Methods and systems for anonymously tracking and/or analysing individuals based on biometric data
Methods and systems are provided for anonymously tracking and/or analyzing flow or movement of individual subjects and/or objects using biometric data. A computer-implemented method enabling anonymous estimation of the amount and/or flow of individual subjects and/or objects, referred to as individuals, in a population moving and/or coinciding between two or more subject states using biometric data includes receiving identifying data, wherein the identifying data includes and/or is based on biometric data, from two or more individuals; generating, online and by one or more processors, an anonymized identifier for each individual; and storing: the anonymized identifier of each individual together with data representing a subject state; and/or a skew measure of such an anonymized identifier.
1. A system comprising:
one or more processors configured to: receive, for each one of a multitude of individuals comprising individual subjects and/or objects in a population of individuals, identifying information representative of an identity of the individual, wherein the identifying information representative of the identity of the individual includes and/or is based on biometric data, and to generate anonymous identifier skew measures based on identifying information of one or more individuals, wherein anonymization takes place online in real-time and/or near real-time, immediately deleting the identifying information after processing;
a memory configured to store at least one anonymous identifier skew measure based on at least one of the generated identifier skew measures; and
an estimator configured to, by the one or more processors: receive, from said memory and/or directly from the one or more processors, a number of anonymous identifier skew measures, at least one identifier skew measure for each of at least two subject states of individuals, and to generate one or more population flow measures related to individuals passing from one subject state to another subject state based on the received anonymous identifier skew measures.
2. The system of claim 1 , wherein each identifier skew measure is generated based on two or more identifier density estimates and/or one or more values generated based on identifier density estimates.
3. The system of claim 1 , wherein each identifier skew measure is representing the skew of the identifying information of one or more individuals compared to the expected distribution of such identifying information in the population.
4. The system of claim 1 , wherein the identifier skew measure of the one or more processors is based on a group identifier representing a multitude of individuals.
5. The system of claim 4 , wherein the identifier skew measure is based on a visitation counter.
6. The system of claim 3 , wherein the identifier skew measure is generated based on the identifying information using a hashing function.
7. The system of claim 6 , wherein said one or more population flow measures includes the number and/or ratio of visitors passing from one tempo-spatial location to another tempo-spatial location.
8. The system of claim 7 , wherein at least one of said one or more population flow measures is generated at least partly based on a linear transform of counter information of two or more visitation counters.
9. The system of claim 8 , wherein the one or more processors and/or the identifying information representative of the identity of an individual is stochastic and wherein the stochasticity of the identifying information and/or the one or more processors is taken into consideration when generating the linear transform.
10. The system of claim 1 , wherein a baseline corresponding to the expected correlation from two independently generated populations is subtracted when generating the population flow measure(s).
11. The system of claim 1 , wherein each identifier skew measure is generated using a combination of the identifier and noise such that the contribution to the identifier skew measure is rendered anonymous due to a sufficient noise level for a visit to a subject state not being attributable to a specific identifier.
12. The system of claim 11 , wherein the identifier skew measure is based on two or more identifier density estimates.
13. The system of claim 1 , wherein
the one or more processors is configured to generate at least one identifier skew measure based on the anonymous identifier skew measure(s) stored in memory, and
anonymity is provided by having added sufficient noise to the anonymous identifier skew measure stored in memory, at one or more moments, for the total contribution from any single identifier to be undeterminable.
14. The system of claim 13 , wherein information about the generated noise sample(s) are also stored d and used for the lowering the variance in the population flow measure.
15. The system of claim 1 , wherein the identifying information representative of the identity of an individual includes and/or is based on at least one of: iris image, facial image, biometric feature vector and/or body image, fingerprint and/or gait.
16. The system of claim 1 , wherein the subject states include tempo-spatial locations, computer system states in an interaction with the user and/or states of the health and health monitoring of a subject.
