the first processing circuit to:
- receive information related to a printer usage situation;
- receive purchased printer information;
- train a learning model using supervised data and at least the information related to a printer usage situation and the purchased printer information as learning data;
- and
- transmit at least a portion of the learning model to the second processing circuit;
- and
- the at least one memory of the second processing circuit storing instructions that, when executed by the at least one processor of the second processing circuit, cause the second processing circuit to
- receive the at least a portion of the learning model from the first processing circuit;
- acquire sales performance information of sales related to a purchased device made on a store;
- generate a learned model using the at least a portion of the learning model, wherein the learned model is generated using at least training data corresponding to a trend of a product and wherein the learned model has a smaller size than the learning model;
- accept information that is related to a usage situation of a user printer from a customer;
- infer a purchase target device using the learned model, based on the information that is related to the usage situation of the user printer that was accepted from the customer and the sales performance information that was acquired;
- and
- output as proposal information a result of the inference,
- wherein
- the output proposal information preferentially outputs the result of the inference regarding a printer whose manufacturer is the same as that of a printer which was previously used by the customer.
18 more elements
A method that is executed in a proposal system having a first processing circuit and a second processing circuit, the method comprising:
- in the first processing circuit,
- receiving information related to a printer usage situation;
- receiving purchased printer information;
- training a learning model using supervised data and at least the information related to a printer usage situation and the purchased printer information as learning data;
- and
- transmitting at least a portion of the learning model to the second processing circuit;
- and
- in the second processing circuit,
- receiving the at least a portion of the learning model from the first processing circuit;
- acquiring sales performance information of sales related to a purchased device made on a store;
- generating a learned model using the at least a portion of the learning model, wherein the learned model is generated using at least training data corresponding to a trend of a product and wherein the learned model has a smaller size than the learning model;
- accepting information that is related to a usage situation of a user printer from a customer;
- inferring a purchase target device using the learned model, based on the accepted information that is related to the usage situation of the user printer and the acquired sales performance information;
- and
- outputting as proposal information a result of the inference,
- wherein
- the outputting preferentially outputs the result of the inference in the inferring regarding a printer whose manufacturer is the same as that of a printer which was previously used by the customer.
14 more elements
A non-transitory computer-readable storage medium that stores a program for causing a proposal system having a first processing circuit and a second processing circuit to perform a method comprising:
- in the first processing circuit,
- receiving information related to a printer usage situation;
- receiving purchased printer information;
- training a learning model using supervised data and at least the information related to a printer usage situation and the purchased printer information as learning data;
- and
- transmitting at least a portion of the learning model to the second processing circuit;
- and
- in the second processing circuit,
- receiving the at least a portion of the learning model from the first processing circuit;
- acquiring sales performance information of sales related to a purchased device made on a store;
- generating a learned model using the at least a portion of the learning model, wherein the learned model is generated using at least training data corresponding to a trend of a product and wherein the learned model has a smaller size than the learning model;
- accepting information that is related to a usage situation of a user printer from a customer;
- inferring a purchase target device using the learned model, based on the accepted information that is related to the usage situation of the user printer and the acquired sales performance information;
- and
- outputting as proposal information a result of the inference,
- wherein
- the outputting preferentially outputs the result of the inference in the inferring regarding a printer whose manufacturer is the same as that of a printer which was previously used by the customer.
14 more elements
Dependencies are inferred from the claim text.