Ji I Chen

20220414592, Dec 29, 2022

Jun 25, 2021

17/359486

- San Francisco CA, US
Ji Chen - Mountain View CA, US
Soren Zeliger - Oakland CA, US
Yijia Chen - Oakland CA, US

G06Q 10/08

An online concierge system displays an interface to a user identifying an estimated time of arrival for an order. To generate the estimated time of arrival for the order, the online concierge system trains a prediction engine to predict delivery time based on a predicted selection time for a shopper to select the order for fulfillment and predicted travel time for the shopper to deliver items of the order to a location identified by the order. The online concierge system generates a policy optimization model that computes an adjustment for the predicted delivery time. The adjustment is determined by solving a stochastic optimization problem with a constraint on a probability of the order being delivered after the estimated time of arrival. The predicted delivery time combined with the adjustment determines the estimated time of delivery displayed to the user to balance between minimizing late deliveries and wait times.

20220358443, Nov 10, 2022

May 5, 2021

17/308996

- San Francisco CA, US
Ji Chen - Mountain View CA, US
Chris Sun - Atherton CA, US
Yile Liu - Sunnyvale CA, US
Yijia Chen - Oakland CA, US

G06Q 10/06
G06Q 10/08

An online concierge system allows users to order items within discrete time intervals later than a time when an order was received. Each order may require a different set of characteristics for fulfilment by shoppers. Because different shoppers may have different capabilities, it is most efficient to reserve shoppers with specialized characteristics for orders that require them. The online concierge system maintains a set of hierarchical structures for different characteristics of shoppers, with each level in a hierarchical structure having a value. To select a shopper to fulfill an order, the online concierge system scores identifies groups of shoppers having characteristics capable of fulfilling the order based on levels in the hierarchical structure for each characteristic of a group. A shopper from a group having a minimum score is selected to fulfill the order.

20220292580, Sep 15, 2022

Mar 15, 2021

17/202190

- San Francisco CA, US
Zi Wang - Mountain View CA, US
Site Wang - San Francisco CA, US
Yijia Chen - Oakland CA, US
Mingzhe Zhuang - Los Altos Hills CA, US
Ji Chen - Mountain View CA, US
Deepak Tirumalasetty - Castro Valley CA, US

G06Q 30/06
G06Q 10/06
G06Q 30/02
G06Q 10/08

An online concierge system allows users to order items within discrete time intervals later than a time when an order was received. The online concierge system allocates a specified percentage of an estimated number of shoppers during a discrete time interval to fulfilling orders received before the discrete time interval. An order may include a flag authorizing flexible fulfillment of the order along with a discrete time interval, which allows the order to be fulfilled earlier than the identified discrete time interval. The online concierge system generates groups of multiple orders authorizing flexible fulfillment and determines a cost for fulfilling different groups of orders. The online concierge system identifies a group of orders authorizing flexible fulfillment having a minimum cost for fulfillment by a shopper, allowing for more allocation of shoppers by enabling grouping of orders identifying different discrete time intervals.

20230034221, Feb 2, 2023

Jul 29, 2021

17/389281

- San Francisco CA, US
Ji Chen - Mountain View CA, US
Zi Wang - Mountain View CA, US
Soren Zeliger - Oakland CA, US
Ganesh Krishnan - San Francisco CA, US
Wa Yuan - Alameda CA, US
Michael Scheibe - San Francisco CA, US

G06Q 30/02
G06Q 30/06
G06Q 10/06
G06N 20/00
G06N 5/04

An online concierge system allows users to order items within discrete time intervals later than a time when an order was received or for short-term fulfillment when the order was received. To account for a number of shoppers available to fulfill orders during different discrete time intervals and numbers of orders for fulfillment during different discrete time intervals, the online concierge system specifies a target rate for orders fulfilled later than a specified discrete time interval and a threshold from the target rate. A trained machine learning model periodically predicts a percentage of orders being fulfilled late, with an order associated with a predicted percentage when the order was received. The online concierge system increases a price of orders associated with predicted percentages greater than the threshold from the target rate. The increased price of an order is determined from a price elasticity curve and the predicted percentage.

20210042619, Feb 11, 2021

Jul 30, 2020

16/944019

- Mountain View CA, US
Sricharan KUMAR - Mountain View CA, US
Ji CHEN - Mountain View CA, US
Debasish DAS - Mountain View CA, US

G06N 3/08
G06N 3/04

Certain aspects of the present disclosure provide techniques for performing finite rank deep kernel learning. In one example, a method for performing finite rank deep kernel learning includes receiving a training dataset; forming a set of embeddings by subjecting the training dataset to a deep neural network; forming, from the set of embeddings, a plurality of dot kernels; linearly combining the plurality of dot kernels to form a composite kernel for a Gaussian process; receiving live data from an application; and predicting a plurality of values and a plurality of uncertainties associated with the plurality of values simultaneously using the composite kernel.

20190305926, Oct 3, 2019

Mar 29, 2018

15/939795

Shenggao Li - Pleasanton CA, US
Ji Chen - Sunnyvale CA, US
Michael De Vita - Santa Clara CA, US
Fulvio Spagna - San Jose CA, US
Guluke Tong - San Ramon CA, US

H04L 7/033
G06F 13/40
G06F 13/42

Some embodiments include apparatus having sampling circuitry, a first circuit path, a second circuit path, and a digitally controlled oscillator (DCO). The sampling circuit samples an input signal and provide data information and phase error information based on the input signal. A first circuit path provides proportional control information based on the data information and phase error information. A second circuit path provides integral control information based on the data information and phase error information. The first circuit path operates at a frequency higher than the second circuit path. The DCO generates a clock signal and controls the timing of the clock signal based on the integral control information and the proportional control information.

20180367349, Dec 20, 2018

Aug 24, 2018

16/112391

- Santa Clara CA, US
Ji Chen - Sunnyvale CA, US

H04L 25/03
H04L 29/06

Some embodiments include apparatus and methods using a first latch in a decision feedback equalizer (DFE), a second latch in the DFE, and circuitry coupled to the first and second latches. The second latch includes a first input node coupled to an output node of the first latch. The circuitry includes a first input node coupled to the first output node, a second input node coupled to a second output node of the second latch, and an output node to provide information having a first output value based on first values of information at the first and second output nodes and a second output value based on second values of information at the first and second output nodes.

20180167240, Jun 14, 2018

Dec 8, 2016

15/372851

- Santa Clara CA, US
Ji CHEN - Sunnyvale CA, US

H04L 25/03
H04B 1/16
H04L 1/00

An apparatus is described that includes a receiver. The receive includes a data sampler, a positive error sampler and a negative error sampler each having respective inputs coupled to a same differential channel. The receiver also includes circuitry to drive the respective inputs, the circuitry to place a same calibration voltage on the differential channel to calibrate each of the data sampler, positive error sampler and negative error sampler with the same calibration voltage.