17. The system of claim 1 , wherein the subject states are tempo-spatial locations or localities,
wherein the one or more processors is configured to generate a group identifier based on the identifying information of the individual to perform microaggregation of the population into corresponding groups,
wherein the memory is configured to store visitation counters for each of two or more group identifiers from each of two or more tempo-spatial locations or localities associated with the corresponding individuals, and
wherein the estimator is configured to receive counter information from at least two visitation counters, and generate one or more population flow measures related to individuals passing from one tempo-spatial location to another tempo-spatial location.
18. The system of claim 17 , wherein the one or more processors is configured to generate a group identifier based on the identifying information of the individual by using a hashing function.
19. The system of claim 17 , further comprising an input module configured to, by the one or more processors: receive location data, for each one of the multitude of individuals, representative of a tempo-spatial location, and match the tempo-spatial location of the individual with a visitation counter corresponding to the group identifier related to the individual, and each visitation counter for each group identifier also corresponds to a specific tempo-spatial location.
20. A system for anonymously tracking and/or analyzing flow or movement of individual subjects and/or objects, referred to as individuals, between subject states based on biometric data, the system comprising:
one or more processors configured to determine, for each individual in a population of multiple individuals, an anonymized identifier using identifying information representative of an identity of the individual as input, wherein the identifying information representative of the identity of the individual includes and/or is based on biometric data, each anonymized identifier corresponding to any individual in a group of individuals, the identity information of which results in the same anonymized identifier with probabilities such that no individual generates the anonymized identifier with greater probability than the sum of the probabilities of generating the identifier over all other individuals, wherein anonymization takes place online in real-time and/or near real-time, immediately deleting the identifying information after processing; and
a memory configured to store skew measures, one skew measure for each of two or more subject states, each skew measure being generated based on anonymized identifiers associated with the corresponding individuals associated with a specific corresponding subject state,
wherein one or more processors are configured to determine at least one population flow measure representative of the number of individuals passing from a first subject state to a second subject state based on the skew measures corresponding to the subject states.
21. The system of claim 20 , wherein the anonymized identifiers are group identifiers and/or noise-masked identifiers.
22. The system of claim 20 , wherein the system is configured to determine, for each individual in a population of multiple individuals, a group identifier based on a hashing function using information representative of an identity of the individual as input,
wherein each group identifier corresponds to a group of individuals, the identity information of which results in the same group identifier, thereby performing microaggregation of the population into at least two groups,
wherein the subject states are tempo-spatial locations or localities and the skew measures correspond to visitation data, and the system is configured to keep track, per group, of visitation data representing the number of visits to two or more tempo-spatial locations by individuals belonging to the group, and
wherein the system is configured to determine at least one population flow measure representative of the number of individuals passing from a first tempo-spatial location to a second tempo-spatial location based on visitation data per group identifier.
23. The system of claim 20 , wherein the system comprises processing circuitry and memory,
wherein the memory comprises instructions, which, when executed by the processing circuitry, causes the system to anonymously track and/or analyze flow or movement of individuals.
24. A computer-implemented method for enabling anonymous estimation of the amount and/or flow of individual subjects and/or objects, referred to as individuals, in a population moving and/or coinciding between two or more subject states, based on biometric data, said method comprising:
receiving identifying data from two or more individuals, wherein the identifying data of each individual includes and/or is based on biometric data;
generating, online and by one or more processors, an anonymized identifier for each individual, wherein anonymization takes place online in real-time and/or near real-time, immediately deleting the identifying information after processing; and
storing: the anonymized identifier of each individual together with data representing a subject state, and/or a skew measure of such an anonymized identifier.
25. The method of claim 24 , wherein the anonymized identifier is an anonymized identifier skew measure or other anonymized identifier that is effectively uncorrelated with the population flow.
26. The method of claim 24 , wherein the identifying data is correlated in some way with the population flow, and
wherein the skew measure is decorrelating and/or the anonymized identifier is generated with a decorrelation module and/or a decorrelating hashing module.
