Information processing apparatus and non-transitory computer readable medium storing program

1. An information processing apparatus comprising:

a processor configured to

acquire a first recognition result and a first recognition probability on target data from a first recognizer,

acquire a second recognition result and a second recognition probability on the target data from a second recognizer,

execute checking of the first recognition result and the second recognition result,

execute first control in a case where the first recognition result and the second recognition result match each other as a result of the checking, and

execute second control in a case where the first recognition result and the second recognition result do not match each other as a result of the checking,

wherein the first control is control for executing either of first processing or second processing on the matched recognition result and outputting a processing result based on at least one of the first recognition probability or the second recognition probability,

wherein the second control is control for executing either of the first processing or the second processing on the first recognition result, and

wherein a human workload for the first processing is smaller than a human workload for the second processing.

2. The information processing apparatus according to claim 1 ,

wherein, in the first control, the first processing is executed on the matched recognition result in a case where the first recognition probability is higher than a threshold value, and the second processing is executed on the matched recognition result in a case where the first recognition probability is equal to or lower than the threshold value.

3. The information processing apparatus according to claim 2 ,

wherein the processor is configured to further

execute the first processing on the first recognition result in a case where the first recognition probability is higher than a second threshold value higher than the threshold value before executing the checking, and

the checking is executed in a case where the first recognition probability is equal to or lower than the second threshold value.

4. The information processing apparatus according to claim 1 ,

wherein, in the first control, the first processing is executed on the matched recognition result in a case where the first recognition probability is higher than a third threshold value and the second recognition probability is higher than a fourth threshold value, and the second processing is executed on the matched recognition result in a case where the first recognition probability is equal to or lower than the third threshold value or the second recognition probability is equal to or lower than the fourth threshold value.

5. The information processing apparatus according to claim 4 ,

wherein the third threshold value is lower than the threshold value for the first recognition probability for use in control for determining which of the first processing and the second processing is to be executed on the matched recognition result in a case where the second recognition probability is not used in the first control.

6. The information processing apparatus according to claim 2 ,

wherein the second control is control for executing the first processing on the first recognition result in a case where the first recognition probability is higher than a second threshold value higher than the threshold value, and executing the second processing on the first recognition result in a case where the first recognition probability is equal to or lower than the second threshold value.

7. The information processing apparatus according to claim 4 ,

wherein the second control is control for executing the first processing on the first recognition result in a case where the first recognition probability is higher than a second threshold value higher than the threshold value, and executing the second processing on the first recognition result in a case where the first recognition probability is equal to or lower than the second threshold value.

8. The information processing apparatus according to claim 5 ,

wherein the second control is control for executing the first processing on the first recognition result in a case where the first recognition probability is higher than a second threshold value higher than the threshold value, and executing the second processing on the first recognition result in a case where the first recognition probability is equal to or lower than the second threshold value.

9. The information processing apparatus according to claim 1 ,

wherein, in the first control, control for determining which of the first processing and the second processing is to be executed on the matched recognition result is executed based on both of the first recognition probability and the second recognition probability.

10. The information processing apparatus according to claim 9 ,

wherein the processor is configured to further

execute the first processing on the first recognition result in a case where the first recognition probability is higher than a fifth threshold value before executing the checking, and

execute the first processing on the second recognition result in a case where the second recognition probability is higher than a sixth threshold value before executing the checking, and

the checking is executed in a case where the first recognition probability is equal to or lower than the fifth threshold value and the second recognition probability is equal to or lower than the sixth threshold value.

11. The information processing apparatus according to claim 1 ,

wherein the processor is configured to further

acquire a k-th recognition result and a k-th recognition probability on the target data from a k-th recognizer for each k from k=3 to k=N (where N is an integer equal to or greater than 3),

execute checking of the k-th recognition result for each k from k=1 to k=N in the checking, and

execute third control instead of the first control in a case where all of the k-th recognition result for each k from k=1 to k=N match one another as a result of the checking, and

the third control is control for executing either of the first processing or the second processing on the matched recognition result and outputting a processing result based on at least one of the k-th recognition probability for each k from k=1 to k=N.

12. A non-transitory computer readable medium storing a program that causes a computer to execute processing for

acquiring a first recognition result and a first recognition probability on target data from a first recognizer,

acquiring a second recognition result and a second recognition probability on the target data from a second recognizer,

executing checking of the first recognition result and the second recognition result,

executing first control in a case where the first recognition result and the second recognition result match each other as a result of the checking, and

executing second control in a case where the first recognition result and the second recognition result do not match each other as a result of the checking,

wherein the first control is control for executing either of first processing or second processing on the matched recognition result and outputting a processing result based on at least one of the first recognition probability or the second recognition probability,

wherein the second control is control for executing either of the first processing or the second processing on the first recognition result, and

wherein a human workload for the first processing is smaller than a human workload for the second processing.