# US 2023/0274332 A1 · Method and apparatus for generating recommendation reason, and storage medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0274332 A1
- Document ID: US20230274332A1
- Status: Published application
- Kind: A1
- Application number: 18/004,008
- Filed: 2021-06-25
- Published: 2023-08-31
- Earliest claimed: 2020-07-01
- Assignees: Beijing Wodong Tianjun Information Technology Co., Ltd.; Beijing Jingdong Century Trading Co., Ltd.
- Applicants: Beijing Wodong Tianjun Information Technology Co., Ltd.; Beijing Jingdong Century Trading Co., Ltd.
- Inventors: Hainan ZHANG; Hongshen CHEN; Zhuoye DING; Yongjun BAO; Weipeng YAN
- Web page: https://patentgrep.com/patent/US20230274332A1

## CPC

- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06Q 30/0631: {Recommending goods or services}
- G06F 16/3329: Natural language query formulation
- G06F 16/335: Filtering based on additional data, e.g. user or group profiles (filtering in web context G06F16/9535, G06F16/9536)
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/04: Inference or reasoning models
- G06Q 30/0251: Targeted advertisements
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The embodiment of the present application provides a method and apparatus for generating a recommendation reason, a device and a storage medium. Content information of an object to be recommended is acquired, and the recommendation reason of the object to be recommended is generated according to a pre-trained recommendation reason generation model and the content information, where the training data used by the recommendation reason generation model includes question-answer data and content information of multiple objects. In this technical solution, since the training of the recommendation reason generation model takes the question-answer data and the content information of multiple objects into account, commodities that users care about most are mined through the question-answer data, therefore, the recommendation reason generated by this solution can accurately target users’ needs and improve user experience.

## Claims

### Claim 1

A method for generating a recommendation reason, comprising:
acquiring content information of an object to be recommended; and
generating the recommendation reason of the object to be recommended according to a pre-trained recommendation reason generation model and the content information, training data used by the recommendation reason generation model comprising question-answer data and content information of multiple objects.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the generating the recommendation reason of the object to be recommended according to the pre-trained recommendation reason generation model and the content information comprises:
encoding the content information by using a preset encoder to obtain a content information vector; and
generating the recommendation reason of the object to be recommended according to the pre-trained recommendation reason generation model and the content information vector.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the content information comprises a title and an attribute, the encoding the content information by using the preset encoder to obtain the content information vector comprises:
encoding the title and the attribute by using the preset encoder respectively to obtain a title vector and an attribute vector; and
obtaining the content information vector according to the title vector, the attribute vector and a preset weight.

### Claim 4 (depends on 2)

The method according to claim 2, wherein the preset encoder comprises at least one of the following encoders:
a bidirectional long short-term memory network (LSTM) encoder, a unidirectional LSTM encoder or a transformer model.

### Claim 5 (depends on 1)

The method according to claim 1, wherein before the generating the recommendation reason of the object to be recommended according to the pre-trained recommendation reason generation model and the content information, the method further comprises:
acquiring the training data; and
training an initial model based on the training data and a target recommendation reason corresponding to the multiple objects to obtain the recommendation reason generation model.

### Claim 6 (depends on 5)

The method according to claim 5, wherein the acquiring the training data comprises:
acquiring the content information of the multiple objects;
acquiring the question-answer data of the multiple objects;
filtering the question-answer data and the content information to obtain valid data; and
correspondingly, the training the initial model based on the training data and the target recommendation reason corresponding to the multiple objects to obtain the recommendation reason generation model comprises:
training the initial model based on the content information of the multiple objects, the valid data and the target recommendation reason corresponding to the multiple objects to obtain the recommendation reason generation model.

### Claim 7 (depends on 5)

The method according to claim 5, wherein the initial model comprises:
a prior network module, configured to obtain a first recommendation reason according to a content information vector;
a posterior network module, configured to obtain a second recommendation reason according to the content information vector and a question-answer data vector; and
a decoding module, configured to obtain a predicted recommendation reason according to the first recommendation reason, the second recommendation reason and a target recommendation reason.

### Claim 8 (depends on 7)

The method according to claim 7, wherein the initial model further comprises:
a loss function calculating module, configured for at least one of the following purposes:
obtaining a first loss function according to the question-answer data vector and the target recommendation reason, the first loss function being used to indicate to adjust a relevant parameter in the decoding module;
obtaining a second loss function according to the predicted recommendation reason and the target recommendation reason, the second loss function being used to indicate to adjust a relevant parameter in the decoding module; and
obtaining a third loss function according to the first recommendation reason and the second recommendation reason, the third loss function being used to indicate to adjust at least one of a relevant parameter in the prior network module and/or a relevant parameter in the posterior network module.

