Abstract: The disclosure discloses a temperature compensation circuit and method for a neural network computing-in-memory array. Reference arrays sparsely inserted in the computing-in-memory array are adopted to provide a reference voltage for ADCs, so that an input voltage and a reference voltage of the ADCs have a same temperature coefficient. Finally, after analog-to-digital conversion by the ADC, the digital output of the ADC is not affected by the external temperature, thereby ensuring the operational precision of the neural network. According to the temperature compensation circuit of the disclosure, the reference arrays have the same structure as the computing-in-memory array. The insertion density of the reference arrays is related to the temperature field where the computing-in-memory arrays are located.

Abstract: The disclosure discloses a temperature compensation circuit and method for a neural network computing-in-memory array. Reference arrays sparsely inserted in the computing-in-memory array are adopted to provide a reference voltage for ADCs, so that an input voltage and a reference voltage of the ADCs have a same temperature coefficient. Finally, after analog-to-digital conversion by the ADC, the digital output of the ADC is not affected by the external temperature, thereby ensuring the operational precision of the neural network. According to the temperature compensation circuit of the disclosure, the reference arrays have the same structure as the computing-in-memory array. The insertion density of the reference arrays is related to the temperature field where the computing-in-memory arrays are located.

Abstract: A photoelectric computing unit, a photoelectric computing array and a photoelectric computing method. The photoelectric computing unit includes a semiconductor multifunctional region structure, which includes at least one carrier control region, at least one coupling region, and at least one photon-generated carrier collection region and readout region.

Abstract: A method and system for processing service continuity are provided in the disclosure. The method comprises: a slave ATCF determines that a master ATCF is unavailable; the slave ATCF sends an allocated STN-SR to an SCC AS; the SCC AS sends an ATU-STI and a C-MSISDN to the slave ATCF according to the STN-SR; and the slave ATCF continues a service according to the STN-SR, the ATU-STI, and the C-MSISDN. Therefore, a problem in related art that how to recover a service as soon as possible when an exception occurs in the master ATCF is solved, so that an effect of rapidly continuing the service is achieved when an exception occurs in the master ATCF and there is no registration information of the UE.

Abstract: Provided are a method and device for sending identifier information or a call transfer request. The method for sending a call transfer request includes: determining that a call for which a UE initiates a transfer in a PS domain to a CS domain includes an emergency call; acquiring identifier information of an EATF to which the UE is anchored when initiating the emergency call; and initiating transfer of the emergency call of the UE in the CS domain according to the identifier information. By means of the technical solution, the problem that an emergency call cannot be transferred in a case of networking of multiple service domains is solved, and the effect of ensuring that transfer of the emergency call can be completed is further achieved.

Abstract: A method and system for processing service continuity are provided in the disclosure. The method comprises: a slave ATCF determines that a master ATCF is unavailable; the slave ATCF sends an allocated STN-SR to an SCC AS; the SCC AS sends an ATU-STI and a C-MSISDN to the slave ATCF according to the STN-SR; and the slave ATCF continues a service according to the STN-SR, the ATU-STI, and the C-MSISDN. Therefore, a problem in related art that how to recover a service as soon as possible when an exception occurs in the master ATCF is solved, so that an effect of rapidly continuing the service is achieved when an exception occurs in the master ATCF and there is no registration information of the UE.