27. The method of claim 25 , wherein the anonymized identifier is an anonymous skew measure and the anonymized skew measure is generated based on a stored anonymous identifier skew measure to which noise has been added at one or more moments.
28. The method of claim 24 , wherein the anonymized identifier is generated by adding noise to the identifying data.
29. The method of claim 27 , wherein a compensation term to be added to a population flow estimate and/or necessary information for generating such a population flow estimate is calculated based on one or more generated noise sample(s) used by the method.
30. The method of claim 24 , wherein any two stored anonymized identifiers or identifier skew measures are not linkable to each other such that no pseudonymous identifier links the states in the stored data.
31. The method of claim 24 , wherein the anonymized identifier is a group identity, and the group identity of each individual is stored together with data representing subject state; and/or a counter per subject state and group identity.
32. The method of claim 31 , wherein the subject state is a tempo-spatial location, a computer system state in an interaction with a user and/or a state of health and/or health monitoring of a subject.
33. The method of claim 31 , wherein activity data representative of one or more actions or activities of each individual is also stored together with the corresponding group identity and data describing subject state.
34. The method of claim 24 , further comprising generating a population flow measure between two subject states.
35. A computer-implemented method for generating a measure of flow or movement of individual subjects and/or objects, referred to as individuals, between subject states, based on biometric data, said method comprising:
configuring one or more processors to receive anonymous identifier skew measures generated online in real-time and/or near real-time, based on biometrically based identifiers from visits and/or occurrences of individuals to and/or in each of two subject states, wherein each identifier being representative of the identity of an individual and includes including and/or being based on biometric data and being deleted immediately after processing;
generating, using said one or more processors, a population flow measure between two subject states by comparing the anonymous identifier skew measures between the subject states; and
storing said population flow measure to a memory.
36. The method of claim 35 , wherein the subject states are tempo-spatial locations, computer system states in interaction with a user and/or states of health and/or health monitoring of a subject.
37. The method of claim 35 , wherein the anonymous identifier skew measures are counters of group identities.
38. The method of claim 35 , wherein a single visitor present in one subject state cannot be reidentified in another subject state with high probability using the anonymous identifier skew measures.
39. The method of claim 35 , wherein the generating is not based on data already containing some measure of the population flow between the locations on an individual level and/or microaggregated level.
40. The method of claim 35 , wherein the anonymous identifier skew measures are effectively uncorrelated with the population flow.
41. The method of claim 35 , wherein the population flow estimate is generated based on a linear mapping from the anonymous identifier skew measures.
42. The method of claim 35 , wherein the population flow measure is also generated based on information about noise samples used to anonymize the data.
43. The method of claim 35 , wherein the configuring includes configuring one or more processors to receive counters of anonymous and approximately independently distributed group identities originating from visits of individuals to each of two subject states, and the generating includes generating a population flow measure between two subject states using a linear correlation between counters of group identities for each of the two subject states.
44. The method of claim 43 , wherein the subject states are tempo-spatial locations, and the population flow measure between two tempo-spatial locations is generated using a linear correlation between counters of group identities for each of the two subject states.
45. The method of claim 24 , wherein an anonymous identifier or identifier skew measure for each subject state is based on two or more identifier density estimates.
46. A non-transitory computer-readable medium having stored thereon a computer program comprising instructions, which when executed by at least one processor, cause the at least one processor to perform a computer-implemented method for enabling anonymous estimation of the amount and/or flow of individual subjects and/or objects, referred to as individuals, in a population moving and/or coinciding between two or more subject states, based on biometric data, said method comprising:
receiving identifying data from two or more individuals, wherein the identifying data of each individual includes and/or is based on biometric data;
generating, online and by one or more processors, an anonymized identifier for each individual, wherein anonymization takes place online in real-time and/or near real-time, immediately deleting the identifying information after processing; and
storing: the anonymized identifier of each individual together with data representing a subject state, and/or a skew measure of such an anonymized identifier.