### Claim 9

An apparatus for generating a recommendation reason, comprising a memory and a processor:
the memory is configured to store program instructions; and
the processor is configured to invoke the program instructions in the memory to:
acquire content information of an object to be recommended; and
generate the recommendation reason of the object to be recommended according to a pre-trained recommendation reason generation model and the content information, the training data used by the recommendation reason generation model comprising question-answer data and content information of multiple objects.

### Claim 10 (depends on 9)

The apparatus according to claim 9, wherein the processor is configured to:
encode the content information by using a preset encoder to obtain a content information vector; and
generate the recommendation reason of the object to be recommended according to the pre-trained recommendation reason generation model and the content information vector.

### Claim 11 (depends on 10)

The apparatus according to claim 10, wherein the content information comprises a title and an attribute, when being configured to encode the content information by using the preset encoder to obtain the content information vector, the processor is configured to:
encode the title and the attribute by using the preset encoder respectively to obtain a title vector and an attribute vector; and
obtain the content information vector according to the title vector, the attribute vector and a preset weight.

### Claim 12 (depends on 10)

The apparatus according to claim 10, wherein the preset encoder comprises at least one of the following encoders:
the bidirectional long short-term memory network (LSTM)-encoder, the unidirectional LSTM encoder or the transformer model.

### Claim 13 (depends on 12)

The apparatus according to claims 12, wherein the processor is further configured to:
acquire the training data; and
train an initial model based on the training data and a target recommendation reason corresponding to the multiple objects to obtain the recommendation reason generation model.

### Claim 14 (depends on 13)

The apparatus according to claim 13, wherein when being configured to acquire the training data, the processor is configured to:
acquire the content information of the multiple objects;
acquire the question-answer data of the multiple objects;
filter the question-answer data and the content information to obtain valid data; and
correspondingly, when being configured to train the initial model based on the training data and the target recommendation reason corresponding to the multiple objects to obtain the recommendation reason generation model, the processor is configured to:
train the initial model based on the content information of the multiple objects, the valid data and the target recommendation reason corresponding to the multiple objects to obtain the recommendation reason generation model.

### Claim 15 (depends on 13)

The apparatus according to claim 13, wherein the initial model comprises:
a prior network module, configured to obtain a first recommendation reason according to a content information vector;
a posterior network module, configured to obtain a second recommendation reason according to the content information vector and a question-answer data vector; and
a decoding module, configured to obtain a predicted recommendation reason according to the first recommendation reason, the second recommendation reason and a target recommendation reason.

### Claim 16 (depends on 15)

The apparatus according to claim 15, wherein the initial model further comprises:
a loss function calculating module, configured for at least one of the following purposes:
obtaining a first loss function according to the question-answer data vector and the target recommendation reason, the first loss function being used to indicate to adjust a relevant parameter in the decoding module;
obtaining a second loss function according to the predicted recommendation reason and the target recommendation reason, the second loss function being used to indicate to adjust a relevant parameter in the decoding module; and
obtaining a third loss function according to the first recommendation reason and the second recommendation reason, the third loss function being used to indicate to adjust a relevant parameter in the prior network module and/or a relevant parameter in the posterior network module.

### Claim 17

(canceled)

### Claim 18

A non transitory computer readable storage medium, wherein a computer program is stored on the readable storage medium; when the computer program is executed, following operations are implemented:
acquiring content information of an object to be recommended; and
generating the recommendation reason of the object to be recommended according to a pre-trained recommendation reason generation model and the content information, training data used by the recommendation reason generation model comprising question-answer data and content information of multiple objects.

### Claim 19 (depends on 2)

The method according to claim 2, wherein before the generating the recommendation reason of the object to be recommended according to the pre-trained recommendation reason generation model and the content information, the method further comprises:
acquiring the training data; and
training an initial model based on the training data and a target recommendation reason corresponding to the multiple objects to obtain the recommendation reason generation model.

### Claim 20 (depends on 3)

The method according to claim 3, wherein before the generating the recommendation reason of the object to be recommended according to the pre-trained recommendation reason generation model and the content information, the method further comprises:
acquiring the training data; and
training an initial model based on the training data and a target recommendation reason corresponding to the multiple objects to obtain the recommendation reason generation model.

### Claim 21 (depends on 4)

The method according to claim 4, wherein before the generating the recommendation reason of the object to be recommended according to the pre-trained recommendation reason generation model and the content information, the method further comprises:
acquiring the training data; and
training an initial model based on the training data and a target recommendation reason corresponding to the multiple objects to obtain the recommendation reason generation model.
